Systems, devices, and methods related to drug dosage guidance

Abstract

To provide improved systems, devices, and methods that take into account the physiology, dietary habits, and the like of a user, improve accuracy and reliability, determine a medication dose, and automatically deliver the medication dose.SOLUTION: A method includes, by a processor, by executing a pattern analysis algorithm that receives time-correlated analyte data of a user, which has been acquired during an analysis period, as input, the steps of: determining an analyte pattern type during at least one time-of-day (TOD) period; determining a before-meal correction factor on the basis of the analyte pattern type and a defined dosing strategy of the user for the analysis period by the processor executing the algorithm; and storing an indicator of before-meal correction in a computer memory and outputting to at least one of the user or a medication dosing device. The pattern analysis algorithm may be a glucose pattern analysis (GPA) algorithm.SELECTED DRAWING: Figure 1A

Description

Related applications

[0001] This application claims priority and benefit to U.S. Provisional Patent Application No. 62 / 882249 filed on 2 August 2019, U.S. Provisional Patent Application No. 62 / 979578 filed on 21 February 2020, U.S. Provisional Patent Application No. 62 / 979594 filed on 21 February 2020, U.S. Provisional Patent Application No. 62 / 979618 filed on 21 February 2020, and U.S. Provisional Patent Application No. 63 / 058799 filed on 30 July 2020, and the entire contents of those applications are incorporated herein by reference for all purposes. This application is a divisional application with Japanese Patent Application No. 2022-506627 filed on 31 July 2020 as its parent application. [Technical Field]

[0002] The subject matter described herein generally relates to systems, devices, and methods related to drug dose guidance, such as determining insulin dosages to treat elevated glucose levels caused by diabetes. [Background technology]

[0003] The detection and / or monitoring of analytes such as glucose, ketones, lactate, oxygen, and hemoglobin A1C can be critical to the health of individuals with diabetes. Patients with diabetes may suffer complications including loss of consciousness, cardiovascular disease, retinopathy, neuropathy, and nephropathy. Generally, patients with diabetes need to monitor their glucose levels to ensure they are maintained within a clinically safe range, and this information can also be used to determine whether and / or when insulin is needed to lower glucose levels in the body, or whether additional glucose is needed to raise glucose levels in the body.

[0004] Growing clinical data shows a strong correlation between the frequency of glucose monitoring and blood glucose control. However, despite this correlation, many individuals diagnosed with diabetes do not monitor their glucose levels as frequently as necessary due to a combination of factors, including inconvenience, difficulty in deciding whether to test, pain associated with glucose testing, and cost.

[0005] For patients who rely on medication (e.g., insulin) to treat or manage diabetes, it is desirable to have a system, device, or method that can automatically utilize glucose information collected by an analyte monitoring system to provide drug dosage guidance in an easily accessible manner as needed. Such a system, device, or method would further preferably take into account the physiology, diet, activity, and / or behavior of the user or patient receiving treatment when providing such drug dosage guidance, which could improve accuracy and reliability. Furthermore, in some situations, it would also be desirable that such a system, device, or method be able to automatically deliver the selected drug dose. [Overview of the Initiative] [Problems that the invention aims to solve]

[0006] For these and other reasons, there is a need for improved systems, methods, and devices related to drug dosage guidance. [Means for solving the problem]

[0007] This specification provides exemplary embodiments of systems, devices, and methods relating to drug dose guidance and, in some embodiments, drug delivery. According to one embodiment, many of the embodiments described herein include a dose guidance system comprising a display device, a sensor control device, and a drug delivery device. The dose guidance system may include a dose guidance application (e.g., software) that can determine and output dose guidance (e.g., recommendations regarding dosage, correction, and titration) to the patient. Furthermore, according to some embodiments, the dose guidance system may learn the patient's drug administration strategy during a learning period in which the dose guidance system can estimate key administration parameters. According to some embodiments, the dose guidance system may also provide guidance for titration and correction once the system is configured with the patient's current drug administration strategy. The dose guidance system may also provide guidance for different meal administration scenarios. For example, in some embodiments, the dose guidance system may provide dose guidance at or before the start of a meal or after the start of a meal. The dose guidance system may also provide dose guidance for an added meal (e.g., dessert) or for a "touch-up" dose to address high glucose levels after a meal. Exemplary system and safety features of the dose guidance system are also described.

[0008] Many of the embodiments provided herein include improved software functionality or graphical user interfaces for use in an analyte monitoring system, are highly intuitive and user-friendly, and provide rapid access to a user's physiological information. More specifically, these embodiments enable a user (or HCP) to quickly determine an appropriate drug therapy based on information related to the user's physiological condition, past dosing patterns, and other factors without having to perform the cumbersome task of examining large amounts of analyte data. Further, some of the GUI and GUI functionality enable a user (and their caregiver) to better understand and improve the user's dosing patterns as well as subsequent hypoglycemic and hyperglycemic episodes. Similarly, many of the other embodiments provided herein include improved software functionality of a dosing guidance system and provide dosing guidance to a user by enabling a safe titration strategy that minimizes hypoglycemic episodes, a method of changing dosing guidance depending on the dosing timing of a dose relative to the start time of a meal (e.g., before, at, or after the start of a meal), consideration of real-world events that affect the dosing strategy, post-meal alarms based on predicted probabilities of occurrence rather than thresholds, among others, but these are merely examples. Other improvements and advantages are also provided. The various configurations of these devices are described in more detail by way of non-limiting embodiments.

[0009] Other systems, devices, methods, features, and advantages of the subject matter described herein will be apparent to those skilled in the art upon consideration of the following figures and detailed description. All such additional systems, devices, methods, features, and advantages are included within this specification, are within the scope of the subject matter described herein, and are intended to be protected by the accompanying claims. The features of the illustrative embodiments should not be construed as limiting the claims unless such features are expressly recited in the claims. BRIEF DESCRIPTION OF THE DRAWINGS [[ID

[0010] The details of the subject matter described in this specification can become apparent by considering the accompanying drawings, both as to its structure and operation (like reference numerals in the drawings refer to like parts). The components in the drawings are not necessarily to scale, instead emphasis has been placed upon illustrating the principles of the subject matter. Further, all of the figures are intended to convey concepts, and relative sizes, shapes, and other detailed attributes may be shown schematically rather than literally or precisely. [Figure 1A] FIG. shows a block diagram of an exemplary embodiment of a dosing guidance system. [Figure 1B] FIG. shows a block diagram of an exemplary embodiment of a dosing guidance system. [Figure 2A] FIG. is a schematic diagram showing an exemplary embodiment of a sensor control device. [Figure 2B] FIG. is a block diagram showing an exemplary embodiment of a sensor control device. [Figure 3A] FIG. is a schematic diagram showing an exemplary embodiment of a drug delivery device. [Figure 3B] FIG. is a block diagram showing an exemplary embodiment of a drug delivery device. [Figure 4A] FIG. is a schematic diagram showing an exemplary embodiment of a display device. [Figure 4B] FIG. is a block diagram showing an exemplary embodiment of a display device. [Figure 5] FIG. is a block diagram showing an exemplary embodiment of a user interface device. [Figure 6-1] FIG. shows an exemplary glucose pattern report. [Figure 6-2] FIG. is a continuation of FIG. 6-1. [Figure 6-3] FIG. is a continuation of FIG. 6-2. [Figure 7] FIG. is a flowchart showing an exemplary embodiment of a portion of a process flow of a dosing guidance application directed to a learning method for estimating a patient's insulin dosing habit. [Figure 8A]This flowchart illustrates an exemplary embodiment of the process flow for operation by a dose guidance application for evaluating meal bolus titration for frequent injectable (MDI) drug therapy. [Figure 8B] This flowchart illustrates an exemplary embodiment of the process flow for operation by a dose guidance application for glucose pattern analysis (GPA). [Figure 8C] This figure shows an exemplary embodiment of a graph that displays information for determining the risk of hypoglycemia and other indicators for GPA. [Figure 8D] This flowchart illustrates various exemplary embodiments of an algorithm for evaluating dietary bolus titration for MDI insulin therapy. [Figure 8E] This flowchart illustrates various exemplary embodiments of an algorithm for evaluating dietary bolus titration for MDI insulin therapy. [Figure 8F] This flowchart illustrates various exemplary embodiments of an algorithm for evaluating dietary bolus titration for MDI insulin therapy. [Figure 8G] This flowchart illustrates various exemplary embodiments of an algorithm for evaluating dietary bolus titration for MDI insulin therapy. [Figure 8H] This flowchart illustrates various exemplary embodiments of an algorithm for evaluating dietary bolus titration for MDI insulin therapy. [Figure 9A] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance using a physiological dose algorithm. [Figure 9B] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance using a physiological dose algorithm. [Figure 9C] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance using a physiological dose algorithm. [Figure 10A] This flowchart illustrates an exemplary embodiment of the process flow for operation by a dose guidance application for correction factor titration. [Figure 10B] This flowchart illustrates how a user interface device is controlled to output data for adjusting correction coefficients in response to analyte data. [Figure 10C] This flowchart illustrates how a user interface device is controlled to output data for adjusting correction coefficients in response to analyte data. [Figure 11] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance for administration at or before the start of a meal. [Figure 12A] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance to be administered after the start of a meal. [Figure 12B] This flowchart illustrates an exemplary embodiment of an alternative method for determining dose guidance to be administered after the start of a meal. [Figure 12C] This flowchart illustrates an exemplary embodiment of an alternative method for determining dose guidance for administration after the start of a meal. [Figure 13] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance for administration in addition to additional meals. [Figure 14] This flowchart illustrates an exemplary embodiment of a method for determining dose guidance for administering a corrective dose. [Figure 15] This flowchart illustrates an exemplary embodiment of how to alert a target. [Figure 16A] This flowchart illustrates an exemplary embodiment of how to override dose guidance settings. [Figure 16B] This flowchart illustrates an exemplary embodiment of a method for detecting sensor faults. [Figure 16C] This flowchart illustrates an exemplary embodiment of a method for detecting changes in medication strategy. [Figure 16D]This flowchart illustrates an exemplary embodiment of a method for detecting discrepancies in medication strategies. [Figure 16E] This flowchart illustrates an exemplary embodiment of a method for managing frequent dosing. [Figure 16F] This flowchart illustrates an exemplary embodiment of a method for adjusting insulin dose guidance. [Figure 16G] This flowchart illustrates an exemplary embodiment of a method for managing medication strategies. [Figure 17A] This flowchart illustrates an exemplary embodiment of a method for recommending insulin dose titration. [Figure 17B] This flowchart illustrates another exemplary embodiment of a method for recommending insulin dose titration. [Figure 17C] This flowchart illustrates an exemplary embodiment of a method for recommending insulin dose titration during the nighttime period. [Figure 17D] This flowchart illustrates an exemplary embodiment of a method for recommending insulin dose titration in accordance with the duration of dinner. [Figure 17E] This flowchart illustrates an exemplary embodiment of a method for recommending insulin administration. [Figure 17F] This flowchart illustrates an exemplary embodiment of a method for determining whether insulin delivery is abnormal. [Figure 17G] This figure shows an exemplary embodiment of an exemplary tracking pair graph. [Figure 18A] This is a block diagram illustrating an exemplary embodiment of a part rotation system. [Figure 18B] This is a flowchart illustrating an exemplary embodiment of a method for monitoring drug injection sites. [Modes for carrying out the invention]

[0011] Before describing the subject matter of the present invention in detail, it should be understood that this disclosure is not limited to the specific embodiments described herein and may, of course, be modified in itself. Furthermore, it should be understood that the terms used herein are solely for the purpose of describing specific embodiments and are not intended to limit the scope of this disclosure, as it is limited only by the appended claims.

[0012] Generally, embodiments of the present disclosure include systems, devices, and methods relating to drug dose guidance. Dose guidance can be based on a broad range of user-specific information and information categories, such as the user's current and past analyte levels, current and past diet, current and past physical activity, current and past medical history, and other physiological information about the user. According to one embodiment, the dose guidance provided by the systems, devices, and methods of the present disclosure can be based not only on individual information categories but also on the expected impact that such information categories will have on the user's future analyte levels.

[0013] The dose guidance function may be implemented as a dose guidance application (DGA) that includes software and / or firmware instructions stored in the memory of a computing device and is executed by at least one processor or processing circuit. The computing device may be owned by a user or a healthcare professional (HCP), and the user or HCP may form an interface to the computing device via a user interface. According to some embodiments, the computing device may be a server or trusted computer system accessible over a network, and the dose guidance software may be presented to the user in the form of an interactive web page via a browser running on a local display device (having a user interface) that communicates with the server or trusted computer system over the network. In these embodiments and other embodiments, the dose guidance software may run across multiple devices, or partly run on the processing circuit of a local display device and partly on the processing circuit of a server or trusted computer system. When the DGA is described as performing an operation, it will be understood by those skilled in the art that such operation is performed according to instructions stored in computer memory (including instructions hardcoded into read-only memory) that cause the DGA to perform the operation described when executed by at least one processor of at least one computing device. In all cases, the operation can be performed alternatively by hardware (e.g., dedicated circuitry) that is hardware-integrated to perform the operation, as opposed to execution by instructions stored in memory.

[0014] Furthermore, as used herein, a system in which DGA is implemented may be referred to as a dose guidance system. A dose guidance system may be configured solely for the purpose of providing dose guidance, or it may be a multifunctional system in which dose guidance is only one aspect. For example, in some embodiments, the dose guidance system may also monitor the user's analyte level. In some embodiments, the dose guidance system may also deliver the drug to the user using an injection or infusion device, for example. In some embodiments, the dose guidance system may be capable of both analyte monitoring and drug delivery.

[0015] These and other embodiments described herein represent improvements in the fields of computer-based dose determination, analyte monitoring, and drug delivery systems. Specific features and potential advantages of the disclosed embodiments are further described below.

[0016] Before describing in detail embodiments of dose guidance, it is desirable to first describe an example of a dose guidance system on which a dose guidance application can be implemented.

[0017] Exemplary Embodiment of a Dosage Guidance System Figure 1A is a block diagram showing an exemplary embodiment of the dose guidance system 100. In this embodiment, the dose guidance system 100 is capable of providing dose guidance, monitoring one or more analytes, and delivering one or more drugs. This multifunctional example is used to illustrate the high level of interoperability and performance achieved by the system 100. However, in the embodiments described herein, the analyte monitoring component, the drug delivery component, or both may be omitted as desired.

[0018] Here, system 100 includes a sensor control device (SCD) 102 configured to collect analyte level information from the user, a drug delivery device (MDD) 152 configured to deliver drugs to the user, and a display device 120 configured to present information to the user and to receive input or information from the user. The structure and function of each device are described in detail herein.

[0019] System 100 is configured for highly interconnected and highly flexible communication between devices. Each of the three devices 102, 120, and 152 can communicate with each other directly (without intermediate electronic devices) or indirectly (via the cloud network 190, or via another device and then through the network 190, etc.). The bidirectional communication capability between devices and between devices and the network 190 is indicated by double arrows in Figure 1A. However, a person skilled in the art will understand that one or more devices (e.g., SCDs) may be capable of unidirectional communication, such as broadcast, multicast, or advertising communication. In any case, whether bidirectional or unidirectional, communication can be wired or wireless. The protocols controlling communication on each path may be the same or different, and may be proprietary or standardized. For example, wireless communication between devices 102, 120, and 152 can be performed according to Bluetooth (including Bluetooth Low Energy) standards, NFC (Near Field Communication) standards, Wi-Fi (802.11x) standards, mobile telephony standards, etc. All communications across various paths can be encrypted, and each device in Figure 1A can be configured to encrypt and decrypt those communications being sent and received. In any case, the communication paths in Figure 1A can be direct (e.g., Bluetooth or NFC) or indirect (e.g., Wi-Fi, mobile telephony, or other internet protocols). Embodiments of System 100 do not need to have the ability to communicate across all of the paths shown in Figure 1A.

[0020] In addition, although Figure 1A shows a single display device 120, a single SCD 102, and a single MDD 152, those skilled in the art will understand that system 100 may comprise multiple of any of the aforementioned devices. For illustrative purposes only, system 100 may comprise a single SCD 102 communicating with multiple (e.g., two, three, four, etc.) display devices 120 and / or multiple MDD 152s. Alternatively, system 100 may comprise multiple SCD 102s communicating with a single display device 120 and / or a single MDD 152. Furthermore, each of the multiple devices may be the same or different device type. For example, system 100 may comprise multiple display devices 120, including smartphones, handheld receivers, and / or smartwatches, each of which may communicate with the SCD 102 and / or MDD 152, as well as with each other.

[0021] Analyte data can be transferred autonomously between devices within system 100 (e.g., automatically according to a schedule) or in response to requests for analyte data (e.g., a request for analyte data is sent from the first device to the second device, and then the analyte data is sent from the second device to the first device). To accommodate more complex systems, other technologies for data communication, such as a cloud network 190, can also be employed.

[0022] Figure 1B is a block diagram showing another exemplary embodiment of the dose guidance system 100. Here, the system 100 includes an SCD 102, an MDD 152, a first display device 120-1, a second display device 120-2, a local computer system 170, and a trusted computer system 180 accessible by a cloud network 190. The SCD 102 and MDD 152 are able to communicate with each other and with the display device 120-1, which can aggregate information from the SCD 102 and MDD 152, process and display that information at a desired location, and function as a communication hub for transferring some or all of the information to the cloud network 190 and / or the computer system 170. Conversely, the display device 120-1 can receive information from the cloud network 190 and / or the computer system 170 and communicate some or all of the received information to the SCD 102, MDD 152, or both. The computer system 170 may be a personal computer, server terminal, laptop computer, tablet, or other suitable data processing device. The computer system 170 may include or present software for data management and analysis, as well as for communication with components within system 100. The computer system 170 can be used by a user or medical professional to display and / or analyze analyte data measured by the SCD 102. Furthermore, although Figure 1B shows a single SCD 102, a single MDD 152, and two display devices 120-1 and 120-2, those skilled in the art will understand that system 100 may include multiple of any of the aforementioned devices, and that each of the multiple devices may be of the same or different types.

[0023] Referring further to Figure 1B, according to some embodiments, a trusted computer system 180 may be owned physically or virtually via a secure connection by a manufacturer or distributor of the components of system 100 and can be used as a server to perform authentication of the devices of system 100 (e.g., devices 102, 120-n, 152), to securely store user data, and / or to provide data analysis programs (e.g., accessible via a web browser) for performing analysis of the user's measured analyte data and medical history. The trusted computer system 180 can also function as a data hub for routing and exchanging data among all devices communicating with system 180 via the cloud network 190. In other words, all devices of system 100 that can communicate with the cloud network 190 (e.g., directly using an internet connection or indirectly via other devices) can also communicate directly or indirectly with all other devices of system 100 that can communicate with the cloud network 190.

[0024] The display device 120-2 is shown communicating with the cloud network 190. In this example, device 120-2 may be owned by another user authorized to access the analytes and drug data of the person wearing the SCD 102. For example, the person owning display device 120-2 may be, as an example, the parent of a child wearing the SCD 102, or, as an example, the caregiver of an elderly patient wearing the SCD 102. System 100 can be configured to communicate the analytes and drug data about the wearer to another user authorized to access the data via the cloud network 190 (for example, via a trusted computer system 180).

[0025] Exemplary Embodiment of an Analytical Substance Monitoring Device The analyte monitoring function of the dose guidance system 100 can be implemented by including one or more devices capable of collecting, processing, and displaying the user's analyte data. Exemplary embodiments of such devices and methods of use are described in International Application No. 2018 / 152241 and U.S. Patent Application No. 2011 / 0213225, the entire contents of which are incorporated herein by reference for all purposes.

[0026] Analyte monitoring can be performed in numerous different ways. A "continuous analyte monitoring" device (e.g., a "continuous glucose monitoring" device) can, for example, automatically transmit data from a sensor control device to a display device automatically according to a schedule, with or without prompting. A "flash analyte monitoring" device (e.g., a "flash glucose monitoring" device or simply a "flash" device) can, as another example, transfer data from a sensor control device in response to a user-initiated data request (e.g., a scan) by a display device, using protocols such as NFC (Near Field Communication) or RFID (Radio Frequency Identification).

[0027] Analyte monitoring devices that utilize sensors configured to be partially or entirely placed within a user's body can be referred to as in vivo analyte monitoring devices. For example, an in vivo sensor can be placed within a user's body so that at least a portion of the sensor is in contact with bodily fluids (e.g., interstitial fluid (ISF), such as dermal fluid in the dermis or subcutaneous fluid below the dermis, or blood), and can measure the concentration of an analyte in those bodily fluids. In vivo sensors can utilize various types of sensing technologies (e.g., chemical, electrochemical, or optical). Some systems utilizing in vivo analyte sensors can also operate without requiring fingerstick calibration.

[0028] An "in vitro" device is a device that brings a sensor into contact with a biological sample outside the body (or "ex vivo"). These devices typically include a port to receive an analyte test strip carrying the user's bodily fluids, which can then be analyzed to determine the user's blood glucose level. Other ex vivo devices attempt to measure the user's internal analyte levels non-invasively, for example, by using optical techniques that can measure internal analyte levels without mechanically penetrating the user's body or skin. Both in vivo and ex vivo devices often include in vitro functionality (e.g., in vivo display devices that also include a test strip port).

[0029] This subject describes a sensor capable of measuring glucose concentration, but the detection and measurement of concentrations of other analytes are also within the scope of this disclosure. These other analytes include, for example, ketones, lactate, oxygen, hemoglobin A1C, acetylcholine, amylase, bilirubin, cholesterol, chorionic gonadotropins, creatine kinase (e.g., CK-MB), creatine, DNA, fructosamine, glutamine, growth hormone, hormones, peroxides, prostate-specific antigen, prothrombin, RNA, thyroid-stimulating hormone, and troponin. It is also possible to monitor the concentrations of drugs such as antibiotics (e.g., gentamicin, vancomycin), digitoxins, dytoxins, drugs of abuse, theophylline, and warfarin. The sensor can be configured to measure two or more different analytes at the same or different times. In some embodiments, the sensor control device can be coupled with two or more sensors, one sensor configured to measure a first analyte (e.g., glucose), and one or more other sensors configured to measure one or more different analytes (e.g., any of those described herein). In other embodiments, the user can wear two or more sensor control devices, each capable of measuring a different analyte.

[0030] The embodiments described herein can be used with any type of in vivo, in vitro, and ex vivo device capable of monitoring the aforementioned analytes, etc.

[0031] In many embodiments, the operation of the sensor can be controlled by the SCD102. The sensor can be mechanically and communicatively coupled to the SCD102, or simply communicatively coupled to the SCD102 using wireless communication technology. The SCD102 may include electronics and a power supply that enable and control the sensing of the analyte performed by the sensor. In some embodiments, the sensor or the SCD102 may be self-generating so as not to require a battery. The SCD102 may also include communication circuits for communicating with another device (e.g., a display device) which may or may not be localized to the user's body. The SCD102 can reside in the user's body (e.g., it can be attached to the user's skin, positioned in another way, or carried in the user's clothing). The SCD102 may also be implanted in the user's body along with the sensor. The functionality of the SCD102 can be divided between a first component implanted in the body (e.g., a component that controls the sensor) and a second component located on or outside the body (e.g., a relay component that communicates with the first component and further communicates with an external device such as a computer or smartphone). In other embodiments, the SCD102 may be located outside the body and configured to non-invasively measure the user's analyte levels. The sensor control device may also be referred to, to name a few, depending on the actual implementation or embodiment, as a "sensor control unit," an "on-body electronic device" device or unit, an "on-body" device or unit, an "in-body electronic device" device or unit, an "in-body" device or unit, or a "sensor data communication" device or unit.

[0032] In some embodiments, the SCD102 may include a user interface (e.g., a touchscreen) capable of processing analyte data and displaying the resulting calculated analyte levels to the user. In this case, the embodiments of dose guidance described herein can be implemented directly by the SCD102, either in whole or in part. In many embodiments, it may be desirable to have a display device that the user can use to read analyte levels and interface with the sensor control device, either because the physical form factor of the SCD102 is minimized (e.g., to minimize its appearance on the user's body), the sensor control device may be inaccessible to the user (e.g., if it is entirely embedded), or due to other factors.

[0033] Figure 2A is a side view of an exemplary embodiment of the SCD102. The SCD102 may include a case or mount 103 (Figure 2B) for sensor electronics, which can be electrically coupled to an analyte sensor 101, configured here as an electrochemical sensor. According to some embodiments, the sensor 101 may be configured to be partially present in the user's body (e.g., through the outermost surface of the skin), therein it may be in fluid contact with the user's bodily fluids and used together with the sensor electronics to measure the user's analyte-related data. An attachment structure 105, such as an adhesive patch, may be used to secure the case 103 to the user's skin. The sensor 101 may extend through the attachment structure 105 and protrude away from the case 103. Those skilled in the art will understand that other forms of attachment to the body and / or case 103 may be used in addition to, or instead of, adhesives, and are fully included within the scope of this disclosure.

[0034] The SCD102 can be applied to the body in any desired manner. For example, an insertion device (not shown), sometimes referred to as an applicator, can be used to position all or part of the analyte sensor 101 through the outer surface of the user's skin to come into contact with the user's bodily fluids. In this case, the insertion device can also position the SCD102 on the skin. In other embodiments, the insertion device can first position the sensor 101, and then subsequently couple (e.g., insert into a mount) accompanying electronic equipment (e.g., wireless transmission circuits and / or data processing circuits) with the sensor 101, either manually or with the help of a mechanical device. Examples of insertable devices are described in U.S. Patent Publications 2008 / 0009692, 2011 / 0319729, 2015 / 0018639, 2015 / 0025345, and 2015 / 0173661 and 2018 / 0235520, the entire contents of which are incorporated herein by reference for all purposes.

[0035] Figure 2B is a block diagram showing an exemplary embodiment of an SCD102 having an analyte sensor 101 and sensor electronics 104. The sensor electronics 104 can be implemented on one or more semiconductor chips (e.g., application-specific integrated circuits (ASICs), processors or controllers, memory, programmable gate arrays, etc.). In the embodiment of Figure 1B, the sensor electronics 104 includes an analog front-end (AFE) 110 configured to interface with the sensor 101 in an analog manner and convert analog signals to and / or from digital format (e.g., using an A / D converter), a power supply 111 configured to power the components of the SCD102, processing circuits 112, memory 114, timing circuits 115 (e.g., oscillators and phase-locked loops for providing clocks or other timings to the components of the SCD102), and communication circuits 116 configured to communicate wired and / or wirelessly with one or more devices outside the SCD102, such as a display device 120 and / or MDD 152.

[0036] The SCD102 can be implemented in a highly interconnected manner, where the power supply 111 is coupled to each component shown in Figure 2B, and these components that communicate or receive data, information, or commands (e.g., AFE110, processing circuit 112, memory 114, timing circuit 115, and communication circuit 116) can be coupled to communicate with all other such components, for example, via one or more communication connections or bus 118.

[0037] The processing circuit 112 may include one or more processors, microprocessors, controllers and / or microcontrollers, each of which may be a discrete chip or distributed among (and some of) several different chips. The processing circuit 112 may include onboard memory. The processing circuit 112 interfaces with the communication circuit 116 and can perform analog-to-digital conversion, encoding and decoding, digital signal processing, and other functions that facilitate converting data signals into formats suitable for wireless or wired transmission (e.g., in-phase and quadrature). The processing circuit 112 also interfaces with the communication circuit 116 and can perform the inverse functions necessary to receive wireless transmissions and convert them into digital data or information.

[0038] The processing circuit 112 can execute instructions stored in the memory 114. These instructions can cause the processing circuit 112 to process raw analyte data (or pre-processed analyte data) and reach a final calculated analyte level. In some embodiments, when executed, instructions stored in the memory 114 can cause the processing circuit 112 to process the raw analyte data and determine one or more of the following: a calculated analyte level, an average calculated analyte level within a predetermined time window, a calculated rate of change for the analyte level within a predetermined time window, and / or whether a calculated analyte index exceeds a predetermined threshold condition. These instructions can also cause the processing circuit 112 to read and act on received transmissions, adjust the timing of the timing circuit 115, process data or information received from other devices (e.g., calibration information, encryption or authentication information received from the display device 120), perform tasks to establish and maintain communication with the display device 120, interpret voice commands from the user, and transmit them to the communication circuit 116. In embodiments where the SCD102 includes a user interface, instructions can cause the processing circuit 112 to perform tasks such as controlling the user interface, reading user input from the user interface, displaying information on the user interface, and formatting data for display. The functions described herein, which are coded as instructions, can instead be implemented by the SCD102 using hardware or firmware designs that do not rely on the execution of software instructions stored to achieve the functions.

[0039] Memory 114 can be shared by one or more of the various functional units present in the SCD 102, or distributed among two or more functional units (for example, as separate memories present on different chips). Memory 114 can also be a separate chip itself. Memory 114 is non-temporary and can be volatile memory (e.g., RAM) and / or non-volatile memory (e.g., ROM, flash memory, F-RAM).

[0040] The communication circuit 116 can be implemented as one or more components (e.g., transmitters, receivers, transceivers, passive circuits, encoders, decoders, and / or other communication circuits) that perform functions for communication over their respective communication paths or links. The communication circuit 116 may include or be coupled to one or more antennas for wireless communication.

[0041] The power supply 111 may include one or more batteries, which may be rechargeable or single-use disposable batteries. Power management circuits may also be included to regulate battery charging, monitor the usage of the power supply 111, increase power, perform DC conversion, and so on.

[0042] Furthermore, an optional temperature sensor (not shown) can collect readings or measurements of skin temperature or sensor temperature. These readings or measurements can be communicated from the SCD102 to another device (e.g., a display device 120) (individually or as aggregated measurements over time). However, the temperature readings or measurements can be used in combination with software routines executed by the SCD102 or the display device 120 to correct or compensate for analyte measurements output to the user, instead of actually outputting the temperature measurements to the user, or in addition to this.

[0043] Exemplary Embodiments of Drug Delivery Devices The drug delivery function of the dose guidance system 100 can be achieved by including one or more drug delivery devices (MDDs) 152. An MDD 152 can be any device configured to deliver a specific dose of drug. An MDD 152 may also include a device that transmits dose-related data to the DGA, such as a pen cap, even if the device itself does not deliver the drug. An MDD 152 can be configured as a portable injection device (PID) capable of delivering a single dose per injection, such as a bolus. A PID is essentially a manually operated syringe, where the drug must be pre-loaded into the syringe or drawn from a container into the syringe before injection. However, in most embodiments, the PID includes electronic components to form an interface with the user and perform drug delivery. While a pen-like appearance is not mandatory, PIDs are often referred to as medication pens. PIDs with user interface electronic components are often referred to as smart pens. PIDs may be discarded after being used to deliver a single dose, or they may be durable and reused to deliver multiple doses over a period of time, such as a day, a week, or a month. PIDs are commonly used by users undergoing frequent daily injection (MDI) therapy, where injections are administered multiple times a day.

[0044] The MDD may also include a pump and an infusion set. The infusion set includes a cannula that is at least partially present in the recipient's body. This cannula is in fluid communication with the pump, which can repeatedly deliver the drug in small doses into the recipient's body through the cannula. The infusion set can be applied to the recipient's body using an infusion set applicator, and the infusion set is often left implanted for 2-3 days or longer. The pump device includes electronics that form an interface with the user to control the slow infusion of the drug. Both the PID and the pump can store the drug in a drug reservoir.

[0045] The MDD152 can function as part of a closed-loop system (e.g., an artificial pancreas system that does not require user intervention for operation), a semi-closed-loop system (e.g., an insulin loop system that requires little to no user intervention for operation, such as confirming dose changes), or an open-loop system. For example, the analyte levels of a diabetic patient can be repeatedly and automatically monitored by the SCD102, and this information can be used by the dose guidance embodiments described herein to automatically calculate or otherwise determine an appropriate drug dose to control the analyte levels of a diabetic patient, and then that dose can be delivered to the diabetic patient's body. This calculation can be performed in the MDD152 or any other device of system 100, and the resulting determined dose can then be transmitted to the MCD152.

[0046] In many embodiments, the dose guidance provided by the embodiments described herein pertains to the type of insulin (e.g., rapid-acting (RA), short-acting insulin, intermediate-acting insulin (e.g., NPH insulin), long-acting (LA), ultra-long-acting insulin, and mixed insulin) and is the same drug delivered by MDD152. Examples of insulin types include human insulin and synthetic insulin analogs. Insulin may also include premix formulations. However, the embodiments of dose guidance and the drug delivery capabilities of MDD152 described herein can also be applied to other non-insulin drugs. Such drugs may include, but are not limited to, exenatide, sustained-release exenatide, liraglutide, lixisenatide, semaglutide, pramulintide, metformin, SLGT1-i inhibitors, SLGT2-i inhibitors, and DPP4 inhibitors. Embodiments of dose guidance may also include combination therapies. Combination therapies include, but are not limited to, insulin and glucagon-like peptide-1 receptor agonists (GLP-1RAs), and insulin and pramulintide.

[0047] To facilitate the description of the dosage guidance embodiments herein, the MDD152 is often described in the form of a PID, specifically a smart pen. However, those skilled in the art will readily understand that the MDD152 may alternatively be configured as a pen cap, pump, or any other type of drug delivery device.

[0048] Figure 3A is a schematic diagram showing an exemplary embodiment of the MDD152 configured as a PID, specifically as a smart pen. The MDD152 may include a case 154 for electronics, an injection motor, and a drug reservoir (see Figure 3B) from which a drug can be delivered via a needle 156. The case 154 may include a removable or detachable cap or cover 157, which, when attached, can cover the needle 156 when not in use and then be removed for injection. The MDD152 may include a user interface 158, which can be implemented as a single component (e.g., a touchscreen for outputting information to and receiving input from the user) or as multiple components (e.g., a touchscreen or display combined with one or more buttons, switches, etc.). The MDD152 may also include an actuator 159 that can be moved, pressed, touched, or otherwise actuated to begin delivering a drug from the internal reservoir through the needle 156 into the recipient's body. According to some embodiments, the cap 157 and actuator 159 may also include one or more safety mechanisms to prevent separation and / or activation in order to mitigate the risk of injecting harmful drugs. Details of these safety mechanisms and others are described in U.S. Patent Publication No. 2019 / 0343385 ('385), which is incorporated herein by reference in its entirety for all purposes.

[0049] Figure 3B is a block diagram showing an exemplary embodiment of an MDD152 having electronic equipment 160 coupled to a power supply 161, and an electrically operated injection motor 162 similarly coupled to the power supply 161 and a drug reservoir. A needle 156 is shown in fluid communication with the reservoir 163, and a valve (not shown) may be present between the reservoir 163 and the needle 156. The reservoir 163 may be permanent or removable and replaceable with another reservoir containing the same or different drug. The electronic equipment 160 can be implemented on one or more semiconductor chips (e.g., application-specific integrated circuits (ASICs), processors or controllers, memory, programmable gate arrays, etc.). In the embodiment of Figure 3B, the electronic equipment 160 may include a high-level functional unit including processing circuitry 164, memory 165, communication circuitry 166 configured to communicate wired and / or wirelessly with one or more devices outside the MDD152 (e.g., display device 120), and user interface electronic equipment 168.

[0050] The MDD152 can be implemented in a highly interconnected manner, where the power supply 161 is coupled to each component shown in Figure 3B, and these components that communicate or receive data, information, or commands (e.g., processing circuit 164, memory 165, and communication circuit 166) can be coupled to all other such components in a communicative manner, for example, via one or more communication connections or bus 169.

[0051] The processing circuit 164 may include one or more processors, microprocessors, controllers and / or microcontrollers, each of which may be a discrete chip or distributed among (and some of) a number of different chips. The processing circuit 164 may include onboard memory. The processing circuit 164 interfaces with the communication circuit 166 and can perform analog-to-digital conversion, encoding and decoding, digital signal processing, and other functions that facilitate converting data signals into formats suitable for wireless or wired transmission (e.g., in-phase and quadrature). The processing circuit 164 also interfaces with the communication circuit 166 and can perform the inverse functions necessary to receive wireless transmissions and convert them into digital data or information.

[0052] The processing circuit 164 can execute software instructions stored in memory 165. These instructions can cause the processing circuit 164 to receive a selection or provision of a specified dose from the user (e.g., input via user interface 158 or received from another device), process a command to deliver the specified dose (e.g., a signal from actuator 159), and control the motor 162 to deliver the specified dose. These instructions can also cause the processing circuit 164 to read and operate on received transmissions, process data or information received from other devices (e.g., calibration information, encryption or authentication information received from display device 120), perform tasks to establish and maintain communication with display device 120, interpret voice commands from the user, and transmit them to communication circuit 166. In embodiments where the MDD 152 includes a user interface 158, instructions can cause the processing circuit 164 to control the user interface, read user input from the user interface (e.g., input of a drug dose for administration or input to confirm a recommended drug dose), display information on the user interface, format data for display, and so on. The functions described here, which are coded as instructions, can instead be implemented by the MDD152 using hardware or firmware designs that do not rely on the execution of software instructions stored to achieve the functions.

[0053] Memory 165 can be shared by one or more of the various functional units present in the MDD 152, or distributed among two or more functional units (for example, as separate memories present on different chips). Memory 165 can also be a separate chip itself. Memory 165 is non-temporary and can be volatile memory (e.g., RAM) and / or non-volatile memory (e.g., ROM, flash memory, F-RAM).

[0054] The communication circuit 166 can be implemented as one or more components (e.g., transmitters, receivers, transceivers, passive circuits, encoders, decoders, and / or other communication circuits) that perform functions for communication over their respective communication paths or links. The communication circuit 166 may include or be coupled to one or more antennas for wireless communication. Details of exemplary antennas can be found in Publication 385, the entire contents of which are incorporated herein by reference for all purposes.

[0055] The power supply 161 may include one or more batteries, which may be rechargeable or single-use disposable batteries. Power management circuits may also be included to regulate battery charging, monitor the usage of the power supply 161, increase power, perform DC conversion, and so on.

[0056] The MDD152 may also include an integrated or attachable in vitro glucose meter, which includes an in vitro test strip port (not shown) for receiving in vitro glucose test strips for performing in vitro blood glucose measurement.

[0057] Exemplary Embodiments of Display Devices The display device 120 can be configured to display information related to the system 100 to the user and to accept or receive user input also related to the system 100. The display device 120 can display recently measured analyte levels to the user in any number of forms. The display device can also display other indicators that describe the user's analyte information, not just the user's past analyte levels (e.g., glucose control index (time in range), external glucose profile (AGP), hypoglycemia risk level, etc.). The display device 120 can display drug delivery information such as past dose information and the time and date of administration. The display device 120 can display alarms, alerts, or other notifications related to analyte levels and / or drug delivery.

[0058] The display device 120 may be a dedicated device for use with system 100 (e.g., an electronic device designed and manufactured primarily to form an interface with an analyte sensor and / or drug delivery device), or it may be a multifunctional, general-purpose computing device such as a handheld or portable mobile communication device (e.g., a smartphone or tablet), or a laptop, personal computer, or other computing device. The display device 120 may be configured as a mobile smart wearable electronic device assembly such as smart glasses, or a smartwatch or wristband. The display device and its variations may be referred to as, to name a few, a “reader device,” a “reader,” a “handheld electronic device” (or handheld), a “portable data processing” device or unit, an “information receiver,” a “receiver” device or unit (or simply a receiver), a “relay” device or unit, or a “remote” device or unit.

[0059] Figure 4A is a schematic diagram showing an exemplary embodiment of the display device 120, where the display device 120 includes a user interface 121 and a case 124 that holds the display device electronics 130 (Figure 4B). The user interface 121 can be implemented as a single component (e.g., a touchscreen capable of input and output) or as multiple components (e.g., a display and one or more devices configured to receive user input). In this embodiment, the user interface 121 includes a touchscreen display 122 (configured to display information and graphics and to accept user input by touch) and input buttons 123, both of which are coupled to the case 124.

[0060] The display device 120 may have stored software (for example, software downloaded by the manufacturer or by the user in the form of one or more “apps” or other software packages) that forms an interface to the SCD 102, MDD 152, and / or the user. In addition, or instead, the user interface may be controlled by a web page displayed in a browser or other internet interface software that can run on the display device 120.

[0061] Figure 4B is a block diagram of an exemplary embodiment of a display device 120 with a display device electronic device 130. Here, the display device 120 includes a user interface 121 with a display 122 and input components 123 (e.g., buttons, actuators, touch-sensitive switches, capacitive switches, pressure-sensitive switches, jog dials, microphones, speakers, etc.), processing circuits 131, memory 125, communication circuits 126 configured to communicate with and / or from one or more other devices outside the display device 120, a power supply 127, and timing circuits 128 (e.g., oscillators and phase-locked loops for providing clocks or other timing to the components of the SCD 102). Each of the aforementioned components can be implemented as one or more different devices or integrated into a multifunction device (e.g., integration of the processing circuits 131, memory 125, and communication circuits 126 on a single semiconductor chip). The display device 120 can be implemented in a highly interconnected manner, with the power supply 127 coupled to each component shown in Figure 4B, and those components that communicate or receive data, information, or commands (e.g., user interface 121, processing circuit 131, memory 125, communication circuit 126, and timing circuit 128) can be coupled communicatively to all other such components, for example, via one or more communication connections or bus 129. Figure 4B is a simplified representation of typical hardware and functionality present in the display device, and those skilled in the art will readily recognize that other hardware and functionality (e.g., codecs, drivers, glue logic) may also be included.

[0062] The processing circuit 131 may include one or more processors, microprocessors, controllers and / or microcontrollers, each of which may be a discrete chip or distributed among (and some of) several different chips. The processing circuit 131 may include onboard memory. The processing circuit 131 interfaces with the communication circuit 126 and can perform analog-to-digital conversion, encoding and decoding, digital signal processing, and other functions that facilitate converting data signals into formats suitable for wireless or wired transmission (e.g., in-phase and quadrature). The processing circuit 131 also interfaces with the communication circuit 126 and can perform the inverse functions necessary to receive wireless transmissions and convert them into digital data or information.

[0063] The processing circuit 131 can execute software instructions stored in memory 125. These instructions can cause the processing circuit 131 to process raw analyte data (or pre-processed analyte data) and reach the corresponding analyte level suitable for display to the user. These instructions can cause the processing circuit 131 to read, process, and / or store administration instructions from the user and transmit the administration instructions to MDD 152. These instructions can cause the processing circuit 131 to execute user interface software adapted to present an interactive group of graphical user interface screens to the user for the purpose of configuring system parameters (e.g., alarm thresholds, notification settings, display preferences, etc.), presenting current and past analyte level information to the user, presenting current and past drug delivery information to the user, collecting other non-analyte information from the user (e.g., information on meals consumed, activities performed, drugs administered, etc.), and presenting notifications and alarms to the user. These instructions can also cause the processing circuit 131 to transmit to the communication circuit 126, and to perform tasks such as reading and acting on received transmissions, reading input from the user interface 121 (e.g., inputting the drug dosage to be administered or confirming the recommended drug dosage), displaying data or information on the user interface 121, adjusting the timing of the timing circuit 128, processing data or information received from other devices (e.g., analyte data, calibration information, encryption or authentication information received from the SCD 102), performing tasks to establish and maintain communication with the SCD 102, and interpreting voice commands from the user. The functions described herein, which are coded as instructions, can instead be implemented by the SCD 102 using hardware or firmware designs that do not rely on the execution of software instructions stored to achieve the functions.

[0064] The memory 125 can be shared by one or more of the various functional units present within the display device 120, or distributed among two or more functional units (for example, as separate memories present on different chips). The memory 125 can also be a separate chip itself. The memory 125 is non-temporary and can be volatile memory (e.g., RAM) and / or non-volatile memory (e.g., ROM, flash memory, F-RAM).

[0065] The communication circuit 126 can be implemented as one or more components (e.g., transmitters, receivers, transceivers, passive circuits, encoders, decoders, and / or other communication circuits) that perform functions for communication over their respective communication paths or links. The communication circuit 126 may include, or be coupled to, one or more antennas for wireless communication.

[0066] The power supply 127 may include one or more batteries, which may be rechargeable or single-use disposable batteries. Power management circuits may also be included to regulate battery charging, monitor the usage of the power supply 127, increase power, perform DC conversion, and so on.

[0067] The display device 120 may also include one or more data communication ports (not shown) for wired data communication with external devices such as a computer system 170, SCD102, or MDD152. The display device 120 may also include an integrated or attachable in vitro glucose meter, which includes an in vitro test strip port (not shown) for receiving in vitro glucose test strips for performing in vitro blood glucose measurements.

[0068] The display device 120 can display analyte data received from the SCD 102 and can also be configured to output alarms, alert notifications, glucose values, etc., which may be visual, auditory, tactile, or any combination thereof. In some embodiments, the SCD 102 and / or MDD 152 can also be configured to output alarms or alert notifications in visual, auditory, tactile form, or a combination thereof. Further details and other display embodiments can be found, for example, in U.S. Patent Publication 2011 / 0193704, the entire contents of which are incorporated herein by reference for all purposes.

[0069] Exemplary embodiments related to dosage guidance The following exemplary embodiments relate to the dose guidance function provided by the dose guidance system 100. In many embodiments, the dose guidance function is implemented as a set of software instructions stored and / or executed on one or more electronic devices. This dose guidance function will be referred to herein as a dose guidance application (DGA). In some embodiments, the DGA is stored, executed, and presented to the user on the same single electronic device. In other embodiments, the DGA may be stored and executed on one device and presented to the user on different electronic devices. For example, the DGA may be stored and executed on a trusted computer system 180 and presented to the user via a web page displayed through an internet browser running on a display device 120.

[0070] Therefore, many different embodiments exist in relation to the number and type of electronic devices used to store, execute, and present the DGA to the user. With regard to presentation to the user, a device configured to implement this capability will be referred to herein as a user interface device (UID) 200. Figure 5 is a block diagram showing an example of one embodiment of the UID 200. In this embodiment, the UID 200 includes a case 201 coupled with a user interface 202. The user interface 202 can output information to the user and receive input or information from the user. In some embodiments, the user interface 202 is a touchscreen. As shown herein, the user interface 202 includes a display 204 which may be a touchscreen and input components 206 (e.g., buttons, actuators, touch-sensitive switches, capacitive switches, pressure-sensitive switches, jog dials, microphones, touchpads, soft keys, keyboards, etc.).

[0071] Many of the devices described herein can be implemented as UID200. For example, the display device 120 is used as UID200 in many embodiments. In some embodiments, the MDD 152 can be implemented as UID200. In embodiments where the SCD 102 includes a user interface, the SCD 102 can be implemented as UID200. The computer system 170 can also be implemented as UID200.

[0072] Detection of MDI dosing strategies Turning to the DGA aspect, more specifically, the DGA can use the patient's dosing strategy and analyte-level knowledge to provide accurate dose guidance. This specification describes exemplary embodiments relating to automated detection of a patient's dosing strategy that can facilitate and expedite the setup of the DGA. Detection of the dosing strategy can be based on numerous characteristics of the monitored drug (e.g., insulin) dose. For example, in this embodiment, doses can be identified as basal or bolus based on the MDD152 used to administer the dose. Some patients may have multiple MDD152s. For example, a patient may have one MDD for administering long-acting insulin (e.g., basal dose) and another MDD for administering rapid-acting insulin (e.g., meal dose). Additionally, basal strategies can be classified as "single" or "split" basal dosing strategies using the count (e.g., number of doses) and timing of basal administrations per dose. For example, in a "split" basal dosing strategy, the daily basal dose of 20U can be divided into two 10U doses, one of which can be administered before bedtime and the other upon waking.

[0073] When consecutive bolus doses are administered in quick succession, the system can attempt to distinguish between the original meal dose, an increase to the original meal dose, or a corrective dose for inter-meal high glucose. When DGA detects a large dose following a small dose (both occurring near the start of a meal), it can group these doses as a single meal dose, even if the initial dose was a priming dose not injected into the patient. Subsequently, if a dose occurs much later than doses (groups) tagged as known meals and / or meal doses, DGA can tag the later dose as a corrective dose for post-meal high glucose or as a dose increasing the previous meal dose to account for any extra food consumed. Once a meal event is recognized based on the meal detector algorithm or a user-entered meal event, DGA uses the amount of the previous dosing event and its timing relative to the currently detected meal to help determine whether the previous dosing was the first of multiple meal dosings or a corrective for inter-meal high glucose. Corrective doses are expected to be smaller in size than meal doses. Furthermore, if the time elapsed between the previous medication and the current meal event is sufficiently long, it is reasonable to assume that these two events are not related to the treatment of the same glucose excursion event, thus ruling out the possibility that the previous medication was the first of multiple medications related to a given meal. Therefore, if the previous dose is sufficiently small compared to the meal dose recorded within this window over the past few days and sufficiently far from the current meal, the previous dose can be classified as a corrected dose event.

[0074] DGA can be configured to use a real-time meal detection algorithm and dosing time to identify doses added to the basal as bolus doses for breakfast, lunch, and / or dinner, as well as / or corrective doses. DGA can also be configured to use the number of daily bolus dosings to identify dosing strategies as basal only, basal + 1, basal + 2, etc.

[0075] These different scenarios and aspects of DGA will be discussed in more detail elsewhere in this specification.

[0076] Onboarding To enhance the safety profile of DGA, HCP can approve the learned insulin dosing parameters and the subsequent titrations calculated by DGA. Embodiments of DGA include numerous interaction methods between HCP and DGA, thereby providing HCP with relevant evidence for approving proposed dose learning and titrations in a concise and informative manner that improves the workflow.

[0077] For diabetic patients already on an insulin regimen, HCPs can leverage existing reports that provide insights into the patient's glucose patterns to identify users who may benefit from dose guidance. An embodiment of DGA provides a learning period during which the patient's medication strategy and tendencies can be categorized (e.g., while using DGS100). If insulin and glucose binding data further confirms that a user is a suitable candidate for DGA, for example, that DGA can learn a specific medication strategy, the insulin medication parameters learned during the learning period can serve as initial conditions for dose guidance that DGA may then titrate as needed. A method for HCP notification for DGA dose parameter initialization and titration can also be provided. This process streamlines DGA onboarding and titration, assisting both HCPs and users while ensuring DGA is used only by those who are directed to it. If DGA is unable to learn the patient's medication parameters, DGA can indicate a patient medication mismatch, which HCPs can use to address the mismatch.

[0078] The first step in identifying potential users of DGA could include an initial analysis of a patient's blood glucose control using glucose concentration profiles. To ensure that as many users as possible have access to DGA, this process can be made independent of the glucose monitoring methods currently being used by the user.

[0079] For diabetic patients currently using SCD102, a glucose pattern report may be available that includes key indicators, glucose concentration profiles (e.g., outpatient glucose profiles (AGP)), identified patterns at different time points, and titration and lifestyle suggestions to improve glucose levels when they are consistently outside the target range. This pattern can be identified using the GPA algorithm, as will be explained in more detail elsewhere. An exemplary glucose pattern report 250 is shown in Figure 6. Those skilled in the art will understand that the glucose pattern report 250 may be a graphical user interface output to the display of a computing device. The glucose pattern report 250 may include a glucose control index (TIR) ​​display 252 showing the percentage of time the patient's glucose level was below the target range (e.g., less than 70 mg / dL), within the target range (e.g., 70–180 mg / dL), and above the target range (e.g., greater than 180 mg / dL). The TIR display 252 can also report the amount of time the patient's glucose level was below the lower limit of the target range (e.g., less than 54 mg / dL) or above the upper limit of the target range (e.g., greater than 250 mg / dL). The TIR display 252 may include a histogram in which different ranges are displayed in different colors. For example, time below the target range may be displayed in red, time within the target range in green, and time above the target range in yellow or orange. The glucose pattern report 250 can also display the average glucose level 254 over a time period 264 of the report, for example, about 14 days. The glucose pattern report 250 can also display a glucose concentration profile 256, such as an external glucose profile (AGP). The glucose concentration profile 256 is a graph of glucose data over a time period of the report, and the various data points on the graph can be color-coded according to whether their glucose analyte levels are below, within, or above the target range. This color coding may correspond to the color coding of the TIR display 252.Boxes 258 surrounding different portions of the glucose concentration profile 256 highlight patterns detected according to the GPA algorithm described elsewhere in this specification (e.g., hyperglycemia, hypoglycemia, moderate or moderate hyperglycemia, moderate or moderate hypoglycemia, and combinations thereof).

[0080] Medication guidance 260 can also be provided in the glucose pattern report 250 if the patient's current therapy (e.g., basal + RA insulin, basal only, basal + SU, etc.) is known. Medication guidance can be provided in the form of text recommendations. General advice regarding insulin dose titration can be provided based on identified high-glucose and low-glucose patterns highlighted in box 258 in the glucose concentration profile 256. This general advice could be determined without access to data on the actual insulin dose administered. Recommendations can generally follow the rule of reducing any low patterns before reducing high patterns. If the glucose pattern report includes suggestions regarding insulin dose titration, the glucose pattern report 250 may also include suggestions that the patient is a good candidate for DGS100, which can facilitate conversation between the HCP and the patient before moving on to the learning period.

[0081] If the GPA algorithm identifies a highly variable pattern, self-care guidance 262 can be displayed in the glucose pattern report 250. Alternatively, the glucose concentration profile 256 may have such high variability values ​​that the logic behind the report cannot make specific suggestions; in this case, instead of the aforementioned case, the default is for the user to consult with an HCP about lifestyle or treatment changes.

[0082] As described above, for individuals who are not currently using a device or system (e.g., SCD102) associated with an application capable of generating a glucose pattern report 250, the HCP may suggest monitoring the patient with a different device or system so that a report 250 or similar can be generated. For example, a patient may wear an SCD102, configured in a masking or blind mode, in which the user is unable to access measured glucose levels and therefore unable to modify their behavior during this period, in order to collect glucose data over a period of several days or weeks. From this data, a glucose pattern report can be generated. If a proposed insulin titration is included in the glucose pattern report, the glucose pattern report 250 may also include a suggestion that the patient is a good candidate for DGS100 and may suggest a period for learning a drug dosing strategy.

[0083] During the learning period, MDD152 can be integrated into the glucose sensing system used for the initial screening, providing a more complete portrait of insulin-intensive diabetes management. The learning period can utilize algorithms, such as those described elsewhere in this specification, to detect the user's insulin dosing strategy. During the learning period, DGA can be configured to determine how the user determines mealtime doses. For example, DGA can determine whether the user determines mealtime doses based on carbohydrate counting, whether the user determines mealtime doses based on empirical methods such as learning appropriate dosages based on past or similar meal experiences, whether the user administers a fixed amount of insulin with meals, whether the user modifies the mealtime insulin dose (determined from fixed dose, carbohydrate counting, or empirical dose) based on pre-meal glucose levels, whether the user considers residual insulin (IOB) from previous injections or other techniques when determining dosage (determined from fixed dose, carbohydrate counting, or empirical dose). DGA can also determine whether the user's mealtime dose is constant or variable depending on the type of meal (e.g., breakfast, lunch, and dinner). A determination that mealtime doses are changing may indicate that the user is basing mealtime doses on carbohydrate counting techniques. DGA can also determine whether the user is adjusting mealtime doses to account for high pre-meal glucose levels. In some embodiments, DGA can also determine a target glucose level, and the user adjusts or corrects mealtime doses if their level is above or expected to be above the target glucose level. DGA can also determine which meals are associated with insulin administration. DGA can also determine patterns of forgotten mealtime administration. For example, DGA can detect whether the user has missed at least two, or instead at least three, doses associated with a meal or time period during a given period (e.g., one or two weeks).

[0084] The learning period can be any duration sufficient to obtain the necessary information. In many embodiments, this period is at least two days, more preferably one week or longer (e.g., 14 days), and may vary depending on how well the DGA can learn the trends. The results can be compiled into a summary report for both the user and the physician.

[0085] Learning methods Manual configuration of the DGS100 requires time from the Health Care Planner (HCP), but sufficient time may not always be available. Furthermore, even if time is available, the configuration can be complex and prone to errors. To mitigate these issues, a Patient Parameter Initialization (PI) module can be included in the DGA, which requires no configuration or minimal configuration. The PI module learns the patient's medication strategy, including basal only, basal +1, basal +2, etc., and parameterizes the patient's medication habits to configure the DGA's dose guidance settings.

[0086] According to one embodiment, the learning process of the PI module may include a step of automatically configuring the patient's dose guidance settings from observed data. Once the settings are successfully learned, the DGS100 can enter guidance mode, allowing the patient to request dose guidance and receive notifications regarding administration. During the learning process preceding guidance mode, the DGA can process glucose and insulin data collected by the patient's SCD102, UID202, and / or other devices, and determine administration information based on the processed data.

[0087] Dosage information may include, for example, the medication regimen, meal-to-dose type, dose parameters, and dosage range. Medication regimens may include, for example, basal dose + BF, basal dose + LU, basal dose + DI, basal dose + BF / LU, basal dose + BF / DI, basal dose + LU / DI, and basal dose + 3, where BF represents "breakfast," LU represents "lunch," and DI represents "dinner." Additional regimens, such as the dose for an afternoon snack, may also be included. Meal dose types may include, for example, fixed meal doses or variable meal doses. Dose parameters may include, for example, the nominal fixed dose or carbohydrate ratio for each meal, the pre-meal correction factor (CF), and the post-meal CF. The dose range may include an estimate of the minimum meal dose.

[0088] For each of the above-mentioned types of dosage information, the DGA can determine whether the accumulated data is sufficient or insufficient to determine the dosage information. In some embodiments, the patient's SCD102 can be configured to operate for a predetermined time period, for example, 14 days. In these embodiments, after the predetermined time period (or earlier if the sensor stops operating before the end of the period), the DGA can determine whether the available analytes and dosage data are sufficient to determine each of the above-mentioned dosage information. If sufficient, the DGA can perform the parameterization method 300 and initiate the dose guidance mode. In alternative embodiments, periodically during the learning period (e.g., once a day), the DGA can determine whether the data is sufficient to determine each of the above-mentioned dosage information. In any case, if the collected data is sufficient, the DGA can terminate the learning period, perform parameterization, and initiate the guidance period. Otherwise, the DGA can continue the learning process.

[0089] Referring to Figure 7, the DGA can be configured to run Method 300 alone or in any combination on a suitable computing device, for example, UID200, SCD102, and MDD152. The program instructions for running Method 300 can be grouped in a PI module or any other suitable code configuration. Outline, Method 300 may include a step in step 302 in which the DGA classifies each of the drug doses received by the patient during the analysis period based on data characterizing the patient's analytes and the drug doses received by the patient during the analysis period. Method 300 may further include a step in step 304 in which each dose is grouped into one of a set of mealtime groups. The Method may further include a step in step 306 in which it creates a patient dose parameter by applying the data for each mealtime group to a model, at least partially. The Method may further include a step in step 308 in which it stores the dose parameter in computer memory and configures a dose guidance setting. In the embodiments described herein, the analyte may be glucose or include an indicator of the patient's glucose level, and the drug may be insulin or include insulin. The dose guidance settings can be used by the DGA to formulate dose guidance or provided for output to an interface device, such as UID200 or a healthcare worker's terminal. More detailed aspects of each operation in Method 300 are described below. As used herein, “PI module” refers to a part or portion of the DGA that performs the operations of Method 300 and any auxiliary operations. The PI module is not limited to a specific configuration and can encompass various arrangements of computer code.

[0090] In one embodiment, the classification operation 302 may include the step of classifying each dose of a drug (e.g., insulin) into one of the following: meal dose, corrective dose, and / or ambiguous dose. If the DGA cannot classify a drug dose as a meal dose or corrective dose with a defined confidence level, the DGA may classify the drug dose as ambiguous and omit it from use when creating dose parameters for dose guidance.

[0091] The DGA can classify drug doses by a sequence of two operations, referred herein as feature extraction and classification. Relating this to Figure 7, the classification operation 302 may include the step of creating a feature matrix that correlates a set of classification features to each of the doses. In some embodiments, the DGA may consist of a vector of insulin injection timestamps, a data file containing analyte measurements from the patient's SCD102, and results from a meal detection algorithm module, discussed elsewhere herein, as inputs to a function that outputs a feature matrix for insulin dose classification. The number of rows in the feature matrix may represent the amount of injections, or equivalent drug administration events, during the relevant analysis period. Each row in the feature matrix may be, or contain, a feature vector for a single drug administration event. In embodiments for classifying insulin injections, each vector may contain elements, referred herein as classification features, as described below. The DGA may determine each element of the feature vector based on a time range for insulin injection time, e.g., a corresponding segment of glucose monitoring data from -2.5 hours to 1.5 hours.

[0092] In the embodiment, the classification feature may include the time of administration for each dose, for example, the time period recorded by MDD152 or the time period recorded by the patient using UID200.

[0093] The classification features may further include time-filtered analyte values, such as glucose values ​​filtered using non-parametric smoothing filters like Savitsky-Golay filters, low-pass filters, band-pass filters, or locally estimated scatterplot smoothing filters, or other filters. In one embodiment, the Savitsky-Golay filter may be of order 2 with a frame length of 7 and a sampling interval of 15 minutes.

[0094] The classification features may further include the rate of change in analyte values ​​closest to the time of administration, for example, the rate of change in analyte (e.g., glucose) values ​​calculated by linear regression of five analyte data points (e.g., using a 15-minute sampling interval) centered on the data point closest to the time of administration (e.g., injection).

[0095] The classification features may further include an Area Under the Curve (AUC) index, which shows the integral of the difference between the analyte value and the analyte value closest to the time of administration, over the interval prior to the time of administration. For example, to obtain the left-side AUC index, DGA can collect all data points from filtered analyte data within a time window (e.g., 2.5 hours), count back from the injection time, then calculate the difference between the average analyte value of the collected data points and the data point closest to the injection time (i.e., the reference data point), and calculate the left-side AUC index by multiplying this difference by the duration of the time window to calculate the increment of the left-side AUC.

[0096] The classification features may further include a right-hand AUC index, which represents the integral of the difference between the analyte value and the analyte value closest to the time of administration, over an interval after the time of administration. For example, DGA can calculate the right-hand AUC index by collecting all data points from filtered analyte data within a time window (e.g., 1.5 hours), counting back from the injection time, then calculating the difference between the average analyte value of the collected data points and the data point closest to the injection time (reference data point), and multiplying this difference by the duration of the time window to calculate the increment of the right-hand AUC.

[0097] Classification features can further include the elapsed time between medication times. For example, DGA can calculate the elapsed time between the previous injection time and the current injection time for each injection time by subtracting the previous injection time from the current injection time. For the first injection time in the insulin log, since there is no available previous injection time, DGA can calculate the elapsed time from the first SCG time data point to the current injection time. In addition, as a further example, DGA can calculate the elapsed time between the current injection time and the next injection time by subtracting the current injection time from the next injection time. For the last injection time in the insulin log, since there is no available next injection time, DGA can calculate the elapsed time from the current injection time to the last SCG time data point. In both backward and forward calculations, if the elapsed time is greater than a predetermined maximum value (e.g., 12 hours), DGA can set the elapsed time value to equal the maximum time.

[0098] The classification features may further include the probability that a meal will be initiated within a defined interval prior to the time of administration, for example, the maximum probability of a meal being initiated within a time window before injection (e.g., 1.5 hours). This probability can be calculated by a meal detection module described elsewhere in this specification.

[0099] The classification features may further include the most probable interval of time elapsed since the most recent meal, for example, the time elapsed from the point of maximum probability of meal initiation relative to the injection time (e.g., determined by the meal detection module).

[0100] The classification features may further include the probability that a meal will be initiated within a defined interval after the time of medication administration, for example, the maximum probability of initiating a meal within 2 hours after injection (determined by the meal detection module).

[0101] The classification features may further include the most probable interval to the next meal, for example, the predicted elapsed time from the injection time to the point of maximum probability of meal initiation after the meal injection (e.g., determined by the meal detection module).

[0102] As mentioned above, the step of calculating some of the classification features includes the step of estimating the time of each meal consumed by the patient during the analysis period, and the method for estimating meal times is described in more detail below. Briefly, the step of estimating the time of each meal may further include the step of creating a feature matrix based on time-correlated analyte data using DGA, where the feature matrix correlates a set of analyte (e.g., glucose) data features into distinct regions classified as rising, pre-falling, and falling. The set of analyte data features may be, or include, the maximum analyte rate of change, maximum analyte acceleration, analyte value at the point of maximum analyte acceleration, region duration, region height, maximum deceleration, mean rate of change within the region, and the time of maximum analyte acceleration. The estimation step may further include the step of creating estimated meal times based on the feature matrix using the algorithm described below.

[0103] More detailed embodiments of the retrospective mealtime detection algorithm for use in Method 300 or elsewhere are described in the following paragraphs. The description of other embodiments of Method 300 follows. The DGA can perform retrospective mealtime detection on time-correlated analyte data by executing one or more code modules, for example, a feature extraction module and a meal detection module. When executed by the DGA, the feature extraction module can cause the DGA to output a feature matrix that takes a glucose time series as input and passes through the retrospective meal detection module to detect glucose excursions in response to meal events.

[0104] DGA can perform feature extraction using the following operations, which can be divided into a sequence of three sub-operations: smoothing, segmentation, and extraction.

[0105] In the smoothing sub-operation, the DGA can smooth the analyte (e.g., glucose) time series using a Savitzky-Golay filter (order 2) and calculate the rate of change and acceleration rate at each analyte data point. The filter's frame length parameter may be the number of data points collected in a first time interval (e.g., 60 minutes), and therefore sampling is interval-dependent. The DGA can calculate the rate of change by taking the average of the before-and-after differences in the smoothed analyte values ​​between the point of interest and points in a second interval (e.g., 15 minutes) before and after that point, where the second interval is smaller than the first interval, for example, equal to one-quarter of the first interval. Similarly, the DGA can calculate the acceleration rate by taking the average of the before-and-after differences in the rate of change of the analyte between the point of interest and points in a second interval (e.g., 15 minutes) before and after that point.

[0106] In the segmentation suboperation, DGA can segment the smoothed analyte trace into monotonically increasing regions (i.e., rising regions) and decreasing regions (i.e., falling regions). Each rising region can be considered a candidate for glucose excursion in response to a meal event.

[0107] In the extraction sub-operation, DGA can extract features from the data. For example, it can extract 16 features that may or may not be features from each ascending region (e.g., 8 features), the preceding descending region (e.g., 4 features), and the next descending region (e.g., 4 features). Features that DGA can extract from ascending features may include, for example, the following: 1) the maximum analyte rate of change, 2) the maximum analyte acceleration, 3) the analyte value at the point of maximum analyte acceleration (reference point), 4) the duration of the ascending region (elapsed time from the reference point to the last point of the region), 5) the height of the region (difference in smoothed analyte values ​​between the last point and the reference point), 6) the analyte value at the point of maximum analyte acceleration (reference point), 7) the average rate of change within the region (height / duration), and 8) the time of the data at the reference point. To give a further example, the four features extracted from the preceding and succeeding descending regions may include the following: Specifically, these are 1) the height of the downward region, 2) the duration of the downward region, 3) the average rate of change of the region (height / duration), and 4) the maximum absolute value of the rate of change of glucose. The number of rows in the feature matrix output by the feature extraction module may be the same as the number of upward regions in the smoothed glucose time series.

[0108] According to another embodiment, a retrospective meal detection module can take a feature matrix as input and output a binary detection result for each rise region. Such outputs may include a binary classification result and a probability value that each rise region is an analytic (e.g., glucose) excursion in response to a meal event. The DGA can assign the probability value of each rise region to its reference point. In some embodiments, for example, a pre-trained machine learning model for meal detection can be implemented using a Random Forest Classifier by scikit-learn (https: / / scikitlearn.org / stable / modules / generated / sklearn.ensemble.RandomForestClassifier.html). The meal detection module can detect meal-induced postprandial glucose excursions based on a number of decision trees built and optimized during the training process. In alternative embodiments, the DGA can build a pre-trained model based on alternative classification algorithms, including, for example, gradient boosting, ADA boosting, artificial neural networks, linear discriminant analysis, and extra trees.

[0109] Referring again to method 300 in Figure 7, the classification operation 302 can take a patient feature matrix as input and output a binary classification result for each relevant medication event (e.g., for each insulin injection). For example, the DGA can output binary data "1" representing meal doses and "0" representing non-meal doses. According to some embodiments, the classification operation 302 can use meal detection results, in which case meal detection can be performed before insulin dose classification. As described for retrospective meal time detection, the classification operation 302 can include a pre-trained machine learning model, for example, a model implemented using a random forest classifier with scikit-learn (see above). The machine learning model implemented by the DGA can perform classification based on tree construction rules and thresholds for various features in each decision tree, which are optimized during the training process. Alternatively, this model can also be trained with other machine learning algorithms, including gradient boosting, ADA boosting, artificial neural networks, linear discriminant analysis, and extra trees. Once the DGA successfully classifies each dose, the determination of the medication regimen and administration parameters can be initiated.

[0110] In step 304, method 300 may include the step of DGA grouping each dose into one of a set of mealtime groups or clusters. For example, DGA can determine a medication strategy by clustering an analysis of the timing of administration (e.g., injection) of meal doses. DGA can run a clustering module implemented with the K-means algorithm together with the elbow method, which takes injection times as input and outputs the optimal number of clusters K (up to 3) and cluster index for each injection time. The optimal number of clusters K can be the number of meal doses a patient takes in a day. Using the cluster index for each injection, DGA can classify meal doses into K groups according to the cluster index.

[0111] DGA can identify these groups as breakfast, lunch, or dinner (B,L,D) as follows: For each group, DGA can determine the typical time of day (TOD) by calculating the median TOD of the group. Alternatively, DGA can use other centroid indicators. If K=3, DGA can associate breakfast with the group after the longest period between the group's typical TODs. The next group is lunch, and the last group is dinner. If K=2, DGA can estimate which groups are associated with breakfast, lunch, or dinner using a rule of assumptions about the time between each meal. For example, if two groups are more than 6 hours apart from each other, DGA can identify the group as breakfast and dinner. In addition, if the first group occurs before 10 a.m., DGA can identify the group as breakfast and lunch; otherwise, it can identify the group as lunch and dinner. In an alternative embodiment, after DGA has identified the typical times of meal events, the user can be prompted to identify the meals associated with each typical time. As a further example, in an alternative embodiment, the DGA can combine the two methods described herein by prompting the user for confirmation after estimating the relevance of meals. Further alternative methods include analyzing glucose data to identify meals and clustering meal times to detect typical meal times. This may be useful for distinguishing meals in the case of K=2, i.e., identifying meals for which no dose was taken.

[0112] Once the doses are grouped into mealtime clusters, in step 306, the DGA can perform the step of creating patient dose parameters, at least partially, by applying the data for each mealtime group to a model. For example, for each meal group (B, L, D), the DGA can pair each set of corresponding pre-meal glucose levels with the corresponding meal dose. The DGA can then fit each group with an appropriate model, e.g., a linear function with zero slope, a linear function with a non-zero slope, a piecewise linear function joined at one point, or a nonlinear function that approximates a piecewise model but has smooth curvature around the joint point. Other models are also suitable.

[0113] DGA can perform model fitting and parameter estimation by minimizing the sum of squared residuals (SSR) of the model parameters. Then, using a grinding algorithm, DGA can find the optimal parameters that minimize the SSR. For linear models, DGA can perform fitting using the Nelder-Mead simplex method. For nonlinear models, DGA can use the Levenberg-Marquardt algorithm. In other words, DGA can use the Nelder-Mead simplex numerical optimization method for linear models and the Levenberg-Marquardt optimization method for nonlinear models. Other methods for fitting data to these models are also possible.

[0114] If the number of iterations during optimization exceeds the convergence criterion, the model will not fit, and DGA can exclude the unfit model from the candidate models. Furthermore, DGA can apply certain rules to minimize the uncertainty of parameter estimation, for example, by validating the estimated correction coefficient by requiring at least three pre-meal glucose data points greater than the estimated threshold glucose, or by validating the estimated fixed volume by requiring at least three pre-meal glucose data points less than the estimated threshold glucose, or by requiring the 95% confidence interval for the parameter intercept to exclude zero, or by requiring the 95% confidence interval for the model slope to exclude zero.

[0115] If the data is insufficient, model fitting may fail, resulting in certain models being excluded as candidate models. DGA can evaluate each model using the Akaike Information Criterion (AIC) and select the model with the lowest AIC value as the preferred model for each dietary group.

[0116] Once the DGA selects a model for each mealtime cluster, it can then determine dose parameters, including, for example, a fixed dose of insulin, a target glucose level, and a correction factor, based on the selected model for each mealtime cluster. The DGA can determine the target glucose level and correction factor as a single value for each group, as will be described in more detail in the following paragraphs. In an alternative embodiment, the DGA may determine the target glucose level and correction factor separately for each group and use the separately determined parameters for downstream dose guidance operations.

[0117] According to another embodiment, DGA can form combined data groups to obtain a more accurate correction factor for the patient. For example, after fitting dose data to various models for each meal group to select the best model and estimating the fixed insulin dose, DGA can subtract the fixed dose insulin amount from the relevant meal dose for each meal group. The remaining non-zero values ​​correspond to doses with a correction dose. These non-zero values ​​can then be joined from all three meal groups (B, L, D) to form a combined group. If a fixed dose insulin amount cannot be determined for a group, DGA can exclude the data for that group from the combined group. The system can then repeat the operation to find the best model for the combined group, or use the same model identified when analyzing the groups individually. By using this combined group approach, it is assumed that the patient has the same (or constant) correction factor and target glucose for all meals, and the combined group can provide a more accurate fitting with a larger sample size. After determining the target glucose level and correction factor based on the best-fitting model, DGA completes the estimation of the dose parameters. Next, in step 308, the DGA can store the dose parameters in computer memory and configure the dose guidance settings.

[0118] In an additional embodiment, the DGA may determine whether a patient is potentially engaging in carbohydrate counting (e.g., adjusting meal portions to account for carbohydrate consumption) by comparing the AIC value of a preferred model to a threshold such as 50, 75, or 100. If the AIC value is greater than the threshold, the DGA determines that the patient is engaging in carbohydrate counting and may seek confirmation from the patient via UID200.

[0119] In alternative embodiments, one or more of the operations described above may be omitted and replaced by requiring the patient or HCP to manually provide information, or by extracting information from another source, such as EMR or other software programs. Nevertheless, Method 300 should be useful for a variety of applications that do not have more information than what SCD and MDD can provide.

[0120] User feedback during the learning period Next, exemplary embodiments of how user feedback can be obtained during or after the DGA's learning period are described. During the initial learning phase with the DGA, the user may be prompted for feedback. User feedback can indicate to the user that the system is progressing. The DGA may prompt the user for feedback (e.g., input or confirmation) on any aspect of dose guidance, such as the dose administered, the history of the analytes, the patient's behavior or activities, the overall medication strategy, the type of specific dose, and confirmation that the type of dose or strategy determined by the DGA (e.g., learned by the system) is correct.

[0121] During the learning period (or thereafter), DGA may output prompts or other displays to UID200 requesting user feedback. This feedback may relate to a medication strategy, e.g., a strategy regarding the type of insulin action (e.g., long-acting and / or short-acting or rapid-acting). If the feedback (or other decision) indicates the use of a long-acting strategy, DGA may monitor the patient's basal dosing pattern during a first time period, e.g., the first three days, classifying each dose or dosing pattern into single-dose or divided-dose types and / or characterizing doses by time period (e.g., a single morning dose, a single evening dose, or divided doses (e.g., both morning and evening)). DGA may also determine trends in dosage (e.g., median, mean) and associated dose variability values. From this information, DGA can formulate expected basal doses. After the first time period, if the doses actually administered (e.g., automatically registered by MDD152 or entered by the user) differ from expectations, the user may be prompted for feedback.

[0122] According to one embodiment, the DGA can prompt the user in many different situations. For example, the DGA can be configured to detect medication forgetfulness, such as when the user fails to administer a basal or bolus dose during the time period in which a previous basal or bolus dose would have been administered. If medication forgetfulness is detected, the DGA can be configured to prompt the user for input regarding whether a basal dose was administered during that time period. According to some embodiments, the DGA can be configured to detect differences in administration timing. For example, the DGA can be configured to detect when the user administers a basal dose at a different time than when a previous basal dose was administered (for example, when a basal dose usually administered in the morning is administered in the evening). If such a difference in administration timing is detected, the DGA can be configured to prompt the user for input regarding whether the basal dose was administered during a different time period. In another embodiment of this embodiment, the DGA can also be configured to detect when an extra dose has been administered. For example, the DGA can be configured to detect changes in the number of basal doses administered per day. In yet another embodiment, the DGA can be configured to detect whether the medication strategy on day 1 (e.g., one basal dose administered) differs from the medication strategy on day 2 (e.g., two basal doses administered). If a different medication strategy is detected, the DGA can be configured to prompt the user for input regarding whether the user has adopted the medication strategy used on day 2 as the new medication strategy. In yet another embodiment, the DGA can also be configured to detect whether different dosages have been administered. For example, the DGA can be configured to detect whether a first dose administered at a certain time is different (smaller or larger) from a preceding dose administered at a certain time on the previous day. If a different dosage is detected, the DGA can be configured to prompt the user for input regarding whether the user has changed the dosage.

[0123] The user's responses to these prompts allow the DGA to confirm that it has identified the correct pattern (for example, the user confirms that they have forgotten to take their morning basal dose but usually do) or to provide the user with an opportunity to correct the pattern (for example, the user informs the DGA that they will adjust their basal dose based on glucose before taking it).

[0124] In rapid-acting insulin administration strategies, in addition to the prompts mentioned above, DGA may include prompts regarding dose classification. Dose classifications may include, but are not limited to, bolus, corrected, divided dose, bolus + corrected, and bolus + carbohydrate count + corrected.

[0125] Regarding the administration of rapid-acting insulin, prompts can be displayed to the user in various situations. The DGA can be configured to detect whether a dose unrelated to a meal has been administered. For example, the DGA can be configured to determine whether a dose was taken during a time period in which no meal is identified or detected. If the DGA detects that a dose has been taken and no meal was detected within the time period of administration (e.g., within about an hour of administration), the DGA can prompt the user for input regarding the reason for the dose being administered (e.g., because a meal was eaten, to lower glucose, or because the administration of a previous meal had finished). The DGA can also be configured to detect whether a meal dose does not match a previous meal dose related to the same type of meal. For example, the DGA can be configured to determine whether a bolus dose related to a first meal type and administered at a certain time is not the same as a previous bolus dose related to the first meal type and administered at the same time the previous day. If such a difference in bolus doses is detected, the DGA can be configured to determine the reason for the different doses. For example, DGA can be configured to determine the difference in pre-meal glucose levels associated with a bolus dose and a previous bolus dose, and to determine whether the detected difference is a correction. DGA can also prompt the user for input regarding the reason for the difference in bolus doses (e.g., a small / large amount of food eaten and / or correcting for hyperglycemia and / or other factors).

[0126] In addition to enabling DGA to determine what type of rapid-acting dose is being taken throughout the day, it can also facilitate the timing of dose prediction. After a learning period in which no prompts are provided, DGA can provide these prompts to the user when the dose differs from the expected dose in order to improve DGA's model of the user's medication strategy.

[0127] In both long-acting and fast-acting cases, DGA can aim to minimize the number of prompts as time passes and the user responds. The focus can be on frequent prompting in the initial stages, gradually reducing it once repetitive patterns are observed.

[0128] Glucose pattern analysis and dietary bolus titration for MDI insulin therapy Next, an exemplary embodiment of a method for determining meal bolus titration is described. The system can learn (or configure to match) a patient's current medication strategy and provide titration guidance for frequent daily injectable (MDI) therapy. For patients using fixed meal dosing, fixed doses (e.g., breakfast, lunch, dinner, snacks, etc.) can be titrated. For patients performing carbohydrate counting, the carbohydrate ratio can be adjusted for the same meal or different time periods. For patients performing empirical dosing, dose titration can be performed for each meal. Titration guidance by DGA can provide recommendations for changing doses or carbohydrate ratios in a particular direction. The amount of change can be changed by appropriate percentages, for example, 5%, 10%, 15%. Dose guidance may also include initiating meal dosing. For example, if a patient is using basal + 1 (e.g., lunch dosing regimen) and breakfast shows a high pattern, DGA can provide recommendations for administering RA insulin at breakfast.

[0129] DGA may require defining administration categories such as time-of-day (TOD) periods, meal types (e.g., breakfast), and meal composition (e.g., cereal with milk). For example, an administration category could be a time-of-day period defined by the duration associated with meal insulin administration during that period. In a further example, a post-breakfast time-of-day period could be defined as beginning when a meal insulin dose is taken during a defined time period, e.g., 5 a.m. to 10 a.m., and ending after a defined post-meal period (e.g., 6 hours later) or when the next meal insulin dose is taken, whichever comes first. One or more metrics may be required to define whether a post-meal glucose response is nominal or requires correction, or to rank post-meal glucose patterns favorably or unfavorably compared to others. The likelihood of low glucose (LLG) index and median glucose can be used to quantify the degree of hypoglycemia risk and hyperglycemia risk, respectively.

[0130] U.S. Patent Publication No. 2018 / 0188400 ('400), whose entire contents are incorporated herein by reference for all purposes, describes an embodiment for deriving and determining a risk index available for use in glucose pattern analysis (GPA) of an embodiment of DGA. This embodiment, in particular, uses central trend (e.g., mean, median, etc.) and variability value data from a multi-day period to determine a risk index corresponding to the degree of hypoglycemia risk ("hypo risk"). This embodiment is summarized herein, and a more comprehensive description of embodiments and variations thereof can be obtained by referring to '400.

[0131] An alternative to the embodiment described in the publication of the '400 Gazette is described in U.S. Patent Publication No. 2014 / 0350369, which is also incorporated herein by reference in its entirety for all purposes. For example, instead of using median and variability values, this method can employ any two statistical measures that define the distribution of the data. As described in the '369 Gazette, the statistical measures can be based on a glucose target range (e.g., G LOW = 70 mg / dL and G HIGH = 140 mg / dL). Common measurements related to the target range are time in range (TIR), time above target (t AT ), and time below target (t BT ). When glucose data is modeled as a distribution (e.g., gamma distribution), for predefined thresholds G LOW and G HIGH , t AT and t BT can be calculated. For the thresholds, the algorithm can also define t BT_HYPO , and when it exceeds t BT , it can be determined that the patient has a high risk of hypoglycemia. For example, a high risk of hypoglycemia can be defined as when t LOW exceeds 5% when G BT = 70 mg / dL. Similarly, an index of t AT_HYPER can be defined, and when it exceeds t AT , it can be determined that the patient has a high risk of hyperglycemia. The degree of risk of hypoglycemia and hyperglycemia can be adjusted by adjusting either G LOW or t BT_HYPO , G HIGH or t AT_HYPER . A control grid can be defined using any two of the three measures of TIR, t BT and t AT . Using these options (and other options), the risk indicators of the embodiments of the DGA described herein can be determined.

[0132] The embodiments of DGA described herein can operate based on a quantitative assessment of the user's analyte data during a TOD period. This quantitative assessment can be performed in various ways. For example, the embodiments described herein can assess analyte data over several days to determine one or more indicators that describe the relevant risks that the analyte data exhibits for a given TOD. These indicators can be used to classify the analyte data during a TOD period into one of several patterns. For example, these patterns may indicate glucose behavior or trends that are common to or generalized for that TOD. The embodiments of DGA can utilize any number of two or more patterns. For ease of reference, these patterns are referred to as glucose pattern types herein, and the embodiments described herein refer to embodiments that utilize three glucose pattern types (e.g., low pattern, high / low pattern, and high pattern), but other embodiments may utilize only two types or three or more types, and these types may differ from those described herein.

[0133] Taking a fixed meal dose as an example, once the DGA has learned the medication strategy and the amount of dose or carbohydrate ratio, it can begin titration evaluation, which can be categorized into four titration categories: “nighttime,” “after breakfast,” “after lunch,” and “after dinner.” For each of these categories, the DGA can map the two indicators mentioned above (LLG and median glucose) to four logical “pattern” variables using the GPA method described later. Figure 8A shows the operation of an exemplary method 400 by the DGA for evaluating meal bolus titration for frequent injectable (MDI) medication therapy. Method 400 may further include a step in 402 in which the DGA determines at least one TOD analyte pattern type by running a glucose pattern analysis (GPA) algorithm that takes time-correlated analyte data transmitted from a sensor-controlled device worn by the patient during the analysis period as input. Method 400 may further include the step in 406 of storing recommended action guidelines in computer memory for output to at least one of UID200 or MDD152, which administers the drug to the patient, by the DGA. UID200 can use the recommended action guidelines to control its user interface, for example, by displaying a human-readable representation of the guidelines on a display or by creating an audio output that represents the guidelines in human language. MDD152 can use the guidelines to adjust or maintain the next relevant dose administration. Further details of Method 400 are described below.

[0134] Figure 8B is a flowchart illustrating an exemplary embodiment of GPA method 410, which can be implemented as the GPA algorithm referenced in 402. Method 410 can be performed for an entire day (e.g., a 24-hour period), or for specific TOD periods that may be time blocks (e.g., three 8-hour periods), or for parts of the day defined by user activities (e.g., meals, exercise, sleep, etc.). In many embodiments, multiple TOD periods may correspond to meals (e.g., after breakfast, after lunch, after dinner) and sleep (e.g., nighttime). These TOD periods may correspond to fixed times of the day when activities would normally take place (e.g., from 5 a.m. after breakfast to 10 a.m.), and such time blocks may be conditional on the meals or activities actually taking place, as can be set by the user or determined by automatic detection of meals or activities, or by user instructions indicating these (e.g., using UID 200).

[0135] The DGA can independently perform method 410 for each TOD period to obtain individual pattern assessments for that period. In 412, the DGA can determine central trend and variability values ​​from the user's analyte data for a particular TOD period. The user's analyte data may be available from the user's own records or from the records of the user's healthcare professional, or the user's analyte data may be collected by, for example, DGS100. The analyte data preferably spans a period of multiple days (e.g., 2 days, 2 weeks, 1 month, etc.) so that there is enough data within the TOD period to make a reliable judgment. In other embodiments, this method can be performed in real time for limited data. The DGA can use any type of central trend index that correlates with the central trend of the data, including but not limited to the median or mean. Additionally, any variability index can be used, including but not limited to variability ranges spanning the entire dataset (e.g., from minimum to maximum), variability ranges spanning the majority of the data but not the entire dataset to minimize the significance of outliers (e.g., from the 90th to the 10th percentile, or from the 75th to the 25th percentile), or variability ranges targeting specific asymmetric ranges (e.g., low-range variability, which can span, for example, from the central trend value to lower values ​​of the data, e.g., the 25th percentile, the 10th percentile, or the minimum value). The choice of indexes representing central trend and variability can vary depending on the embodiment.

[0136] In 414, DGA can assess hypoglycemia risk ("hypo risk") indicators based on central trend and variability values. One such methodology for determining hypoglycemia risk is described with respect to Figure 8C, which illustrates an exemplary embodiment of a framework for determining hypoglycemia risk and other indicators. While Figure 8C is intended to convey the framework to the reader, this framework can be implemented electronically in a number of different ways, including software algorithms (e.g., formulas, sets of if-else statements), lookup tables, firmware, and combinations thereof.

[0137] Figure 8C is a graph of central trend vs. variability (e.g., low-range variability) that can be used to evaluate or identify regions or zones that hold or correspond to data pairs of central trend and variability determined for a particular TOD. Any number of two or more zones can be used. In this embodiment, the data pairs may correspond to one of the target zone 425 or three hypo-risk zones: low zone 426, moderate zone 428, or high zone 430. A first hypo-risk function (e.g., a curve or linear boundary), referred to as the moderate-risk function 422, distinguishes between low zone 426 and moderate zone 428. A second hypo-risk function, referred to as the high-risk function 424, distinguishes between moderate zone 428 and high zone 430. The data pairs with central trend and variability can be evaluated against or compared to zones to determine a hypo-risk index for the corresponding TOD period.

[0138] The hypoglycemia risk functions 422 and 424 can be explicitly implemented in the DGA as mathematical functions (e.g., polynomials), or implicitly implemented by defining each zone by the included pairs, using lookup tables, a set of if-else statements, threshold comparisons, etc. The hypoglycemia risk functions 422 and 424 can be preloaded into the DGA, downloaded from a trusted computer system 480, or set by another party such as an HCP. Once implemented in the DGA, the hypoglycemia risk functions 422 and 424 can be treated as fixed or can be adjusted by the user or HCP. An exemplary methodology for determining the hypoglycemia risk functions is described in Publication 400.

[0139] In 416, DGA can assess a hyperglycemia risk index ("hyper risk") based on the central trend value. In this embodiment, hyperglycemia risk can be assessed by comparing the central trend value for a particular TOD period to a target or threshold 432 for the central trend. The magnitude and / or sign of the difference between the central trend value and the target 432 can identify the amount of hyperglycemia risk. For example, if the central trend value is less than the target 432 (e.g., a negative value), a low hyperglycemia risk may exist. A moderate hyperglycemia risk may exist if the central trend value is below the threshold (e.g., 5 percent, 10 percent, etc.) but above the target 432 (e.g., a positive value). A high hyperglycemia risk may exist if the central trend value is greater than the threshold and above the target 432. The use of three separate groupings for hyperglycemia risk (e.g., low, medium, high) is an example, and any number of two or more groupings can be used.

[0140] In other embodiments, DGA can assess the hyperglycemia risk index at 416 before assessing the hypoglycemia risk at 414. Alternatively, in another embodiment, the assessment of hypoglycemia risk at 414 and the assessment of hyperglycemia risk at 416 can be performed simultaneously and in parallel.

[0141] Other indicators, such as volatility risk, can also be evaluated. For example, a volatility value smaller than the first volatility threshold of 434 may indicate low volatility risk, a volatility value greater than the first volatility threshold of 434 but smaller than the second volatility threshold of 436 may indicate moderate volatility risk, and a volatility value greater than the second volatility threshold of 436 may indicate high volatility risk. Here again, the use of three separate groupings for volatility risk is just one example. DGA can use any number of two or more groupings.

[0142] In step 418, DGA can determine the pattern type of the TOD period based on one or more evaluated risk indicators. In an exemplary embodiment, pattern determination can be evaluated using hypoglycemia risk indicators and hyperglycemia risk indicators. If the hypoglycemia risk indicator is high, the pattern can be set as a low pattern. Alternatively, if the hypoglycemia risk is moderate and the hyperglycemia risk is high or moderate, the pattern can be set as a high / low (or moderate) pattern. Alternatively, if the hyperglycemia risk is high or moderate and the hypoglycemia risk is low, the pattern can be set as a high pattern. If both the hyperglycemia risk and hypoglycemia risk are low, the identified pattern can be set as No Problem (for example, an "OK" message is displayed and output).

[0143] Thus, method 410 is an example of how the DGA outputs one of several pattern types for each TOD period. The number of pattern types themselves may differ from those described in this embodiment (e.g., low, high / low, high). Once the pattern types for the TOD periods are determined, the DGA can store the indicators of the pattern types in memory for use in determining the titration recommendations. Referring again to Figure 8A, in 404, after completing the GPA for each relevant TOD period, the DGA can proceed to determine the titration recommendations.

[0144] The recommended approach may branch depending on other factors such as pattern type (e.g., low, high / low, high), TOD period, medication strategy, adherence to the strategy (e.g., whether the dose is insufficient), and whether sufficient data is available to perform the evaluation. The DGA will not recommend titration until sufficient data is available for the corresponding TOD period. For example, if the amount of available data falls below a threshold, such as if the number of other days with more than the minimum portion of available data (e.g., 90%) is below the threshold (e.g., 5), the DGA may skip the evaluation and generate an error message.

[0145] Figures 8D to 8H show examples of branching recommendation algorithms or methods for determining dose titration recommendations based on the input information described above. Other branches may also be useful. Figure 8D shows recommendation method branch 440 for TOD where sufficient data is available and there is a possible cause of a low pattern type, including one or more of the basal dose, meal dose, pre-meal corrected dose, or post-meal dose that is higher than the optimal amount. In 442, DGA assesses whether the pattern type of the nocturnal TOD period is low. If the pattern is low, in 444, DGA generates a recommendation to reduce all relevant doses by the same amount, e.g., 10%, including at least the basal dose and optionally one or more of the meal dose, pre-meal corrected dose, or post-meal dose. A titration recommendation rule for a low pattern may include a step in 444 to generate a recommendation to reduce the dose or basal rate of long-acting insulin for the nocturnal TOD period. In 446, if other TOD periods are low-pattern, DGA may generate a recommendation in 448 to reduce the fixed meal dose only for the relevant TOD period.

[0146] In this embodiment, if there is at least one low pattern, no titration guidance is provided for high-pattern TOD periods. The idea here is to prioritize the prevention of hypoglycemia and to increase the dose only when the risk of hypoglycemia is low throughout all TOD periods. Also, in some cases, if a TOD period has a high pattern, this may be due to a low pattern in the previous TOD period, and the patient overeating to compensate for this, so addressing the low pattern itself may help address the subsequent high pattern. In 449, if the pattern is not high, process 440 waits or terminates without generating a recommendation, or passes the high-pattern assessment 450.

[0147] Therefore, in the case of high / low patterns, DGA does not generate titration guidance. If there is no TOD period for which titration guidance can be given and sufficient data is available for all time periods, DGA can provide the patient with a message indicating that glucose variability needs to be addressed before further titration guidance can be given. DGA can also provide the patient's HCP with a report to consider alternative drug therapies or treatments that can address glucose variability.

[0148] Figure 8E shows how DGA works to generate high-pattern titration recommendations when there are no low-pattern TOD periods. In 452, if the nocturnal period has a high pattern and there are no other periods with a moderate risk of hypoglycemia, DGA can increase the long-acting insulin dose or basal rate recommendation in 454. In 456, if the nocturnal period has a high pattern and there is at least one other non-dinner period with a moderate risk of hypoglycemia, DGA can decrease the meal insulin dose associated with any period with a moderate risk of hypoglycemia in 458. In 460, if the nocturnal TOD period does not have a moderate risk of hypoglycemia and does not have a high pattern, DGA can generate a recommendation to increase the meal insulin dose associated with the first TOD period with a high pattern in 462. In 464, if the nocturnal period has a moderate risk of hypoglycemia and the only postprandial period with a high pattern is dinner, DGA can generate a recommendation to increase the long-acting insulin dose or basal rate in 466. If the nocturnal period has a moderate risk of hypoglycemia and the post-dinner period does not, then in 462, DGA can generate recommendations to increase the meal insulin dose associated with the first TOD period having a high pattern.

[0149] In an alternative embodiment, pre-meal glucose may be higher or lower than the target glucose (e.g., 120 mg / dL). The glucose data for each meal contributing to the calculation of hypoglycemia and hyperglycemia risk indicators can be modified to compensate for the effects of previous meals or conditions that affect glucose not attributable to the current meal. DGA can modify these data by subtracting an offset so that the resulting starting glucose is at the target level. Alternatively, DGA can modify these data using a “trigonometric” function, which subtracts the difference between the meal start glucose and the target glucose for the meal start time, but this modification is reduced linearly over a defined period (e.g., 3 hours) or by another decay function.

[0150] Alternatively, this function can itself be a function of the glucose level or glucose trend at the start of a meal, and / or when the previous meal dose was taken.

[0151] According to another embodiment, the algorithm for generating dietary bolus titration recommendations may become more complex when considering additional aspects such as forgotten meal administration, forgotten basal administration, postprandial and preprandial adjustments. The algorithm for providing appropriate recommendations when these factors are present may need to exclude some data while still meeting a data sufficiency threshold after excluding data to provide guidance.

[0152] For example, referring to Figure 8F, if a high pattern is detected at 461 and there are several days when meal doses are forgotten, the days when meal doses are forgotten are excluded, and the GPA analysis 410 is repeated at 463. Subsequently, if a high pattern is detected at 465, the dose can be increased at 467 based on patterns identified in other TODs, or further input or return can be awaited at 469. Alternatively, the system can evaluate only the high pattern using data excluding the days when meal doses were forgotten. Algorithm 470 with this branching pattern is shown in Figure 8F. If the system detects a low pattern at 473, the low pattern algorithm 472, described in the next paragraph, can be executed. If the system does not detect a high or low pattern, it may return to block 469 for further input or return.

[0153] In case 472, if a meal is missed, the DGA detects a low pattern during the TOD period, and if a meal is missed on any of the days during this TOD, the DGA can generate a recommendation to reduce the dose. Recommendations may include, for example, reducing the fixed dose or corrected dose portion.

[0154] Regarding basal dose forgetting, if DGA detects a low pattern 473 in nocturnal TOD, basal dose forgetting should not affect the dose titration logic. Similarly, if a low pattern is detected in non-nocturnal TOD, basal dose forgetting should not affect the dose titration logic.

[0155] If DGA detects a high pattern 461 in TOD using data that includes at least one day (or TOD) in which a basal dose was forgotten, the pattern analysis 410 can be repeated by excluding data 463 from any day (or TOD) in which a basal dose was forgotten. Subsequent actions may depend on the specific TOD in which the high pattern was detected. For example, if DGA detects a high pattern in nocturnal TODs using data that includes at least one day in which a basal dose was forgotten, the pattern analysis can be repeated by excluding data from any day in which a basal dose was forgotten. If a high pattern is detected in nocturnal TODs when days in which basal doses were forgotten are excluded, the results of nocturnal TODs can be used as a guideline for adjusting basal doses, and the basal dose can be increased. If a high pattern is detected in non-nocturnal TODs, the pattern analysis can be repeated by excluding days in which basal doses were forgotten. If a high pattern is detected when days in which basal doses were forgotten are excluded, the meal doses associated with TODs having a high pattern can be analyzed and titrated as described herein. In either case, the logical flow 470 is as shown in Figure 8F.

[0156] Figure 8G shows an example of a logical flow 474 for formulating recommendations with postprandial adjustments. After GPA 410, if DGA detects a low pattern 479 of TOD over several days including postprandial adjustments, the following analysis can be used to perform adjustment or titration of the meal dose. In 475, if DGA first detects a low pattern 479, it can first test in 487 whether sufficient data is available and exclude data from days without postprandial adjustments. If sufficient data is not available, DGA may perform an error recovery routine 489, for example, by displaying an error message. If sufficient data is available, DGA may repeat the pattern analysis 410. Subsequently, if DGA detects a low pattern, it can reduce the postprandial adjustment dose (i.e., increase the adjustment coefficient) in 476, subject to the pattern analysis results for other TODs. If DGA does not subsequently detect a low pattern, it can reduce the meal dose in 477.

[0157] In all embodiments described herein, a unidirectional correction of the correction dose (e.g., titration) can be achieved by a unidirectional correction of the correction coefficient. These two parameters have an inverse relationship, with an increase in the correction dose being achieved by a decrease in the correction coefficient, and a decrease in the correction dose being achieved by an increase in the correction coefficient. Thus, in all embodiments described herein, the DGA can recommend or implement correction by either a correction of the correction coefficient or a correction of the correction dose. Thus, where the correction of the correction coefficient or titration is described herein, the embodiment can be configured to achieve the same effect by an inverse correction of the correction dose, and conversely, where the correction of the correction dose or titration is described herein, the embodiment can be configured to achieve the same effect by an inverse correction of the correction coefficient. Given this compatibility, both options are available in all embodiments described herein, although not all embodiments are described solely for the sake of clarity.

[0158] Additionally, or alternatively, starting from the original dataset 491, at 478, DGA may exclude days when meal administration was forgotten. After finding sufficient data at 487, if pattern analysis 410 of these data, excluding days when postprandial correction was performed at 490, does not show a low pattern, DGA may recommend reducing the postprandial correction dose at 476. Alternatively, DGA may perform logic 510 in Figure 10B, which may then recommend reducing either the mealtime insulin or preprandial correction portion of the dose guidance. If DGA does not detect low values ​​at 479 and does not detect a high glucose pattern at 492, it may wait for further input or return at 469. If DGA detects a high pattern at 492, process 480 may be performed in block 471 (Figure 8H).

[0159] Referring to Figure 8H, if the DGA detects a high pattern 493 for a TOD with several days that include postprandial adjustments, the following procedure 480 may be performed to formulate recommendations for adjustment and meal dose titration. In 481, the DGA may repeat pattern analysis 410, including data for days with skipped meals and days with postprandial adjustments. Subsequently, if the DGA detects a high pattern in 494, in 482, the postprandial adjustment dose may be increased (i.e., the adjustment coefficient reduced), subject to the pattern analysis results for other TODs. If no high pattern is detected in 494, a low pattern is checked in 495, and if a low pattern is detected, the DGA may return to 474 in Figure 8G, or otherwise wait for further input in 469. Although not shown in Figure 8H, after excluding any data in GPA 410, before running GPA, the DGA may test for data sufficiency and run an error recovery routine if the available data is insufficient.

[0160] Alternatively, or additionally, if a pattern analysis of the data excluding days when meal administration was forgotten at 483, starting from the original dataset at 493, shows a high pattern along either branch 2.1 or 2.2, the DGA can continue with step 480 as follows: In the case of branch 2.1, if a pattern analysis 410 of the data for days when postprandial correction was excluded at 484 (i.e., data with bolus administration only) does not show a high pattern at 497, the DGA can generate a recommendation to increase the postprandial correction dose at 482, subject to the pattern analysis of other TODs. Otherwise, the DGA can generate a recommendation to increase either the mealtime insulin or the pre-meal correction portion, according to step 550 in Figure 10C.

[0161] In branch 2.2, if the pattern analysis of data only for days containing postprandial correction in 485 does not show a high pattern in 496, DGA may increase either the mealtime insulin or the preprandial correction portion according to procedure 550 in Figure 10C. If no high pattern is detected in 496, DGA may return to block 484.

[0162] If the recommendations for correction factor titration from different TODs are contradictory, and the patient is currently using the same correction factor for all TODs, the DGA may increase the correction factor. Procedure 480 suggests that if all three components—meal dose, pre-meal adjustment, and post-meal adjustment—are not optimal, the meal dose may be increased first. The pre-meal adjustment can be increased by titration after the meal dose has been titrated. The post-meal adjustment can be increased by titration after the meal dose and pre-meal adjustment have been completed.

[0163] During subsequent analysis, TODs for which DGA previously generated a recommendation to "increase the correction factor" using the method described above will now be recommended to "keep the correction factor unchanged." Conversely, if a TOD for which DGA previously generated a recommendation to "decrease the correction factor" using the method described above is now recommended to "decrease the correction factor," it is highly likely that different TODs are being optimized using different correction factors.

[0164] Figures 8D to 8H show various aspects of the recommended algorithm 404 for use in method 400, but it should be understood that these are illustrative examples. Various other algorithms may also be suitable.

[0165] Titration hysteresis of a meal bolus Next, an exemplary embodiment of a method for mitigating oscillations around the optimal meal bolus dose will be described. When the DGA has reached or is approaching the optimal titration, a situation may arise where titration continues to be requested but is not actually necessary. That is, the indicators used to determine whether titration is necessary may have a level of error or variability, and this variability may cause the titration algorithm to oscillate around the optimal dose. To mitigate this oscillation problem, a PPC (Patient Parameter Convergence Tracking) module can be incorporated into the DGA.

[0166] In one embodiment, the PPC module can collect historical information from the user, which includes sufficient data to determine the impact of various events on the patient's glucose levels at different times. The PPC module can be configured to calculate and track how multiple outcome indicators change over time. Outcome indicators may include, but are not limited to, hypoglycemia risk, hyperglycemia risk, and glucose control indicators. The PPC module can also be configured to calculate and track changes in dose guidance parameter estimates and / or dose guidance suggestion values. Dose guidance parameter estimates may include, but are not limited to, estimated insulin sensitivity coefficient / insulin correction coefficient, estimated insulin-to-carbohydrate ratio, and estimated average carbohydrates at each mealtime. Dose guidance suggestion values ​​may include, but are not limited to, recommended basal insulin dose, recommended meal dose, recommended touch-up dose, and recommended correction dose.

[0167] In one embodiment, the DGA's PPC module can be configured to create correlations for each outcome metric. These correlations may be multidimensional. The PPC module can be configured to map changes over time in each dose guidance parameter and / or guidance suggestions to changes over time in the outcome metric. The PPC module can also be configured to track the slope of a particular metric. For example, if changes in multiple dose guidance parameters and / or guidance suggestions cause a small, predictable change in an outcome metric, the PPC module can be configured to decide to delay the adjustment suggestion for a certain period of time to prevent unnecessary adjustment requests to the user.

[0168] In another embodiment, the PPC module may be configured to use multiple gradients and compare each gradient to a predetermined set of gradient thresholds. The PPC module may be configured to delay adjustment recommendations if the number of gradients exceeding a threshold is not greater than a predetermined value. The predetermined value can be a universal value or a user-specific value.

[0169] Physiological dose guidance algorithm Next, exemplary embodiments of methods for determining dose guidance based on physiologically relevant processes are described. Many model-based control systems, specifically those utilizing model predictive control (MPC) algorithms, are based on black-box diagrams and lack a rigorous physiological basis. As a result, these models may not be able to explain the specific pharmacokinetic and pharmacodynamic differences of different insulin analogs used in intensive MDI therapy. Furthermore, while MDI therapy requires managing the user's blood glucose levels over several hours with a given insulin dose, many dose guidance algorithms available today are intended for use with insulin pumps that continuously deliver only one type of insulin analog (usually rapid-acting) to the user. MPC algorithms communicate with the CGM to receive frequent glucose feedback (e.g., every 5 minutes) regarding the current insulin delivery rate, and can then change the pump flow rate in real time to maintain euglycemic function. As a result, current MPC algorithms, which can frequently change the pump-driven insulin delivery amount based on glucose feedback, do not work in MDI therapy where the insulin delivery amount is not so high and must predict over longer time horizons. The longer these time horizons become (e.g., several hours), the more important the role that drug pharmacokinetics and pharmacodynamics can play in making accurate predictions. This requirement necessitates the design of insulin dose guidance and glucose control methods based on more physiological insights.

[0170] This specification describes an insulin dose guidance algorithm that takes into account physiologically relevant processes such as insulin diffusion, subcutaneous pharmacokinetics (PK), and glucose-insulin kinetics. Parameters can be determined by numerically solving a modified minimal model of insulin absorption and glucose control (see Bergman, et al. 1978 and Dalla Man, et al., 2007, whose entire contents are expressly incorporated herein by reference) during a “learning phase” for developing user-specific model parameters. Once these parameters are determined, the optimal insulin dose at that point in time can be determined by solving the user-specific minimal model for both mealtime and adjusted doses.

[0171] As similarly described in other embodiments, the DGA can receive or otherwise access glucose values ​​and trends from a glucose monitoring system. The DGA can be configured to prompt the user whether to administer an dose in the near future, and can also be configured to prompt the user for which meals require dose guidance. The DGA can be configured to output dose recommendations based on an algorithm, for example, a physiological dose guidance algorithm or another algorithm described herein. The DGA can then be configured to observe whether the user is adhering to the dose guidance, and can also track the resulting glucose trace for consideration of future dose guidance.

[0172] The DGA can be configured to include a physiological dose guidance algorithm that determines the optimal dose output in the dose guidance. In one embodiment, dose guidance can be provided for users with a frequent insulin injectable (MDI) regimen with once-daily long-acting analogs and three-times-daily rapid-acting meal analogs. This methodology can also be applied to other MDI strategies, such as basal insulin alone or basal insulin with a single rapid-acting injection.

[0173] In an exemplary embodiment, as shown in the flowchart of Figure 9A, in an exemplary method 900 beginning from step 904, DGA determines the possible bolus insulin dose (u1, u2, ..., u) based on past administration history. n ) can be automatically generated. In step 906, the physiological dosage guidance algorithm processes possible insulin doses and, for each bolus insulin dose input, glucose time course (g 1, g2,...,g n )(for example, a data array) can be generated and output. Then, in step 908, the DGA generates cost function values ​​(C1, C2, ..., C) for each glucose time course. n The cost function can be calculated. The cost function can be defined to minimize the time outside the time course range for each glucose time course (e.g., outside the range of approximately 70 mg / dL to approximately 180 mg / dL). In step 910, DGA can determine the optimal insulin bolus dose that minimizes the cost function value.

[0174] The optimal insulin bolus dose (u) to be delivered at time t can be determined from the estimated glucose trace after simulating insulin administration and carbohydrate dietary input (if necessary). This dose is calculated using the following simple bolus formula:

[0175]

number

[0176] It can be broken down into constituent parts such as the glucose correction part, the dietary compensation part, and the insulin onboard part. However, a physiological dose guidance algorithm does not have to use equation (1) to determine the optimal dose. Instead, a physiological dose guidance algorithm can use the individual components of the equation to enable the user and HCP to understand what dose is intended for the current glucose level in relation to dietary compensation. In the equation, u is the optimal insulin bolus dose. The first term of the equation in parentheses. TIFF0007869626000002.tif13114

[0177] This is the glucose correction part, where the user's current glucose (BG(t)) and target value (BG) at time t are used. target The purpose is to correct any offset between ( ). The correction factor (CF) represents the user's specific sensitivity to insulin, i.e., how effective one insulin unit is in lowering the user's blood glucose level. Term 2 (CHO * IC represents the portion of the insulin dose needed to cover a meal if a meal is consumed. The CHO value indicates the amount of carbohydrates in the upcoming meal, while the IC value indicates the subject-specific insulin:carbohydrate ratio, i.e., how many grams of carbohydrates can be covered with a given insulin dose. Finally, the IOB value aims to describe the active "insulin onboard" that can still extract therapeutic effects to avoid insulin stacking. This value can be based on insulin pharmacokinetic models and endogenous insulin production. target The IC and Total Daily Insulin (TDD) values ​​can be defined by the user's HCP. In one embodiment, the initial CF can be defined according to the "1800 rule," which is defined as 1800 / TDD. Furthermore, in one embodiment, during the learning phase, the CF can be improved based on corrected dose data.

[0178] Physiological dose guidance algorithms can use different methods to determine dose guidance for corrected dose, meal dose, and basal dose. However, in all three types of dose guidance, it can be assumed that the duration of action of each can be considered equivalent, since DGA uses a rapid-acting insulin analog (e.g., insulin lispro, aspart, or glulisine) and all three types have similar subcutaneous PK profiles.

[0179] correction dose If DGA requests dose guidance for the corrected dose, the corrected dose is not related to the meal, so there are no new carbohydrates to consider, and therefore CHO = 0. Thus, the second term of equation (1) is equal to 0. Therefore, the components of the corrected dose are the glucose correction component and IOB.

[0180]

number

[0181] In one exemplary embodiment, as shown in the flowchart of Figure 9B, once a corrective dose is prompted by exemplary method 911, starting from step 912, the DGA can generate a plurality of insulin dose candidates. In one embodiment, the plurality of insulin dose candidates can be generated based on the historical data of the insulin dose in question.

[0182] In step 914, the DGA can determine multiple glucose time courses corresponding to multiple insulin dose candidates. In one embodiment, the DGA can calculate the subject-specific glucose time course using a physiological dose guidance algorithm with a minimum model modification for the range of possible dosages. Each dose candidate can be considered as the sum of the injected insulin dose and the amount of long-acting insulin currently onboard. The amount of IOB can be calculated from the pharmacokinetics specific to the subject's long-acting analog and can be the same across all candidate input dose candidates. Numerical differences between all candidate insulin doses may be due to differences in the rapid-acting component of the overall dose.

[0183] In step 916, the DGA can calculate multiple cost function values ​​corresponding to multiple glucose time courses. In one embodiment, for each glucose time course, different glucose control indices can be calculated and used to determine cost function values ​​that describe the risk of time outside the target range (e.g., approximately 70 mg / dL to approximately 180 mg / dL).

[0184] An exemplary cost function is shown in Equation 5 below, but many other forms can be used. The area under the curve (AUC) is used in these calculations to incorporate both the magnitude and duration of hyperglycemic / hypoglycemic events.

[0185]

number

[0186]

number

[0187]

number

[0188] AUC HYPO and AUC HYPER The threshold values ​​can be defined as the minimum time and duration spent in any regime. Each term in C may have associated weighting coefficients w, and their universal set {w1, w2, ..., w} n The sum of the values ​​must equal 1. This weighting allows for prioritizing protection from hypoglycemic events. The insulin dose associated with the minimum cost function value can be the suggested dose in the dose guidance output by DGA.

[0189] In step 918, the DGA can determine the optimal insulin dose, which has the lowest cost function value among several cost function values. In one embodiment, the DGA can be configured to determine the optimal insulin dose as a dose candidate that minimizes an out-of-range time-related cost function C.

[0190] In step 920, the DGA can output dose guidance including the determined optimal insulin dose.

[0191] In another embodiment, instead of simulating the resulting glucose trace from a speculative set of possible insulin doses and selecting the best option, in an alternative embodiment, DGA can provide an initial dose estimate from which the glucose horizon and cost function values ​​can be tracked. A constrained minimization of the cost function can then be performed using either a gradient-based or non-gradient-based approach (e.g., a genetic algorithm). Thus, each insulin dose estimate can be selected following the initial dose to minimize the cost function.

[0192] Once the optimal insulin dose is determined, it can be further subdivided to help the user understand what situations require correction and how much insulin is currently on board.

[0193] Dietary dosage If DGA requests dose guidance for a meal dose, similar to the calculation of corrected doses described above, DGA can calculate a user-specific glucose time course within the range of possible dosages using a minimum model modification. Because dose guidance is meal-related, unlike the process of determining corrected doses, DGA can also consider additional meal carbohydrate information when determining dose guidance. Because dose guidance is meal-related, CHO is greater than zero, and the components of the meal dose include additional meal carbohydrate information (CHO). * This may include IC. Thus, the components of the dietary dose include a glucose correction portion, a dietary compensation portion, and IOB, according to formula (1).

[0194] In one exemplary embodiment, in an exemplary method 921 beginning in step 922, as shown in the flowchart in Figure 9C, the DGA may determine the distribution of carbohydrate values ​​in a meal in response to a user inquiry regarding meal dosage guidance. The distribution of carbohydrate values ​​may include central tendency carbohydrate values, low carbohydrate values ​​smaller than the central tendency carbohydrate values, and high carbohydrate values ​​larger than the central tendency carbohydrate values. In one embodiment, a meal may be represented as a meal-specific distribution of carbohydrate values ​​with known descriptive statistics describing the central tendency (e.g., mean or median) and variability (e.g., standard deviation, coefficient of variation, 25th / 75th percentile values). These data may be transformed to provide these summary statistics. As a result, each meal may have its own carbohydrate distribution.

[0195] In one embodiment, the central tendency carbohydrate value may be the mean or median. In one embodiment, the low carbohydrate value may be, for example, the 25th percentile of glucose data, instead of the 30th percentile, instead of the 35th percentile, instead of a value between the 20th and 40th percentiles, or instead μ-σ if the data is normally distributed. In one embodiment, the high carbohydrate value may be, for example, the 75th percentile, instead of the 80th percentile, instead of the 65th percentile, instead of the 60th percentile, instead of a value between the 60th and 80th percentiles of glucose data, or instead μ+σ if the data is normally distributed.

[0196] In step 924, DGA can determine multiple insulin dose candidates for each of the central tendency carbohydrate values, low carbohydrate values, and high carbohydrate values. In one embodiment, multiple insulin dose candidates can be generated based on the historical data of the target insulin dose.

[0197] In step 926, the DGA can determine multiple glucose time courses corresponding to multiple insulin dose candidates for each of the central-tendency carbohydrate values, low-carbohydrate values, and high-carbohydrate values. In one embodiment, the DGA can calculate the subject-specific glucose time course using a physiological dose guidance algorithm with respect to corrected doses, as described above, using a minimum model modification for the range of possible dosages. Each dose candidate can be considered as the sum of the injected insulin dose and the amount of long-acting insulin currently onboard. The amount of IOB can be calculated from the pharmacokinetics specific to the subject's long-acting analog and can be the same across all candidate input doses. Numerical differences between all candidate insulin doses may be due to differences in the rapid-acting component of the overall dose.

[0198] In step 928, the DGA can calculate multiple cost function values ​​corresponding to multiple glucose time courses for each of the central trend carbohydrate values, low carbohydrate values, and high carbohydrate values. In one embodiment, for each glucose time course, different glucose control indices can be calculated and used to determine cost function values ​​that describe the risk of time outside the target range (e.g., approximately 70 mg / dL to approximately 180 mg / dL). While many other forms can be used, in one embodiment, the DGA can be configured to calculate multiple cost function values ​​using the exemplary AUC analysis described with respect to corrected dose calculation. In other embodiments, for each glucose time course, different glucose values ​​of a predetermined percentile of glucose values ​​within a predetermined (rolling) time window can be determined. For example, instead of a time percentage of hypoglycemia, or instead of an AUC below the low glucose threshold, the 5th percentile value (or other percentile below 30%) within the time window can be calculated and compared to the low glucose threshold. The time window can be a fixed function of the time period within a day, e.g., 9am to 11am, relative to the start and / or end of an event, e.g., approximately 30 minutes after a meal, or alternatively, approximately 300 minutes after a meal, or other definitions. Alternatively, different low percentiles with corresponding low glucose thresholds can be used. Instead of the percentage of time spent in a hyperglycemic state, or instead of the AUC above the high glucose threshold, the 90th percentile value (or any other percentile greater than 70%) can be calculated within the time window and compared to the high glucose threshold.

[0199] In step 930, DGA can determine the optimal insulin dose for each of the central tendency carbohydrate values, low carbohydrate values, and high carbohydrate values. The optimal insulin dose may be the dose with the lowest cost function value among several cost function values ​​for each of the central tendency carbohydrate values, low carbohydrate values, and high carbohydrate values.

[0200] In step 932, the DGA can output multiple dose guidances, including the optimal insulin dose determined for each of the central-tendency carbohydrate values, low-carbohydrate values, and high-carbohydrate values. The dose guidance related to the central-tendency carbohydrate value can correspond to the median meal dose guidance. The dose guidance related to the low-carbohydrate value can correspond to the “smaller than usual” meal dose guidance. The dose guidance related to the high-carbohydrate value can correspond to the “larger than usual” meal dose guidance. In one embodiment, the DGA can output not only the range of meal dose guidance considering the current glucose value but also the distribution of meal carbohydrate values. In extreme cases, it can be modified or distorted as needed. For example, the optimal insulin dose associated with a larger than usual meal may need to be based on the 60th percentile rather than the 75th percentile to avoid postprandial hypoglycemia as a result of an overdose bolus. Using formula (1), the optimal insulin dose can be further divided to show the user and HCP the amount allocated to the meal or the amount allocated to the pre-meal glucose level. In one embodiment, each component of the dose guidance (e.g., glucose correction portion, dietary compensation portion, and IOB) may be output and displayed to the user and / or HCP.

[0201] Basal dose The basal dose of long-acting insulin analogs is administered once or twice daily, depending on the chosen drug. For example, insulin glargine has a 24-hour duration of action and is administered once daily, while insulin detemir has a 12-hour duration of action and is administered twice daily. Because these time scales are much longer than the 4-5 hour duration of action associated with rapid-acting analogs, long-acting analogs can encompass different subcutaneous insulin PK profiles. The time course of action is the difference in the case of basal doses compared to the other two. Similar to corrected doses, basal administration is not meal-dependent and is rather present with all meals due to its extended pharmacokinetic profile.

[0202] In one exemplary embodiment, referring to the flowchart in Figure 9B, starting from step 912, when the DGA is prompted for basal dose guidance, the DGA can generate multiple basal insulin dose candidates. In one embodiment, the multiple basal insulin dose candidates can be generated based on the historical data of the basal dose in question.

[0203] In step 914, the DGA can determine multiple glucose time courses corresponding to multiple basal insulin dose candidates. In one embodiment, the DGA can calculate the subject-specific glucose time course using a physiological dose guidance algorithm with a minimum model modification for a range of possible dosages. The amount of IOB can be calculated from the pharmacokinetics specific to the insulin analog dose of the subject and can be the same across all candidate input doses.

[0204] In one embodiment, the DGA can be configured to extend multiple glucose time courses in terms of time to reflect the longer duration of action (e.g., 12 or 24 hours) associated with long-acting analogs. Since basal insulin is typically a once-daily drug, long-acting basal guidance can be formulated to prompt the user at the same time each day. Similar to corrected dose and meal dose determination, the DGA can be configured to generate a blood glucose profile for basal dose candidates. Each of the multiple glucose time courses includes three meal events, each of which may include an associated rapid-acting dose input to simulate the variation within a 24-hour window of basal action. Each meal event may include both a carbohydrate input and a rapid-acting insulin input. In one embodiment, the value of the insulin input can be based on subject-specific median rapid-acting analog requirements from MDD152 data. In one embodiment, the meal input can be represented by the centrally trending carbohydrate amount (e.g., median or mean carbohydrate amount), as described in the meal dose guidance determination. In one embodiment, the meal event may be the same for all basal simulation events within a single dose guidance. In one embodiment, the basal dose is the only input value that changes.

[0205] In step 916, DGA can calculate multiple cost function values ​​corresponding to multiple glucose time courses. In one embodiment, for each glucose time course, different glucose control indices can be calculated and used to determine cost function values ​​that describe the risk of time outside the target range (e.g., approximately 70 mg / dL to approximately 180 mg / dL). In one embodiment, the cost function analysis for multiple glucose time courses generated for multiple basal dose candidates may be the same as that described with respect to the corrected dose analysis. In another embodiment, the cost function analysis for multiple glucose time courses generated for multiple basal dose candidates may be different from the cost function analysis used for the corrected dose analysis.

[0206] In step 918, the DGA can determine the optimal basal insulin dose having the lowest cost function value among a plurality of cost function values. In one embodiment, the DGA can be configured to determine the optimal insulin dose as a basal dose candidate that minimizes an out-of-range time-related cost function C.

[0207] In step 920, the DGA can output dose guidance including the determined optimal insulin dose.

[0208] Correction factor titration Next, an exemplary embodiment of a method for determining correction factor titration is described. Although initiated by a physician, insulin administration for diabetic patients has been primarily patient-centered in managing the disease throughout its course. These management methods are often empirical, with patients learning through trial and error to improve their diabetes management. More quantitative determination methods when using MDIs often rely on simple approaches such as insulin bolus calculators, which depend on frequent blood glucose measurements or values ​​that are difficult to determine and understand from the patient's perspective, such as the insulin:carbohydrate ratio or insulin correction factor. The algorithmic subroutine described here aims to leverage detailed glucose data from a CGM device and insulin administration information from a Bluetooth-enabled insulin pen to titrate patient-specific administration parameters previously learned during a passive observation period to an optimal level, thereby providing personalized dose guidance that evolves with the user with minimal user input.

[0209] As described elsewhere in this specification, to provide initial dose guidance, the DGA can go through a “learning phase” to verify user-specific dosing parameters such as fixed mealtime doses, target glucose, and insulin correction factors. The method for the learning phase is described in relation to Figure 7 of this specification. These parameter values ​​serve as initial estimates and can be further titrated to more optimal patient-specific values ​​as the system is used. This approach of continuous parameter titration following initial learning allows for adaptation not only to disease progression but also to external changes in both lifestyle and pharmacotherapy that the user may experience. As the class of insulin-based diabetes treatments becomes increasingly prevalent and can enhance both endogenous insulin production and insulin sensitivity, the user’s correction factor cannot remain a static value for the lifetime of the system. This specification describes a method for titrating the user’s insulin correction factor (also referred to as insulin sensitivity).

[0210] As used in many embodiments of DGA, the user's correction factor does not have to be a single value, but may be a distinct set of values ​​specific to a given meal type (e.g., breakfast, lunch, dinner). The correction factor may have units of mg / dL glucose per insulin unit. A high correction factor indicates that the user is highly sensitive to insulin, as glucose drops significantly with small doses. Conversely, a low correction factor suggests that the user is less sensitive to insulin. An effective mealtime insulin dose needs to return postprandial blood glucose levels to a safe range within its pharmacodynamic window. For example, assuming the dosing rules of a bolus calculator as described in relation to Figures 8A-8H, the accurate correction factor should take into account both the carbohydrate intake from the meal and the pre-meal glucose increase, thereby contributing to an insulin dose that returns glucose levels to a safe and stable target value. Therefore, if GPA plots all insulin doses for a particular meal against a specific index that quantifies glucose readings over a meal-related time period (e.g., an index that quantifies meal-related glucose data or excursions, such as a time-based dose setting after administration (e.g., 4 hours), or a percentile of glucose values ​​during the meal-related time period (e.g., 5th percentile, 10th percentile)), then theoretically, the best fit of this data would be a straight line with a slope of zero and a y-intercept equal to the user's target glucose. In practice, all mealtime insulin doses bring the user's blood glucose levels back to the target value or range.

[0211] A zero slope in the insulin-to-postprandial glucose relationship represents an ideal scenario for the administration effect. The DGA can be assumed to have pre-learned the user's fixed dose, for example, through user input or transmission from MDD152. For doses greater than the fixed dose, the system can observe the relationship between insulin dose and postprandial glucose from SCD102 or other sources. The DGA can evaluate dose effectiveness using one or more methods, including but not limited to:

[0212] Steps to determine the centroid (median / mean) of postprandial glucose levels. This method uses the difference between a centroid of postprandial glucose levels for an uncorrected insulin dose and a centroid of postprandial glucose levels for an insulin dose with corrections. The ideal scenario is that there is no significant difference between the two centroids. A positive difference above a given threshold is considered to indicate a suboptimal correction factor. Similarly, a negative difference below a given threshold is considered to indicate a correction factor that is higher than optimal.

[0213] Steps to apply a linear fit to the data If the goodness-of-fit criteria are met, DGA can perform a statistical test to determine if there is a statistically significant difference between the slope of the best fit and the ideal case where the slope is zero. If the slope is less than zero, the insulin dose is too high. This corresponds to the correction factor being too low and therefore needing to be increased. If the slope is greater than zero, it indicates that postprandial glucose is elevated and the insulin dose can be increased. This corresponds to the correction factor being too high and therefore needing to be decreased. The amount of titration for these values ​​may vary depending on the slope of the fit. A steeper slope requires more aggressive titration than when it is close to zero. This titration method is independent of fixed-dose titration and can be performed in parallel with fixed-dose titration.

[0214] Steps to determine the area under the postprandial glucose / insulin curve In an ideal administration scenario, there can be a constant area, indicating that glucose levels return to a constant level after all administrations. Therefore, DGA can be evaluated as indicating an error in the correction factor for any change within the area. The integral method can be used to determine whether the meal-time administered component corresponding to the fixed meal dose is effective or whether further titration is necessary. If the integral level is elevated compared to the ideal scenario, it indicates that the fixed dose can be increased to bring the postprandial value closer to the target level.

[0215] During a defined learning phase, for example, up to 14 days depending on the characteristics of SCD or other factors, DGA can learn the user's medication strategy or other user-specific parameters, including but not limited to dosage, correction factors, and insulin action time (IAT) / insulin onboard (IOB). It may be desirable to titrate the correction factors for one or more of the following reasons: (1) when the correction factors are insufficient, or (2) when they change due to therapeutic intervention or environmental changes. In the case of bolus administration (without carbohydrate counting) including only correction, DGA can analyze postprandial glucose values ​​to incrementally titrate the correction factors. For example, if the postprandial glucose peak is greater than 180 mg / dL, or the difference between the postprandial peak and the preprandial value is higher than the threshold and there is no risk of postprandial hypoglycemia, the correction factors can be incrementally titrated per measurement cycle. For example, the correction factors can be titrated by a preset value, e.g., a 1-unit increment, or instead a 2-unit increment. In the case of isolated corrective medications (e.g., no meal) administered to treat hyperglycemia when glucose levels are high, the correction factor can be titrated using the difference between the glucose value at the time of administration and the glucose value at a predetermined time (e.g., 4 hours after administration).

[0216] Mealtime insulin administration consists of two distinct portions: a) a portion intended to cover the meal consumed, and b) a portion intended to address pre-meal glucose levels exceeding the target range. The meal-related portion is typically fixed (for example, the portion taken with breakfast is always a specific amount, which can be titrated over time) or varies according to the amount of carbohydrates the patient is expected to consume. In the following examples, a fixed meal dose is assumed. However, the following description can be applied to a variable portion, the actual portion of which is determined by a fixed ratio of carbohydrates to insulin, and this ratio itself can be titrated. As used herein, the portion for addressing pre-meal glucose refers to a corrected dose or corrected portion determined by a pre-meal correction factor.

[0217] The pre-meal correction factor can be used to control MDD152. Reducing or down-titrating the correction factor is equivalent to increasing the corrected dose, as described herein. For example, Figure 10A shows Method 500 by DGA for providing a pre-meal correction factor in response to analyte data for use in controlling MDD152. In 502, Method 500 may include the step of determining the analyte pattern type for at least one TOD period by running a GPA algorithm that takes time-correlated analyte data transmitted from a sensor control device worn by the patient over the analysis period as input, using at least one processor. In 504, Method 500 may include the step of determining a pre-meal correction factor based on the analyte pattern type and the patient's defined dosing strategy for the analysis period, using at least one processor running an algorithm. In 506, Method 500 may include the step of storing an indicator of the pre-meal correction factor in computer memory for output to at least one user or dosing device. In contrast to the linear fitting embodiments described above, the embodiments described herein are a unified approach in which fixed dose and correction coefficient titration can be performed simultaneously through a single technology or software function (e.g., a single logic tree).

[0218] In a relevant embodiment, Figure 8B and the relevant description above disclose a GPA method 410 for classifying a patient's glucose pattern as high, low, or high / low over various TOD periods. Figure 8A and the relevant description disclose a method for a DGA to use the output from GPA 410 to provide MDI dose guidance recommendations. Figures 8D–8H and the relevant description show an example of an algorithm for a DGA to provide specific MDI dose guidance recommendations based on the glucose pattern type output by GPA 410 and the patient's defined medication strategy over the analysis period. The recommendations may be provided for automated or semi-automatic control of MDD 152, or for operation of a user interface to guide manual medication control.

[0219] Figure 10B shows a method 510 for evaluating recommended values ​​for titrating meal dose and pre-meal adjustment to raise high analyte levels, with or without pre-meal adjustment, when GPA shows a low pattern, for example. In a related embodiment, Figure 8G shows an example of algorithm 474 for formulating recommendations for post-meal adjustment. When run by DGA, algorithm 474 asks whether to consider whether to perform pre-meal adjustment when GPA shows a low pattern, considering analyte data excluding data from TOD periods where bolus doses were forgotten. Other low glucose pattern conditions 512 during TOD periods may also be appropriate to trigger the execution of method 510. If both meal dose and pre-meal adjustment are higher than the optimal value, method 510 may output a pre-meal adjustment coefficient that only reduces the meal dose. If there is a low pattern, this may be due to a high fixed dose, a high pre-meal adjustment, or both. In one embodiment, the fixed dose and pre-meal adjustment can be titrated sequentially, with the fixed dose being titrated first as it forms the basis of the dosage. If a low pattern is still observed after the fixed dose has been adequately titrated, the corrected dose may be titrated. In another embodiment, the fixed dose and the pre-meal corrected dose can be titrated in parallel.

[0220] If a low pattern is detected during the TOD period, DGA can determine in 514 whether the meal dose of the defined medication strategy includes pre-meal adjustments. If it does, in 534, DGA can exclude days on which the bolus was forgotten from the original dataset or pre-meal adjustments by, for example, including only a portion of the analyte data for days on which meal administration was performed and the bolus was not forgotten. In 536, DGA can test whether sufficient data remains after excluding data for days on which the bolus or pre-meal adjustment was not forgotten in order to achieve the minimum confidence level. If sufficient data exists, in 410, DGA can repeat GPA410 on the input analyte dataset excluding data for days on which the bolus or pre-meal adjustment was forgotten.

[0221] At 538, DGA can determine if the subsequent glucose pattern is still low; if so, at 540, reduce only the meal portion of the insulin dose. If the pattern is not low, at 542, DGA can reduce the pre-meal adjustment factor, which, if performed by the user or MDD, will reduce the corresponding pre-meal adjustment dose.

[0222] If, at 536, DGA determines that there is insufficient data to determine the pattern, at 516, DGA may include data for days when meal administration and pre-meal adjustments were performed. Then, at 518, DGA may retest the sufficiency of the dataset. If the data is sufficient, at 410, DGA may repeat the GPA on the expanded dataset. At 540, if the resulting glucose pattern is not low, DGA may reduce the recommended values ​​for the meal portion of each dose in the relevant TOD period without reducing the pre-meal adjustment factor. If, at 520, DGA determines that the glucose pattern is low, at 526, DGA may include data for meal doses only. Then, at 530, DGA may retest whether the dataset is sufficient. If the dataset is insufficient, at 528, DGA may reduce both the meal dose and the adjusted dose. If the dataset is sufficient, DGA may perform a GPA at 410 and determine at 532 whether the glucose pattern is low. If the glucose pattern is low, DGA at 540 allows for a reduction in the recommended meal portion of each dose during the relevant TOD period without reducing the pre-meal adjustment factor. If the glucose pattern is not low, GPA at 542 allows for a reduction in the pre-meal adjustment factor, which, when performed by the user or MDD, allows for a reduction in the corresponding pre-meal adjustment dose.

[0223] Figure 10C shows a method 550 for evaluating recommended values ​​for titrating meal dose and pre-meal correction to reduce high analyte levels, with or without pre-meal correction, when, for example, GPA 410 shows a high pattern. In a related embodiment, Figure 8H shows an example of algorithm 480 for formulating recommendations for post-meal correction. When performed by DGA, algorithm 480 prompts consideration of whether to perform pre-meal correction if GPA shows a high pattern. Other high glucose pattern conditions 552 during the TOD period may also be appropriate to trigger the execution of method 550. If both meal dose and pre-meal correction are below the optimal value, method 550 may first increase the meal dose. High glucose patterns can be addressed sequentially so that the corrective dose can be up-titrated after the meal dose has been titrated to avoid hypoglycemia by both increasing the fixed dose and decreasing the correction factor (similar to increasing the corrective dose at a given blood glucose level) (patterns that are not high with uncorrected data). High patterns can be addressed by first increasing the fixed dose. If high-risk patterns still persist and occur only when a corrective dose is included, the correction factor can be titrated.

[0224] If a high pattern is detected for a particular TOD, at 554, the DGA can determine whether the dietary dose for which pre-meal correction has been made is included in the analyte data. If no pre-meal correction is included, at 564, the DGA can exclude the data for the day on which pre-meal correction was made and the day on which the bolus was missed from the original data set and repeat the glucose pattern analysis at 410. At 566, the DGA can determine whether the subsequent glucose pattern is still high. If not, at 572, the DGA can increase the pre-meal correction factor, which will cause a decrease in the pre-meal correction dose by outputting to the UID or MDD. If the glucose pattern is high otherwise, at 562, the DGA can increase the recommended value of the dietary portion of each dose for the relevant TOD period. If it is determined at 554 that pre-meal correction is included, at 556, the DGA can exclude the data for the day on which dietary administration and pre-meal correction were made and the data for the day on which the bolus administration was missed from the original data set and repeat the glucose pattern analysis at 410. At 558, the DGA can determine whether the subsequent glucose pattern is still high. If the pattern is not high, at 562, the DGA can increase the recommended value of the dietary portion of each dose for the relevant TOD period. If the pattern is high at 558, at 564, the DGA can exclude the data for the day on which pre-meal correction was made, exclude the data for the day on which the bolus was missed, and repeat the pattern analysis at 410 and the subsequent steps described above.

[0225] Figures 10B - 10C show aspects of various algorithms for determining the pre-meal correction factor, but it should be understood that these are illustrative. Various other algorithms may also be suitable.

[0226] Insulin dosage guidance method according to administration timing (at the start of a meal or before and after the start of a meal) Next, an exemplary embodiment of a method for determining dosage guidance according to administration timing will be described. To maximize glycemic control, it is desirable for insulin dosing to be temporally synchronized with meals such that the peak of circulating insulin coincides with the post-meal glucose rise. However, patients may forget to take their pre-meal insulin dose before eating. As a result, a mismatch may occur between the glucose rise related to the meal and insulin action, and the appropriate dosage may become unclear. Taking the meal dose after the start of the meal rather than immediately before the start of the meal may cause hypoglycemia. This is because active insulin may still be circulating even after the post-meal glucose rise has subsided. Additionally, patients correcting glucose trends may tend to increase the dosage because the glucose trend at the start of the meal is upward. Such behavior can also cause hypoglycemia. To minimize hypoglycemic episodes related to timing, the DGA can be configured to determine the delay in dosing time and take the delay in dosing time into account when providing dosage guidance. A positive delay time indicates that the insulin dose is administered after the start of the meal. A zero delay time indicates that the insulin dose is administered approximately simultaneously with the start of the meal. A negative time delay indicates that the insulin dose is administered before the start of the meal.

[0227] In many embodiments, the DGA can be configured to include a method for detecting in real-time the omission of meal administration for the purpose of determining whether the meal dosage guidance calculation should be an "on-time" calculation (i.e., zero or negative time delay) or a "late dose" calculation (i.e., positive time delay). In some embodiments, the DGA can also be configured to determine and output an estimated value of the start time of the meal that can be used in the delayed dosing calculation. In some embodiments, if the meal-time insulin dose is not detected +X minutes or -Y minutes after the estimated start of the meal, the DGA can be configured to notify the patient that the administration may have been omitted.

[0228] Algorithm for real-time detection of forgotten meal administration In many embodiments, the DGA can be configured to detect missed meal administrations using a real-time meal detection algorithm. Systems and processes for detecting missed meal administrations in real time and subsequently alerting the patient are described herein. The process for detecting missed meal administrations can be performed periodically (for example, whenever new glucose data becomes available in the system). Alternatively, the process can be performed whenever it is appropriate to provide the patient with a “missed dose” alert, or whenever the alert has been activated.

[0229] In an exemplary embodiment, real-time meal detection can be performed by a feature extraction module and a meal detection module. The feature extraction module can receive CGM data points one at a time as data points become available. When the feature extraction module detects an increase in glucose levels, it can extract multiple features and pass these features to the meal detection module for meal detection.

[0230] In one embodiment, the feature extraction module is configured to perform data smoothing by fitting the data within a time window using a quadratic function and working backward from the current data point each time a new glucose data point is received. The time window can be approximately 60 minutes. The feature extraction module can be configured to store the fitted value at the center of the time window as the current smoothed data. The feature extraction module can also be configured to store the coefficients of the linear and quadratic terms of the fitted value at the center of the time window as the current glucose rate of change and acceleration value, respectively. In addition to being configured to store the fitted value at the center point, the feature extraction module can also be configured to store the fitted value at the current point for feature extraction. The feature extraction module can be configured to determine whether the smoothed glucose data is increasing or decreasing by comparing the current smoothed glucose value with the previous smoothed glucose value (e.g., the smoothed glucose value immediately preceding the current smoothed glucose value). The feature extraction module can be configured to extract multiple features and then pass the multiple features to the diet detection module after the feature extraction module has determined that the current smoothed glucose value is increasing in comparison with the previous smoothed glucose value.

[0231] The feature extraction module can be configured to extract multiple features from two segments of smoothed data. These two segments can be the current ascent segment and the previous descent segment. Multiple features extracted from the current ascent segment may include, but are not limited to, the following: 1) maximum acceleration, 2) time of the maximum acceleration point, 3) glucose value at the maximum acceleration point, 4) height calculated from the difference in glucose value between the current time (fitted value) and the maximum acceleration point (reference point), 5) duration of the current segment calculated from the elapsed time from the reference point to the current point, 6) average rate of ascent of the current segment calculated by dividing height by duration, 7) maximum increase in acceleration (the increase in acceleration at a given time is obtained by subtracting the acceleration at that time from the acceleration at the previous time), and 8) increment of area under the curve (average glucose value minus the glucose value at the reference point, multiplied by the duration of the segment). Multiple features extracted from the previous descent segment may include, but are not limited to, 1) duration, 2) height, 3) average descent rate (height / duration), 4) maximum descent rate (maximum absolute value of the rate of change), and 5) maximum deceleration (maximum absolute value of the acceleration). The feature extraction module can be configured to pass the extracted features to the meal dosage module.

[0232] The meal detection module can be configured to accept a feature vector as input and output a binary detection result indicating whether the current rising segment is a meal-response glucose excursion. The meal detection module can also be configured to output a probability value along with the binary detection result. In one embodiment, the pre-trained machine learning model in the meal detection module can be implemented using a random forest classifier by scikit-learn (https: / / scikit-learn.org / stable / modules / generated / sklearn.ensemble.RandomForestClassifier.html). The meal detection module can be configured to detect the start of a meal based on tree building rules and feature thresholds for each feature in each tree, which can be optimized during the training process. In one embodiment, the pre-trained model can also be built on alternative classification algorithms including gradient boosting, ADA boosting, artificial neural networks, linear discriminant analysis, and extra trees.

[0233] The meal detection model can also be configured to estimate the start time of a meal when a meal is detected. In one embodiment, the start time of a meal can be estimated as the point in time when there is a maximum increase in glucose acceleration, working backward from the detection point within a time window size of approximately 1.25 hours. For example, if the algorithm detects a forgotten meal at 1:15 p.m., the model can determine the start time of the meal by working backward to around 12 p.m. The glucose acceleration at each point can be expressed as a quadratic function, i.e., y=ax 2 This can be calculated by fitting five data points centered on the data point of interest using +bx+c. The fitted parameter "a" is the acceleration at the point of interest. The increase in the acceleration of glucose value at a given time k can be defined as a(k+1)-a(k).

[0234] The meal detection model can also be configured to output a notification to the user regarding medication forgetting via UID200 if it is not detected that mealtime insulin administration was performed within the period before and after the estimated start of a meal. In one embodiment, if the estimated start of a meal is less than two hours away, the notification may also indicate that the patient can still receive meal dose guidance and that medication administration will be delayed.

[0235] Details of other types of meal detection methods and algorithms are described in U.S. Patent Publication No. 2017 / 0185748 and PCT Application No. PCT / US2020 / 12134, which are incorporated herein by reference in their entirety.

[0236] Dosage guidance administered at the start of a meal If the delay in medication timing is negative or zero (i.e., the dose guidance is for administration at or before the start of a meal), the DGA can be configured to account for other factors that may modify the risk of hypoglycemia and hyperglycemia in order to take into account the time span over which bolus insulin can exert its effect before the presence of a meal. For example, the DGA can be configured to include a risk factor related to circadian rhythms.

[0237] In an exemplary embodiment, as shown in the flowchart of Figure 11, in exemplary method 600, the DGA may provide dose guidance for administration to a subject at the start of a meal, for example, when the time delay is negative or zero. Starting in step 602, the DGA may determine a first dose guidance for a meal to be administered at the time of meal initiation. The first dose guidance may be a fixed meal dose (with or without correction) or may be based on the carbohydrate content of the meal.

[0238] In step 604, the DGA can then determine whether there is a risk of hypoglycemia based on at least the first dose guidance and the time of day the dose is administered. The DGA can be configured to determine the risk of hypoglycemia by referring to a risk map. In one embodiment, historical user data (e.g., glucose level and insulin dosage data), population data, or a combination of both historical user data and population data can be used to develop a risk map related to time of day, day of the week, and / or other available patterns. In one embodiment, the DGA can be configured to use the risk map to identify distributional edges close to the highest risk, rather than identifying typical behaviors.

[0239] In step 606, the DGA may output a second dose guidance that differs from the first dose guidance. The second dose guidance may be output to UID200 and may include a lower drug dose than the first dose guidance. The second dose guidance may also be associated with a lower risk of hypoglycemia than the first dose guidance. For example, if a first time zone has a higher risk of hypoglycemia in the near future than another (second) time zone, and the user requests dose guidance at the start of a planned meal or in the first time zone before the start of a meal, the DGA may be configured to output a dose guidance lower than the nominal proposed meal dose guidance (e.g., a fixed meal dose (adjusted or unadjusted) or a meal dose based on carbohydrate content).

[0240] If the dose is administered after the start of a meal (i.e., if the medication time delay is positive), the DGA can be configured to determine the medication time delay and output dose guidance that takes into account the medication time delay and any associated risks.

[0241] In one exemplary embodiment, as shown in the flowchart of Figure 12A, in exemplary method 607, starting from step 608, the DGA may, in response to an inquiry from the subject, determine a first dose guidance for a meal, the first dose guidance determined to be administered to the subject at the start of the meal. In one embodiment, the DGA may be configured to assume that the initial optimal mealtime medication is administered simultaneously with the start of the meal. Thus, in one embodiment, when a user opens the DGA and requests dose guidance, the algorithm can first calculate the optimal insulin dose to be administered at the start of the meal. The optimal insulin dose for a meal can be determined in a number of ways, including, but not limited to, a fixed meal dose (with or without adjustment) or a meal dose based on carbohydrate content.

[0242] In step 610, the DGA can determine whether there is a time delay between the start of a meal and the subject's inquiry (i.e., the start of dose guidance). In one embodiment, the DGA can be configured to identify medication time delays in multiple ways. In one embodiment, the DGA can be configured to determine the estimated start of a meal. In one embodiment, the DGA can be configured to identify medication time delays using the meal detection algorithm described above, which can detect the estimated start of a meal, and the DGA can be configured to record the time between the start and the dose guidance prompted by the user. In another embodiment, the DGA can be configured to identify a medication time delay between the start of a meal and the start of bolus insulin administration, which can be recorded by the user. In this embodiment, the DGA can be configured to prompt the user for input regarding the medication time delay. For example, the DGA can be configured to ask the user whether the requested dose guidance is for a meal or for a corrective dose to correct high glucose. If the requested dose guidance is for a meal, the DGA can be configured to ask whether the meal has already started, and if so, for how long. This input can then be used as a meal-versus-medication time delay for dose guidance.

[0243] In step 612, the DGA may, in response to the time delay determination, determine whether there is a risk of hypoglycemia based on at least the first dose guidance and the time delay. In one embodiment, the first dose guidance and the time delay may determine whether the patient is in a high- or low-glycemic risk range or at risk of hypoglycemia compared to the rest of the user population.

[0244] In one embodiment, DGA can determine the risk of hypoglycemia by referring to a multidimensional surface map. In one embodiment, the map can be population-based. For example, the map can include observations across all DGA users until sufficient data is collected to personalize recommendations based on a specific user requesting dose guidance. In one embodiment, DGA can be configured to receive and store multiple types of data related to a DGA user's mealtime dose. Multiple types of data related to mealtime dose include, but are not limited to, medication time delays, suggested or recommended dose guidance, administered doses, and glucose time series for a predetermined time period after dose administration. The glucose time series can have fixed time intervals, varying time intervals, or a combination thereof between glucose value samples (e.g., from a CGM). Using postprandial glucose data in the glucose time series, a hypoglycemia index specific to a meal / medication episode can be calculated. This hypoglycemia index may be, but are not limited to, a time below approximately 70 mg / dL, a time below approximately 54 mg / dL, or a calculated risk coefficient such as the Hypoglycemia Index (LBG). The hypoglycemia index may also be normalized to the glucose concentration value at the start of the meal. Dose guidance and administered dose can be treated as variables individually, as well as as the difference between them. Then, a multidimensional surface map can be derived in which the resulting hypoglycemia index is a function of various variables. Considering the effects of different meal sizes and circadian rhythms, DGA can create multiple multidimensional surface maps, including multidimensional surface maps for breakfast, lunch, and dinner, respectively. Once the maps are created, DGA can also determine the cutoff value for acceptable hypoglycemia risk. One important variable used in this system may be the meal-to-medication time delay.

[0245] The DGA can be configured to output dosage guidance to the UID200 based on whether the risk of hypoglycemia is determined. If the DGA determines that the first dosage guidance and the time delay do not expose the subject to the risk of hypoglycemia, at step 614, the DGA can output the first dosage guidance. At step 616, the DGA can output a second dosage guidance in response to a determination that there is a risk of hypoglycemia, and the second dosage guidance is associated with a lower risk of hypoglycemia than the first dosage guidance. The second dosage guidance can be output to the UID200. In one embodiment, if the DGA determines that there is a risk of hypoglycemia in the first dosage guidance during the time delay, the DGA can search for a dosage change along the Δ dosage / hypoglycemia risk isopotential of the multi-dimensional surface map that reduces the risk below a predetermined cutoff value. Applying this dosage change to the first dosage guidance can provide an up-to-date dosage guidance for minimizing hypoglycemia. The system can continue to collect information to improve and / or update the multi-dimensional surface map as a function of multiple variables (e.g., dosing time delay, proposed or recommended dosage guidance, administered dosage, and glucose time series over a predetermined time period after dosage administration).

[0246] In another embodiment, the DGA can be configured to determine a late-stage dosage guidance that does not consider endogenous insulin production. The problem with using conventional meal dosage calculations when determining dosage guidance after a meal has started is that usually, even when the user has dosed insulin, the user's glucose increases. If the user administers a meal dosage after the start of a meal and determines the meal dosage using the current glucose value, the user may inject too much insulin and hypoglycemia may ultimately occur. The DGA can be configured to determine a dosage guidance for administration after the start of a meal that mitigates the problem of the user's glucose increase by considering the user's glucose value at the estimated start time of the meal in order to determine a corrective portion of the dosage guidance.

[0247] In an exemplary embodiment, as shown in the flowchart of Figure 12B, in an exemplary method 617 beginning in step 618, the DGA may receive a dose guidance inquiry for a meal with a start time. In step 620, the DGA may determine whether it received a dose guidance inquiry after the start of the meal. In one embodiment, in response to a dose guidance inquiry from the user, the DGA may use the delayed dose detection algorithm described above to determine whether the medication is delayed. In one embodiment, the delayed dose detection algorithm may determine and output an estimated start time for the meal, which the DGA can compare with the time it received the inquiry from the user.

[0248] In step 622, the DGA can determine the user's glucose level in relation to the start time of the meal. In one embodiment, the DGA can determine a glucose value in relation to the start time of the meal (for example, the glucose value that is temporally closest to the start time of the meal).

[0249] In step 624, the DGA can output delayed dose guidance, which includes meal dose guidance and corrected dose guidance. In one embodiment, the corrected dose guidance may be based on the determined glucose level at the start of the meal. The corrected dose guidance may be determined using a bolus calculator to correct for high glucose and may include a glucose correction portion. As previously stated with respect to equation (1), the glucose correction portion of the corrected dose guidance may be determined based on the following equation, where (BG(t)) is the current glucose value and BG target This is the target glucose.

[0250]

number

[0251] In one embodiment, for determining the glucose correction portion for delayed dose guidance, the current glucose value is the glucose value related to the estimated meal start time. In one embodiment, the correction factor may be the user's insulin sensitivity coefficient. In one embodiment, delayed dose guidance is the meal dose guidance plus corrected dose guidance. Meal dose guidance can be determined in a number of ways. In one embodiment, meal dose guidance can be determined based on the estimated carbohydrate content of the meal. In another embodiment, meal dose guidance may be based on a “fixed” or “fixed + corrected” dosing strategy, in which the user takes a predetermined amount of insulin for the meal dose, regardless of the carbohydrate content of the meal.

[0252] In another embodiment, DGA can be configured to determine delayed dosing that takes into account endogenous insulin production. The problem with using conventional meal dose calculations when administering medication after a meal has started is that patients with type 2 diabetes often still produce their own (endogenous) insulin. Therefore, if a user administers medication late after a meal has started, the user may have additional "insulin" produced by their own pancreas, and if this is not taken into account in the dose calculation, it may eventually lead to hypoglycemia. DGA can be configured to determine dose guidance that takes into account the production of additional endogenous insulin.

[0253] In one exemplary embodiment, in an exemplary method 630 beginning with step 632, as shown in the flowchart of Figure 12C, the DGA may determine a first dose guidance for a meal in response to an inquiry from the subject. In one embodiment, the first dose guidance is determined for administration to the subject at the start of a meal. In other embodiments, the first dose guidance may be a fixed meal dose (with or without correction) or a meal dose determined based on at least the carbohydrate content of the meal.

[0254] In step 634, the DGA can calculate the time delay between the start of a meal and the inquiry from the subject. In one embodiment, the time delay can be calculated using the delayed dose detection algorithm described above. In one embodiment, the delayed dose detection algorithm can estimate the detected meal start time and calculate the time delay by comparing the time the dose guidance inquiry from the user is received by the DGA with the estimated start time. The estimated start time can be determined by the DGA as described in relation to other embodiments.

[0255] In step 636, DGA can determine a factor corresponding to the estimated amount of endogenous insulin and the amount of time delay in response to a determination that the time delay is greater than zero (>0). In one embodiment, the factor may be a fraction. In one embodiment, the factor may be determined by the amount of time between the query and the estimated start time of the meal, for example, from a universal lookup table in which the fractional value decreases as the time delay from the start of the meal increases.

[0256] In step 638, the DGA can output a first dose guidance and a second dose guidance associated with a factor. The second dose guidance may be output to UID200. The second dose guidance can be calculated by multiplying the first dose guidance by the factor determined in step 636, which may be a fraction. According to some embodiments, for example, the value obtained by subtracting the fraction from 1 may take into account endogenous insulin production up to the time of injection. In one embodiment, this fraction may be based on a simulation of the type 2 metabolic response to food. Although this may not be known on a case-by-case basis, by adding this value to the fraction of the delayed dose, it is possible to supply a dose that takes endogenous production into account and a modified dose that keeps the user's postprandial blood glucose level within a safe range.

[0257] Dosage guidance for added meals (e.g., dessert) In some situations, patients may administer a mealtime insulin dose to cover a planned meal, but later consume additional food in the form of a "second helping" or dessert. A common strategy is to administer a new dose again, regardless of glucose levels and trends, and this is indeed a common practice. However, there may be situations where this is not the correct course of action. For example, a new dose may be too high and lead to a hypoglycemic episode because the patient did not originally consume enough to cover the initial dose. Conversely, a hyperglycemic episode may occur if the patient takes a conservative approach and does not administer extra insulin to cover the extra meal. In one embodiment, DGA can provide dosage guidance for added meals by (1) ensuring that the user continues to extend the original meal with more food, (2) informing the user of the risk of hypoglycemia before administering an extra dose, and (3) monitoring such risks after the meal.

[0258] The DGA can be configured to output an initial query to the user with UID200 to confirm that the meal has been extended with extra food. If the user wishes to receive dose guidance, it is assumed that they will first open the dose guidance app. In an exemplary embodiment, in exemplary method 660, beginning at step 662, as shown in the flowchart in Figure 13, the DGA can be configured to determine whether the user's query regarding dose guidance was made within the period of a first episode, the first episode including a meal with a start time. The start of the period can be the start time of the meal determined by a real-time meal detection algorithm, and the length of the period can also be determined by the real-time meal detection algorithm. The start time of the meal can be determined in several ways, including, but not limited to, the last time the meal was detected (e.g., by a real-time meal detection algorithm), or the last time dose guidance and / or insulin administration was provided in combination with meal detection.

[0259] As seen in step 664, if the user queries the DGA for dose guidance within the specified period, the DGA may request input from the user to confirm whether the meal was extended with additional food. The DGA may output a prompt or other indication to UID200 requesting user feedback. In one embodiment, the DGA may also request input from the user to confirm whether the purpose of the dose guidance was to correct high glucose. In another embodiment, the DGA may prompt the user for an explanation regarding the recent dose guidance request and optionally provide selectable options as a response. Options include, for example, the option that the additional request was made in response to an extended meal, and the option that the additional request was made to correct high glucose unrelated to additional food intake.

[0260] As seen in step 666, the DGA can determine the risk of hypoglycemia from the time of meal initiation. In one embodiment, to avoid hypoglycemic episodes due to insulin dose stacking, the DGA may be configured to determine the risk of hypoglycemia by determining the point in the user's current glucose excursion before extending the meal with additional food. The DGA may further be configured to create a forward prediction of glucose levels from the determined point in the current excursion to determine whether the user's glucose levels are still rising or falling. As a safety measure to avoid insulin stacking, the DGA may be configured not to provide dose guidance until glucose levels reach a postprandial maximum. For example, if dose guidance for an added meal is requested while the user's glucose is still rising, the DGA may output a notice stating that guidance cannot be provided at that time for safety reasons. In one embodiment, if a risk of hypoglycemia is determined, in step 668, the DGA may be configured to notify the user not to administer any dose or to exercise extreme caution with medication. In another embodiment, if there is no risk of hypoglycemia, in step 670, the DGA may be configured to notify the user to administer medication according to the HCP recommendation for the extra food. Furthermore, in one embodiment, if the DGA detects that an extra dose has been delivered, the DGA may be configured to advise the user to check their glucose levels at least about two hours later to confirm that there is no hypoglycemia.

[0261] Dose guidance method for corrective doses (dosage administration) Under certain circumstances, external factors may affect the effectiveness of insulin administration, and the dose may result in a greater glucose-lowering effect than expected. In these cases, users may conservatively estimate their insulin dose to avoid hypoglycemia. Alternatively, if it is unclear how much insulin is sufficient for a particular type or amount of meal, conservative administration may be possible on an individual basis. For example, a certain type of meal may be higher in fat and / or protein compared to the meals a user typically consumes. To enable conservative administration, the DGA can be configured to provide post-meal dose guidance to the user, accompanied by initial meal insulin administration. In one embodiment, the DGA can be configured to perform at least four functions following initial meal dose guidance and administration. The DGA can be configured to confirm that the user has administered a smaller dose than indicated in the initial meal dose guidance. The DGA can then be configured to determine the risk of hypoglycemia before additional medication is suggested and to notify the user of that risk. The DGA can further be configured to provide additional dose guidance and to monitor subsequent hypoglycemia risk during the period following the introduction of additional dose guidance.

[0262] In an exemplary embodiment, the user inquires with the DGA about the recommended dosage at the start of or just before the start of a meal. In an exemplary method 700 beginning with step 702, as shown in Figure 14, the DGA may output first dose guidance in response to the first user inquiry. The first dose guidance may be output to UID 200. In one embodiment, the first dose guidance may be calculated to be administered at the start of a meal. The first dose guidance may also be a fixed dose (with or without correction) meal guidance. The first dose guidance may also be determined based on the carbohydrate content of the meal.

[0263] However, the user can choose whether or not to follow the recommended dose guidance when administering insulin. If the administered dose differs from the recommended dose, the system records the difference. As step 704, the DGA can determine whether the first administered dose differs from the first dose guidance. The first administered dose may be lower or higher than the first dose guidance. In one embodiment, the first administered dose is lower than the first dose guidance. The DGA can be configured to record if the administered dose is lower than the recommended dose guidance.

[0264] In step 708, DGA can determine whether a second user inquiry regarding second dose guidance was received within the period of administration of the first dose. This period may be determined by a real-time meal detection algorithm from the administration of the first dose, or it may be a predetermined time.

[0265] In step 710, the DGA may request input from the user and, if it determines that a second user inquiry has been received within the period, determine whether the second user inquiry is to adjust for high glucose levels after meal completion. The DGA may output a prompt or other notification to UID200 requesting user feedback. For example, if the DGA subsequently receives an inquiry for a further dose recommendation following a conservative dose (e.g., less than the recommended dose) within a certain time period from the initial meal dose, the DGA may use both the inquiry time and the record of the dose mismatch to prompt the user for the reason for the second dose guidance. In one embodiment, the DGA may be configured to request input to determine whether the later requested dose is to cover additional mealtime food or to account for postprandial high glucose. If the user requests second dose guidance to cover additional mealtime food, the DGA may follow the flow described in the “Additional Meal Dose Guidance” section elsewhere in this specification.

[0266] As seen in step 712, if the user requests a second dose guidance to correct postprandial hyperglucose, the DGA can determine the risk of hypoglycemia by determining at least whether the user's blood glucose is rising. In one embodiment, to avoid hypoglycemic episodes due to insulin dose stacking, the DGA may be configured to determine the risk of hypoglycemia by determining the point in the user's current blood glucose excursion. The DGA may further be configured to create a forward forecast of glucose levels from the determined point in the current excursion to determine whether the user's glucose levels are still rising or falling. In one embodiment, as a safety measure to avoid insulin stacking, the DGA may be configured not to provide dose guidance until the glucose level reaches a postprandial maximum. If a dose recommendation for correction is requested while the user's glucose is still rising, the DGA may be configured to provide a notification that guidance cannot be provided at that time for safety reasons. In one embodiment, the DGA may be configured to provide additional reasons for not providing dose guidance. For example, the DGA may be configured to provide, where available, the most up-to-date estimate of insulin onboard, determined from a combination of population-based aggregate parameters and user-specific parameters.

[0267] In one embodiment, if the DGA determines that the user's blood glucose is low, the DGA may be configured to calculate the risk of future hypoglycemia in the absence of a corrected "touch-up" dose. In another embodiment, the DGA may be configured to calculate the risk of hypoglycemia by calculating a forward predictive value of the current glucose level to examine the likelihood of a hypoglycemic episode. In yet another embodiment, the DGA may be configured to analyze past events to observe how often a given dose induces postprandial hypoglycemia for a given pre-meal glucose range. In one embodiment, if the DGA determines that the current hypoglycemia risk exceeds a predefined threshold, in step 716, the DGA may be configured to output a recommendation to UID200 that no further insulin should be taken at this time.

[0268] If the DGA determines that the user has no current risk of hypoglycemia, in step 714, the DGA can be configured to calculate and output dose guidance as if the subsequent dose were postprandially corrected. Thus, in one embodiment, since the meal has already been completed, the subsequent dose can be determined without considering the intake of new carbohydrates. As described with respect to equation (2), the DGA can be configured to calculate a second dose (corrected dose guidance) as a function of subtracting the residual insulin onboard (IOB) of the initial meal dose from the glucose correction portion. That is,

[0269]

number

[0270] And in the formula, TIFF0007869626000009.tif18114

[0271] This is the glucose correction portion. In one embodiment, the glucose correction portion of the corrected dose guidance is calculated as current glucose (BG(t)) and target glucose (BG targetThe algorithm can be configured to calculate the difference between the given value and the current value divided by a correction factor. The correction factor can be the user's insulin sensitivity index (ISF), which is an index used as a measure of how much one unit of insulin lowers fasting blood glucose levels. The ISF can be personalized for each user during the algorithm learning period. In one embodiment, the IOB can be estimated using population-based statistics on insulin pharmacokinetics (PK) for initial estimation. Rapid-acting insulin analogs generally have a profile that reaches peak plasma concentration in about 45 minutes and then decays exponentially, but this time may be shorter if the user is taking an ultra-rapid-acting insulin analog. This time window may correspond to a dormant period during which the rise in glucose levels prevents DGA from providing guidance. The IOB can be estimated from this profile by directly measuring the exponential decay or by estimating the linear decay from peak insulin concentration to pre-meal value. The IOB value can explain the current decline in glucose levels since the initial insulin dose and can be subtracted from the glucose-corrected dose to minimize insulin stacking. If an extra dose is delivered, the application's user interface will advise the user to scan their glucose levels two hours later to ensure there is no hypoglycemia.

[0272] Postprandial hypoglycemia and hyperglycemia alarm methods in postprandial insulin therapy DGA can be configured to proactively notify the user of anticipated or potential future hypoglycemic and / or hyperglycemic episodes by generating and / or outputting alarms, or by other means. These alarms allow the user to take action to maintain blood glucose levels within the normal blood glucose range, which is a primary goal of diabetes management.

[0273] In contrast to threshold-based alarm methods, DGA's predictive alarm method can be based on the predicted probability of hypoglycemic / hyperglycemic episodes, their predicted timing, and predicted severity. Several advantages are associated with predictive alarm methods. Predictive alarm methods overcome one of the most common problems with threshold-based alarms: how to set the optimal threshold. Setting the threshold too low can lead to many false alarms, while setting it too high may result in patients not receiving the alarm in time. Furthermore, predictive alarm methods can provide patients with more specific information about upcoming blood glucose episodes, including their probability, timing, and severity. The additional specificity provided by the alarm allows patients to take more appropriate action. Additionally, predictive alarm methods can provide patients with personalized choices of appropriate actions.

[0274] In one exemplary embodiment, as shown in the flowchart of Figure 15, in an exemplary method 720 beginning from step 722, the DGA may be configured to receive multiple data, including analyte (e.g., glucose) time-series data and event data. The DGA may be configured to learn specific patterns from the historical data of individual patients. The multiple data received by the DGA may include glucose time-series data and timestamps associated with other event markers. In one embodiment, higher-order derivatives and integrals of the glucose time-series data are also inputs relevant to the alarm system. Furthermore, the multiple data may include, but are not limited to, patient location data, calendar day data, TOD data, and stress level data. Event data may include, but are not limited to, meal data, snack data, exercise data, and medication data, and other timestamps associated with each event. Medication data may include bolus insulin dosage and amount and / or basal insulin dosage and amount.

[0275] In step 724, the DGA can be configured to process at least a portion of multiple data to determine the probability, predicted timing, and predicted severity of future hypoglycemic or hyperglycemic episodes. In one embodiment, historical records of each event type can be profiled to generate predictions of which are most likely to occur in the near future. Predictions of future blood glucose episodes can be made by referencing their association with TOD, time of week, or other events. For example, the DGA can be configured to predict associations with exercise events that occur before or after a specific meal on a particular day of the week.

[0276] DGA can be configured to predict future hypoglycemic or hyperglycemic episodes using a glucose level prediction algorithm. In one embodiment, this algorithm can be implemented using a simple Bayesian classifier. In another embodiment, this algorithm can use a recurrent neural network (RNN) long short-term memory (LSTM) architecture, a random forest, or a combination of various methods. In one embodiment, a population-based model can be developed by first training a machine learning model with glucose time-series data collected from clinical studies and real-world databases. In one embodiment, the population-based model can be the initial model for each patient at the start, and the model can be trained to train subject-specific patterns by continuously training the algorithm with data from patients. Thus, the performance of DGA can be improved subject-by subject as subjects use DGA.

[0277] In step 726, the DGA may be configured to alert the patient to anticipated future hypoglycemic or hyperglycemic episodes. In one embodiment, the DGA may be configured to notify the patient by outputting an alarm to UID200, allowing the patient to act on the alert, for example, by taking carbohydrates to treat a future hypoglycemic state or by taking insulin to treat a future hyperglycemic state. In another embodiment, the DGA may be configured to be coupled with a medication algorithm to suggest an appropriate amount of treatment for the alarm system. In one embodiment, if a future hyperglycemic episode is anticipated, the DGA may be configured to output an alarm to UID200 that includes recommended dose guidance. In another embodiment, the DGA may be configured to provide a user-accessible display to UID200 when determining whether postprandial insulin administration is recommended. For example, if it is calculated that there is a high probability of future hypoglycemia, the DGA may be configured to output dose guidance indicating that additional insulin is not recommended. The DGA may also be configured to output recommendations to UID200 that are not related to dose guidance. For example, DGA can be configured to output messages recommending carbohydrate consumption, recheck glucose levels after a short period (e.g., 15 minutes), set reminders to check glucose after a pre-set time or a user-defined time, and / or enable hypoglycemia threshold alarms. In addition to outputting alarms, DGA can also be configured to include a detailed display of the state of future hypoglycemia / hyperglycemia episodes.

[0278] In one embodiment, the prediction of a particular episode can be modified by the probability of its occurrence. Different levels of probability may result in different system outputs. For example, triggering an alarm may require a higher probability than displaying post-meal dose guidance requested by the patient.

[0279] In another embodiment, the DGA can be configured so that the sensitivity or specificity of the prediction method is adjustable. In one embodiment, different levels of sensitivity and / or specificity allow the user or DGA to select a level of sensitivity and / or specificity that is appropriate to the user's level of involvement at that time. For example, when the user needs to focus on other aspects of life, the user can select a higher specificity so that they are only alerted for high-urgency situations. In another embodiment, a higher sensitivity can be selected. For example, when the user decides to allocate more time to improve glucose management, they can proactively select a prediction system with higher sensitivity to prevent urgent situations. In one embodiment, the sensitivity and specificity settings, as well as the learning module itself, may initially be based on collective data. As more user selections are recorded, pattern recognition can attempt to correlate days of the week (e.g., individual days of the 7-day period, or weekdays vs. weekends), time of day, and potentially the density of activity logs in the user's calendar to evaluate the most likely preference for sensitivity and specificity settings at any given time.

[0280] System Features DGS100 can incorporate systemic considerations to address common events that occur during the management of diabetes with high insulin levels. Current insulin bolus dose calculators do not take these real-world events into account, leaving users to modify recommended doses based on their best judgment. While it is desirable for diabetic patients to be able to adjust ideal dose recommendations to match real-world events, such considerations can be a significant cognitive burden for them. To alleviate this burden and create a more user-friendly medication system, DGS100 leverages insulin and glucose data to adjust doses appropriately to real-world situations. Furthermore, the features of these systems are enhanced by the physician's ability to modify medication parameters.

[0281] Overriding dose guidance settings by HCP DGA can provide dose guidance based on individualized parameters such as fixed dosage, target glucose, correction factors, and insulin action duration. Users can view these various parameters in various ways. For example, users can view the parameters on UID200 via the settings tab within DGA, or they can be displayed as a viewable breakdown of the recommended dose value. Users can view these parameters as part of the recommended dose, but these values ​​are strictly for informational purposes and may not be editable by the user.

[0282] In contrast, DGA can be configured so that a user's HCP can view these values, for example, as part of a clinician-facing system web application, and can also be configured so that the HCP can edit one or more of these parameters. This web application can display patient performance indicators through a set of patient glucose values, including not only glucose concentration profiles but also insulin dosage statistics. If the HCP wishes to modify dose recommendations to accommodate changes in other treatment regimens, the clinician-facing web application can be configured to allow the HCP to edit user-specific dosing parameters, including but not limited to those described above.

[0283] In an exemplary embodiment, as shown in the flowchart of Figure 16A, in exemplary method 800, in step 801, the HCP may create new insulin dose guidance by adjusting at least one parameter used to provide insulin dose guidance for a subject in a dose guidance application. For example, the HCP may adjust at least one of the fixed dose, target glucose, correction factor, and insulin action duration. Before adjusting at least one parameter to create new insulin dose guidance, the HCP may display glucose concentration profiles and insulin statistics to determine whether the subject is experiencing a low-glucose or high-glucose pattern at any time of day and notify if the insulin dose guidance needs to be adjusted. High or low-glucose patterns can be determined by GPA, as described elsewhere herein.

[0284] After the HCP has changed at least one parameter, in step 802, the subject may be notified about the new insulin dose guidance. Furthermore, an explanation of why the dose guidance was changed may also be provided to the subject. In one embodiment, either or both the user and / or the HCP may approve any changes to the dose guidance before the changes become effective. The parameters and dose guidance may be fixed for a certain period (e.g., 14 days to coincide with the sensor's lifespan), but any unchanged parameters may be further modified as part of the algorithm's continuous learning.

[0285] In step 804, the DGA may determine whether the subject experiences any episodes of hypoglycemia during the time period after at least one parameter has been adjusted, for example, within 14 days. If any instance of hypoglycemia is observed during this time period, the HCP may be immediately notified to determine whether the parameter should be returned to its pre-override or pre-adjustment value. At the end of this time period, the HCP may be asked to examine the subject's performance during the time period in detail, e.g., the subject's glucose concentration profile and insulin statistics, to determine whether the adjustment of the medication parameter should be maintained. If the HCP decides to maintain the adjustment of the medication parameter, these values ​​can be used as initial conditions for adjusting future doses. All historical data related to these values ​​are either disregarded or given very little consideration in future dose recommendations.

[0286] If the HCP only notifies the user verbally of changes in medication dosage without updating the DGA, for example, via a web application, a discrepancy may arise between the outputted dosage guidance and the dose administered. If such a discrepancy is consistently observed over a long period (e.g., 3 days), the DGA can notify both the user and the HCP and inquire whether there has been any change in medication dosage. If both the user and the HCP confirm, the algorithm can employ the strategy described above. Furthermore, the system can prompt the user to input the reason for such persistent changes.

[0287] Additionally, DGA can include a "10%" reduction button. If selected by HCP in relation to a specific dose recommendation, the dose recommendation will automatically decrease by 10% (e.g., 1 U). For example, HCP may want to reduce a patient's insulin dose as a result of a change in the dosage of a non-insulin medication. This change in dosage may be known to make the patient more sensitive to insulin. Therefore, the patient's current insulin therapy may have too strong a glucose-lowering effect and cause hypoglycemia. As a precautionary measure, HCP can reduce the insulin dose. In this example, DGA can then titrate based on the adjusted value.

[0288] Onboard glucose sensor failure detection from insulin and glucose data The glucose sensor 101 may have built-in fault detection to notify the user to remove and replace the current sensor, but the DGS100 can also be configured to provide fault detection via the total insulin amount.

[0289] In one exemplary embodiment, the relevant insulin dose data can be received from the MDD152 in an exemplary method 807, starting from step 808, as shown in the flowchart in Figure 16B.

[0290] In step 810, DGA can determine whether multiple recommended insulin dosages differ from multiple previous insulin doses administered over a period of time. Each of the multiple insulin dose guidances and each of the multiple previous insulin doses administered are associated with a TOD period, and each of the multiple insulin dose guidances can be compared to one of the multiple previous insulin doses administered and associated with the same TOD period to determine the difference. A difference is detected if the dose guidance differs from the corresponding prior dose administered over the same time period. If sensor 102 is reading a higher glucose level compared to past sensors, the recommended dose can be increased accordingly to compensate for the increased high glucose. Conversely, if sensor 102 has a much lower value compared to past sensors, the recommended dose can be immediately decreased to prevent hypoglycemia.

[0291] In step 811, the DGA can determine whether a new sensor was connected to the SCD 102 at a time close to the start of the period in which the difference was detected. If it is determined that a new sensor was recently connected to the SCD, in step 812, the DGA can recommend replacing the sensor with a new one. There are several reasons why the glucose readings of the sensor may be high or low, but if the onset of these abnormal glucose levels and dose guidance coincides with the placement of a new sensor and persists while the sensor 102 is fitted, a faulty sensor may be the root cause of such deviations. In this case, the DGA may notify the user to replace the glucose sensor 102.

[0292] Changes in medication strategy in response to combination therapy or a new type of insulin Intensive diabetes management for patients with type 2 diabetes is often highly complex. Diabetic patients frequently take a variety of medications in addition to insulin, which act complementaryly or synergistically to improve glucose homeostasis as insulin sensitivity gradually declines. Changes in adjunctive therapy, such as therapies using secretagogues or incretins, can affect both endogenous insulin production and tissue insulin sensitivity. Consequently, changes in adjunctive therapy can affect the subsequent effectiveness of exogenous insulin and should be considered as part of insulin dose guidance. Similar situations can arise when a user switches to a different insulin (e.g., from rapid-acting to ultra-rapid-acting, or from once-daily basal to twice-daily basal).

[0293] Changes in medication strategy can occur if the HCP changes the patient's adjunctive therapy or insulin type. In this case, as mentioned above, the HCP can provide adjustments to insulin dosage parameters to minimize hypoglycemic episodes. However, in some cases, the DGA may not be informed of changes in adjunctive therapy or medication recommendations. In this case, the system can monitor trends in differences related to insulin dose over a period of time.

[0294] In one exemplary embodiment, the relevant insulin dose data can be received from the MDD152 in an exemplary method 813, starting from step 814, as shown in the flowchart in Figure 16C.

[0295] In step 816, the DGA can detect a trend in differences related to multiple insulin doses administered in a first time period over a certain time period. The trend in differences may include, but are not limited to, the difference between the proposed dose and the administered dose, as well as the difference in the effectiveness of that dose compared to a previous dose at a given dose value (in either the magnitude of the response or the lifetime). If a trend in differences is observed over a certain period, in step 818, the DGA can provide a notification regarding the trend in differences to the user, the HCP, or both. This period may be approximately 2 days, 3 days, or 4 days. In one embodiment, the DGA may also output a prompt on UID200 to the HCP and / or user asking for confirmation of a change in treatment in order to explain the trend in differences.

[0296] As a trend in differences, if the administered dose consistently differs from the DGA recommended dose, the HCP may have overridden the user's medication parameters, as described in the section "HCP Overrides Dose Guidance Settings" above. As a trend in differences, if the recommended dose shows a significant and consistent difference in postprandial glucose control compared to past administrations, insulin effectiveness may have changed. This change in insulin effectiveness may be either magnitude (indicating a change in adjunctive therapy) or duration (indicating a change in insulin analog).

[0297] If an adjunct medication is changed, and the user and HCP confirm the change, the DGA can switch to a conservative mode, setting the dose suggestion to a fraction of the previous dose guidance. The DGA can then titrate the medication parameters and dosage to optimize these new conditions. If the insulin type is changed (e.g., from rapid-acting to ultra-rapid-acting), the magnitude of the response should remain unchanged, as the market difference between the two lies in the rapid onset / offset of the drug. Rather, the duration of the response may change. To address this, population-based values ​​for the new insulin type can be used to estimate the duration of insulin action until the system can determine a new, individualized value for it.

[0298] If a user takes a dose different from the recommended dosage guidance While DGA can recommend doses to users, DGS100 does not guarantee that users will strictly adhere to the dose guidance. DGA can record the difference between the administered dose and the recommended dose and detect trends in that difference. Observed persistent trends are described in the sections above, "Overriding Dose Guidance Settings by HCP" and "Changes in Medication Strategy in Response to Adjuvant Therapy or New Insulin Type."

[0299] In an exemplary embodiment, as shown in the flowchart of Figure 16D, in an exemplary method 820 beginning with step 822, the DGA can detect a difference related to the insulin dose administered to the subject during the first time period compared to the dose guidance provided during the first time period. The DGA can compare the dose guidance with insulin dose data received from MDD152 to determine whether a dose other than the dose indicated in the dose guidance was administered to the user. The administered dose may differ from the provided dose guidance in either the amount of insulin ingested or the type of insulin ingested.

[0300] A specific example of taking a dose different from the dosage guidance is when a user takes the wrong amount of insulin (for example, injecting a long-acting insulin instead of a rapid-acting one, or vice versa). The DGA can calculate the optimal dose for a given insulin analog type for any dosing scenario, i.e., use a rapid-acting insulin for mealtime and corrective doses, and a long-acting insulin for basal administration. To avoid any errors, the DGA can output both the type and amount of insulin during the dose guidance on the UID200. The MDD152 can record and transmit both the amount and type of insulin administered. The DGA can collect information on which insulin type was used for the injection and detect any discrepancies. If a discrepancy is detected, the user can be notified on the UID200. This notification may be to indicate that the DGA has detected that a different insulin type was used and to ask the user for confirmation.

[0301] If a user administers the wrong type of insulin, an insulin mismatch notification can be output to UID200 to alert the user as soon as possible, even before a hypoglycemia alarm is triggered, in order to warn the user of the possibility of a severe hypoglycemic episode. For example, if a rapid-acting dose is taken instead of a long-acting dose, severe hypoglycemia may be imminent. There are three reasons for this: (1) Rapid-acting insulin, as the name suggests, has a more pronounced effect immediately after administration than long-acting insulin; (2) A once-daily long-acting dose can be a much larger amount than a single rapid-acting dose taken with a meal; and (3) Depending on the timing of the last meal dose, an incorrect rapid-acting bolus can cause insulin stacking. When a long-acting dose is taken instead of a rapid-acting meal dose, the outcome can be more unpredictable. Because long-acting insulin has a slower pharmacokinetic and pharmacodynamic profile compared to rapid-acting insulin, postprandial blood glucose levels after the incorrect administration of long-acting insulin can cause hyperglycemia in the patient immediately after injection. Depending on the timing of the previous long-acting dose, there is a possibility of insulin stacking and subsequent hypoglycemia, especially since the current dose reaches its peak plasma concentration approximately 6 hours after injection. Users can be aware of the possibility of severe hypoglycemia within the UID200 notification. In either situation, DGA may refrain from making any recommendations regarding insulin dosage until the onboard insulin value for injection approaches zero (e.g., approximately 5-6 hours for rapid-acting insulin, or 12-24 hours for long-acting insulin). Glucose data during these periods may also be flagged by the system so as not to be used for further parameter refinement and dose titration.

[0302] In step 824, DGA can detect hypoglycemic episodes associated with the insulin dose administered during the first time period. For example, DGA can determine a hypoglycemic episode when the glucose level drops below 70 mg / dL.

[0303] In step 826, the DGA may notify the patient and / or HCP that any hypoglycemic episode related to the insulin dose administered during the first time period has been detected. This notification may be output to UID200. If the DGA observes that the user has experienced hypoglycemia due to sustained intake of a higher dose than the recommended dose, it may output a predictive hypoglycemia alert to UID200 to notify the user in advance of the actual hypoglycemic event itself, allowing for immediate mitigation of the associated side effects. However, if hypoglycemia occurs due to sustained administration exceeding the recommended value (e.g., defined as three separate episodes or four separate episodes), notifications can be sent to both the user via the system phone application and the HCP via the clinician web application, alerting both of these trends.

[0304] Differences that do not appear to be part of a broader trend can be noted by DGA, and given doses can be incorporated into a continuous learning system of individual medication patterns. Postprandial indicators can be noted as well as any administered doses. Whenever a different dose is associated with postprandial hypoglycemia (e.g., less than 70 mg / dL) or other negative outcomes, that dose can be flagged so that both the user and HCP can improve their medication approach, respectively. This flag can be displayed to the HCP as a note in the glucose pattern report and to the user as a note in the DGA insulin logbook.

[0305] The mechanism of a system that administers multiple medications in succession. To ensure accurate dosage records, DGAs must be able to correctly interpret situations where multiple insulin injections are administered in quick succession. Examples of such situations include priming (potentially multiple times) before actual medication administration and multiple injections for a given recommended dosage.

[0306] In one exemplary embodiment, the relevant insulin dose data can be received from the MDD152 in an exemplary method 827, beginning with step 828, as shown in the flowchart in Figure 16E.

[0307] In step 830, the DGA can detect the administration of multiple insulin doses. Multiple insulin doses include at least the first and last doses, with the last dose administered within the time period of the first dose. If multiple doses are administered within a short time period, at least one of the doses administered may be a priming dose. Procedural best practice in insulin delivery is to use a new needle for each injection and to prime each new needle with insulin before dose administration. This is done by dispensing a small amount of insulin (typically 2U) into the air until insulin is visible at the tip of the needle, indicating that the needle is full of the injectable. To distinguish priming doses, the DGA can assume that (1) the priming dose is generally much smaller than the actual dose, (2) the priming dose is the same amount each time, and (3) little time has passed between priming and administration. Alternatively, if multiple doses are administered within a short time period, it may actually be a divided dose because there is a large amount to inject. For example, user MDD152 may have less insulin remaining than the requested dosage, requiring a cartridge replacement and subsequent extra injections.

[0308] In step 832, the DGA may record the last dose as the dose administered if the first criterion is met. The first criterion may be met if the last dose was administered within approximately 1 minute, 2 minutes, or 3 minutes of the first dose. In such a situation, the DGA may consider the first dose and any subsequent intermediate doses (except the last dose) to be priming doses and therefore not to be considered actual doses administered. Thus, the DGA may be configured to record only the last dose as the dose administered. Since priming doses typically contain small amounts of insulin, in another embodiment, the first condition may be met if the first dose is substantially smaller than the last dose. For example, the first condition may be met if the first dose is approximately one-tenth, one-fifth, one-quarter, or one-third of the last dose.

[0309] Alternatively, in step 833, if the second criterion is met, the DGA may record the sum of the first and last doses as the amount of dose administered. The second criterion may be met if a single dose is delivered via multiple smaller injections made over a longer time period (e.g., approximately 4 to 35 minutes, or approximately 5 to 30 minutes) than the time period for priming (e.g., 1 to 3 minutes). For example, user MDD152 may have less insulin remaining than the requested dosage, thus requiring a cartridge change and subsequent extra injections. In this case, the DGA may interpret these injections not as separate episodes, but as two actions within the same medication episode. To this end, the DGA may employ a waiting period in recording the medication, and may only record the insulin dose value approximately 30 minutes after the first dose is administered. For example, if the DGA recommends a 10U dose with a meal, but only 4U remains in the insulin cartridge, the injection will be divided into two parts: the first 4U and the remaining 6U. If a new needle is used for the second injection, an intermediate priming dose may also occur. Once the first 4U is given, the DGS100 will look for the remaining 6U. If the 6U dose arrives within 30 minutes of the first dose, the DGA can consider this as one 10U dose. If one or more prime doses are detected between actual doses, the DGA can consider all doses between the first and last doses as primes and, consequently, not be included in the final dosage. Because the DGA communicates with the MDD152, it can be configured to import the remaining amount of insulin in the insulin cartridge along with insulin dose information. Knowing the amount of insulin remaining in the cartridge, the DGA can predict the split dose due to cartridge switching and can even be configured to notify the user about the remaining amount of insulin.

[0310] In another embodiment, the DGA may be configured to consider the priming dose and subsequent dose as divided doses, and to add the two doses together to obtain a single mealtime value that includes the prime dose. If the prime dose is much smaller than the meal dose, the prime dose may have little effect on the titration of the algorithm's dose guidance. This is similar to the divided dose logic described below. Although not precise, the assumption that the priming amount is much smaller than the injected amount may be reasonable for patients with type 2 diabetes suffering from increased insulin resistance.

[0311] Titration using glucose data in cases of medication forgetting To provide optimal medication advice for progressive diseases, DGA can continuously improve estimates of the user's specific medication parameters. Therefore, it is necessary to identify the appropriate data streams that form the basis of this algorithm's learning. To avoid confusion of results, DGA can be configured to learn only based on insulin and glucose data aligned with the user's own clinically recommended medication strategy. Such strategies include, but are not limited to, basal-only, basal and one mealtime rapid-acting insulin dose, basal and two mealtime rapid-acting insulin doses, and full-time frequent injection strategies including basal and three mealtime rapid-acting insulin doses.

[0312] In one exemplary embodiment, the relevant insulin dose data can be received from the MDD152 in an exemplary method 833, starting from step 834, as shown in the flowchart in Figure 16F.

[0313] In step 836, the DGA can detect insulin dose forgetting, where insulin doses have a time period related to the duration of action. For example, the DGA can initially identify the user's medication strategy during the initial learning period before dose guidance can be provided. Also, using an automated meal detection method and data from the Bluetooth-connected MDD152, the system can identify meal events and their associated doses. Thus, the DGA can determine whether medication was forgotten for a given meal. If there is no data reported from the user's long-acting MDD152, basal medication forgetting can be detected.

[0314] In step 838, DGA may disregard glucose analyte data related to the time period when determining adjustments to insulin dose guidance. A single missed dose at mealtime may cause an increase in blood glucose and insulin bolus compared to past occurrences. Not only these changes in mealtime doses, but also glucose levels after the missed meal may distort the current dose titration determined by DGA for a given medication strategy. Similarly, a missed basal dose may cause a sustained increase in glucose over the duration of insulin action, which is generally assumed to be 1 day. As a result, the DGA algorithm will only include glucose and insulin data obtained from meals accompanied by insulin doses. For rapid-acting insulin, the duration of action can be approximately 4 hours, 5 hours, 6 hours, or 4 to 6 hours. For example, if breakfast medication is missed, glucose data for the 4 hours after breakfast may not be included in the dose titration. For long-acting insulin, the duration of action can be approximately 18 hours, 20 hours, 24 hours, or 20 to 24 hours. Because long-acting insulin is useful for both maintaining normal blood glucose levels between meals and preventing diabetic ketoacidosis, system algorithms may not include data within the duration of action in cases where a basal dose is missed. For example, insulin glargine has a reported duration of action of 24 hours. If a user taking glargine misses a basal dose for the day, all data from the following 24 hours will not be used by the system for dose titration.

[0315] Encourage users to avoid forgetting to administer their medication. Adherence to a properly titrated insulin dosage regimen improves diabetes management by reducing not only hyperglycemia associated with medication forgetting, but also hypoglycemia caused by overcompensatory corrective medication. DGA can be configured to provide users with actionable and easily interpretable data that highlights the positive impact of medication adherence. One such method is to provide periodic updates comparing glucose control metrics or other relevant statistics during periods of medication forgetting versus periods without medication forgetting.

[0316] In one exemplary embodiment, the relevant insulin dose data can be received from the MDD152 in an exemplary method 840, starting from step 841, as shown in the flowchart in Figure 16G.

[0317] In step 842, DGA can detect insulin dose forgetting. In step 846, DGA can determine the amount of time the target glucose level remained within the target range (TIR) ​​during the first and second time periods. The target range can be set by DGA, the user, or HCP. The target range can be approximately 70 mg / dL to 180 mg / dL, or approximately 70 mg / dL to 190 mg / dL, or approximately 70 mg / dL to 200 mg / dL. The first and second time periods can be the same length, with the first time period not including insulin dose forgetting and the second time period including insulin dose forgetting. In this way, a comparison of the TIR between periods including and excluding medication forgetting can be prepared.

[0318] In step 848, DGA can notify the user of the determined TIRs for the first and second time periods. If the difference between the two determined TIRs is greater than a threshold (i.e., the difference between the TIR of the first period and the TIR of the second period), a positive message can be displayed to the user on UID200 to encourage good medication behavior and educate the user about the benefits of medication adherence. For example, the user can be notified that the glucose control index increases by 10% on days when all doses are taken compared to days when meal medication is missed.

[0319] safety features The exemplary embodiments of the safety features of the DGS100 described herein prioritize user safety in the guidance and titration process. Current insulin bolus dose calculators calculate dose suggestions using static medication parameters. When the user or HCP updates these values, it becomes a trial-and-error process that may, in some cases, lead to hypoglycemia. As an automated process, the DGA can utilize the user's insulin and glucose data to titrate these parameters and provide user-adjustable dose guidance. Safety measures can be incorporated to ensure that the recommended titration does not cause hypoglycemia after medication.

[0320] Safe titration methods The titration logic of DGA can be set to not increase dose titration until the hypoglycemic period subsides. When an HCP manually performs titration, the HCP may want to increase some doses and decrease others to achieve complete titration as quickly as possible to avoid wasting time. However, automated systems do not titrate as aggressively and do not require the HCP's time, so they take longer (and are more conservative and safer). Therefore, patients with hypoglycemia may experience high average glucose values ​​at the beginning of titration, but once the hypoglycemia subsides, insulin doses may be safely increased to achieve the glycemic target.

[0321] One problem when detecting high glucose patterns after meals is that the previous meal may have postprandial glucose, resulting in the next meal starting with high glucose. If this occurs, the high starting glucose may erroneously indicate a high pattern in the next meal. To address this problem, DGA's titration strategy may include a step of first titrating the nighttime dose before titrating the meal dose, if necessary. Furthermore, meal doses can be titrated in the order of first titrating the earliest meal with a high glucose pattern, and then sequentially titrating later meals that also have a high glucose pattern. For example, recommendations for titrating insulin doses related to nighttime periods may be made first. Then, for any high glucose pattern detected during any postprandial time period, recommendations for titrating insulin doses related to breakfast may be provided before recommendations for doses related to lunch, and recommendations for doses related to lunch may be provided before recommendations for doses related to dinner. By titrating the previous meal first, pre-meal high glucose for the next meal is minimized, and the recommended titration is less likely to affect or interfere with the titration of the next meal.

[0322] In the embodiments described herein, the DGA can detect high / low patterns as described with respect to the GPA described elsewhere herein.

[0323] In the embodiments described herein, the DGA can be configured to recommend changes in insulin dosage (e.g., increases or decreases). The recommended change may be any desired amount of insulin, e.g., a fraction of a unit (0.1 or 0.5 units), or one unit (1.0 unit), or two or more units of insulin (2.0 or more), or any combination thereof. For ease of explanation, the embodiments described herein refer to adjustments at one-unit intervals.

[0324] DGA can perform the various steps described in the safe titration embodiment in a variety of different ways. For example, these steps can be performed before each meal, or at the beginning, end, or every day, or every other day, or every three days, or when the user queries DGA for dose recommendations, or in combination of these.

[0325] In an exemplary embodiment, the DGA can access measured glucose data (e.g., from SCD102). The DGA can determine whether there is a high glucose pattern during the nighttime period. If a high pattern is detected during the nighttime period, the DGA can modify the dose guidance. For example, the DGA can increase the amount of drug in the dose guidance for the basal dose if it is safe to do so, for example, without causing any low glucose patterns at any time of day. The DGA can then determine whether there is a high glucose pattern during at least one postprandial period of the day. If a high pattern is detected, the DGA can increase the amount of drug in the dose guidance associated with the earliest time period of at least one postprandial period of the day. The DGA can then be configured to increase the amount of drug in the dose guidance associated with the next earliest time period of at least one postprandial period of the day that was determined to have a high glucose pattern.

[0326] In another exemplary embodiment, as shown in the flowchart of Figure 17A, in step 852 of exemplary method 850, the DGA may output a first dose guidance that is less than the preceding dose for at least the first time period in response to the detection of a low glucose pattern in at least the first time period in the analyte data of interest. The first dose guidance may be output to UID200. If a low glucose pattern is detected, the DGA may output dose guidance related to the period in which the low glucose pattern was detected. The DGA may be configured not to recommend any reduction in insulin dose to address a high glucose pattern until the low glucose pattern is no longer detected.

[0327] In step 856, the DGA may, in response to detecting a high glucose pattern during the nighttime period in the analyte data, output a second dose guidance lower than the preceding dose for the nighttime period. For example, the DGA may recommend an increase in the basal dose if it is safe to do so, for example, if such an increase does not cause a low glucose pattern during another time period of the day.

[0328] In step 860, the DGA may output a third dose guidance that is less than the preceding dose for at least one postprandial period, in response to detecting a high glucose pattern in at least one postprandial period in the analyte data of interest. In one embodiment, the DGA may be configured to detect all high glucose patterns found in any time period of the day. In another embodiment, the DGA may be configured to detect whether the post-breakfast period has a high glucose pattern, then the DGA may be configured to detect whether the post-lunch period has a high glucose pattern, then the DGA may be configured to detect whether the post-dinner period has a high glucose pattern.

[0329] If high glucose patterns are detected between multiple post-meal intervals, the third dose guidance output by DGA can be associated with the post-meal interval with the earliest onset high glucose pattern during the day. For example, if high glucose patterns are detected both after breakfast and after lunch, DGA can increase the recommended insulin dose associated with breakfast before recommending an increase in the recommended insulin dose associated with lunch. Furthermore, DGA can reassess whether the high glucose pattern during the post-breakfast interval has subsided before recommending an increase in the recommended insulin dose associated with lunch.

[0330] In another exemplary embodiment, as shown in the flowchart of Figure 17B, in exemplary method 862 beginning in step 864, the DGA can detect a low glucose pattern at any time of day. The low pattern can be detected based on GPA as described elsewhere. If a low glucose pattern is detected, in step 866, the DGA can output a first dose guidance for the time of day in which the low glucose pattern was detected. The first dose guidance may include a smaller dose of drug compared to a prior dose administered during the time of day in which the low glucose pattern was detected. The DGA can be configured not to recommend any increase in insulin dose to address a high glucose pattern until a low glucose pattern is no longer detected at any time of day.

[0331] In step 868, the DGA can detect whether a high glucose pattern exists during the nighttime period. If a high glucose pattern is detected, in step 870, the DGA can output a second dose guidance for the basal dose. For example, the second dose guidance may include a higher dose than the prior basal dose if the DGA determines that such a modification is safe, for example, if such an increase does not cause a low glucose pattern during another time period of the day. In one embodiment, the second dose guidance may include a higher dose than the basal dose administered the previous day.

[0332] In step 872, the DGA can detect whether a high glucose pattern exists during the post-breakfast period. If a high glucose pattern is detected, in step 874, the DGA can output a third dose guidance. The third dose guidance may increase the recommended insulin dose associated with breakfast, i.e., the third dose guidance may include a higher dose than the previous post-breakfast dose. In one embodiment, the third dose guidance may include a higher dose than the post-breakfast dose administered the previous day.

[0333] In step 876, the DGA can detect whether a high glucose pattern exists during the post-lunch period. If a high glucose pattern is detected, in step 878, the DGA can output a fourth dose guidance. The fourth dose guidance may increase the recommended insulin dose associated with lunch, i.e., the fourth dose guidance may include a higher dose than the previous post-lunch dose. In one embodiment, the fourth dose guidance may include a higher dose than the post-lunch dose administered the previous day.

[0334] In step 880, the DGA can detect whether a high glucose pattern exists during the post-dinner period. If a high glucose pattern is detected, in step 882, the DGA can output a fifth dose guidance, which may increase the recommended insulin dose associated with dinner, meaning the fifth dose guidance may include a higher dose than the previous post-dinner dose. In one embodiment, the fifth dose guidance may include a higher dose than the post-dinner dose administered the previous day. In one embodiment, the DGA may increase the recommended insulin dose associated with dinner only if it is safe to do so, for example, if it can be increased without causing a low glucose pattern during the nighttime period.

[0335] In another exemplary embodiment, as shown in the flowchart of Figure 17C, in step 885 of exemplary method 883, the DGA can detect whether a high glucose pattern exists during the nighttime period, as described with reference to the GPA.

[0336] If a high glucose pattern is detected during the nighttime period, in step 886, the DGA can determine whether an increase in the basal dose will cause a low glucose pattern at any time of day. If an increase in the basal dose will cause a low glucose pattern at any time of day, in step 887, the DGA can output a first dose guidance for the time of day determined to have a low glucose pattern. The first dose guidance may reduce the recommended insulin dose associated with the time of day determined to have a low glucose pattern; that is, the first dose guidance may include a lower dose than a previous dose administered during the same time of day. In one embodiment, the first dose guidance may include a lower dose than a dose administered on the previous day during the same time of day.

[0337] If increasing the basal dose is not determined to cause a hypoglycemic pattern in any time period, in step 889, the DGA may output a second dose guidance. The second dose guidance may increase the recommended basal dose to address a hyperglucose pattern during the nocturnal period, i.e., the second dose guidance may include a higher dose than the prior basal dose. In one embodiment, the second dose guidance may include a higher dose than the basal dose administered the previous day. The DGA may then be configured to output a first dose guidance that decreases the recommended insulin amount related to the 24-hour period related to the time period in which a hypoglucose pattern was determined to be present in step 887, then perform the next titration iteration in step 888, and then determine in step 885 whether a hyperglucose pattern is present during the nocturnal period.

[0338] In another exemplary embodiment, as shown in the flowchart of Figure 17D, in an exemplary method 890 beginning in step 891, the DGA can detect whether a high glucose pattern is present during the post-dinner period. If a high glucose pattern is detected during the post-dinner period, in step 892, the DGA can determine whether the dinner-related insulin dose can be safely increased. For example, if the dinner-related insulin dose could cause a low glucose pattern during the nighttime period, the dinner dose cannot be safely increased.

[0339] If it is possible to safely increase the insulin dose associated with dinner, in step 893, the DGA may output a first dose guidance. The first dose guidance may increase the recommended insulin dose associated with dinner to address a high glucose pattern during the post-dinner period, i.e., the first dose guidance may include a higher dose than the previous post-dinner dose. In one embodiment, the first dose guidance may include a higher dose than the post-meal dose administered the previous day.

[0340] If the evening dose cannot be safely increased, in step 894a, the DGA may output a second dose guidance. The second dose guidance may decrease or reduce the recommended basal insulin dose, i.e., the second dose guidance may include a lower dose than the prior basal dose. In one embodiment, the second dose guidance may include a lower dose than the basal dose administered the previous day. The DGA may also be configured to subsequently perform the next titration iteration in step 894b after the DGA has reduced the recommended basal dose in step 894a, and then determine in step 891 whether a high glucose pattern exists during the post-meal interval.

[0341] Issues related to MDD connectivity To provide accurate dose guidance, DGAs need access to the latest glucose analyte and insulin dose data. Gaps in either data can lead to inaccurate recommendations and potentially serious hypoglycemic episodes.

[0342] In one exemplary embodiment, as shown in Figure 17E, in an exemplary method 895 beginning in step 896, the DGA may receive or otherwise access the relevant insulin data (e.g., from MDD152). For example, the DGA may check for the latest insulin delivery information by requesting delivery information from various sources, including but not limited to MDD152, MDD-related applications, or interfaces that store the latest insulin delivery information (e.g., an MDD application web server), or by checking the memory of various applications for the latest insulin delivery information.

[0343] In step 897, the DGA may determine whether it has received data relating to the last dose administered to the subject. This step may be particularly applicable to embodiments in which the device or software responsible for recording dose administration is different from the DGA or the device performing the DGA. In embodiments in which the DGA is automatically provided with dose administration data (for example, the DGA is performed by MDD152), this step may not be applicable.

[0344] The DGA can determine whether it has the most up-to-date data available based on various factors. In one embodiment, this can be determined based on the time gap of received insulin dose data. For example, if the user is on a complete frequent injector regimen (basal + 3 mealtime boluses), the DGA can communicate with the MDD152 or its associated application at least every approximately 6 hours. If communication has not occurred during that time, the DGA can be configured to determine that the MDD152 needs to be connected to the DGA before providing dose guidance. In one embodiment, the DGA can assume that it has not received data related to the last administered dose if the time gap difference since the last dose administration was received is longer than the assumed time between meals. For example, the assumed meal time could be approximately 5 hours, or approximately 6 hours, or approximately 6.5 hours, or approximately 7 hours, or approximately 7.5 hours, or approximately 8 hours. In another embodiment, the DGA can detect whether Bluetooth communication is enabled between the user's display device 120, e.g., a smartphone, and the MDD152. For example, Bluetooth communication may not be enabled on either device 120, the MDD152, or both. In another embodiment, the DGA can detect whether the power supply associated with the medication delivery device needs to be replaced.

[0345] If it is determined that data related to the last dose administered to the subject has not been received, in step 898, the DGA may notify the user that it cannot provide dose guidance. In one embodiment, the UID200 may display a message to the user indicating that the DGA cannot output dose guidance until it receives the latest insulin delivery information. In another embodiment, the DGA may also generate a prompt to notify the user to turn on Bluetooth on the display device 120, the MDD152, or both, and display this prompt on the UID200. In another embodiment, the DGA may also indicate that the battery of the MDD152 needs to be replaced. Furthermore, the DGA may determine the remaining battery life of the MDD152 and output a warning to the patient that can be displayed on the UID200 if the battery life falls below a certain threshold, for example, if the battery life falls below 10%. In another embodiment, the DGA may also output a notification displayed in UID200 to inform the user of the last recorded insulin dose and timestamp, and to warn the user that dose guidance will not be based on any doses that may follow that last dose and timestamp.

[0346] If it is determined that data related to the last dose administered to the subject has been received, in step 899, the DGA may output dose guidance to UID200 based on the received glucose analyte data and insulin dose data.

[0347] Recommendation for additional tests in cases of insulin delivery abnormalities DGA can be configured to perform statistics corresponding to various measurements of administered insulin and measured glucose levels. The correlation between various insulin and glucose measurements can be used to identify DGA abnormalities, which may include, but are not limited to, erroneous recordings of insulin dose, potentially skewed low or high glucose readings, and decreased or increased insulin resistance.

[0348] The insulin metric used may be a rolling insulin metric. In one embodiment, the rolling insulin metric may be the total dose of insulin over a time period. The time period may be approximately 24 hours, approximately 48 hours, or approximately 72 hours. Furthermore, the total dose of insulin may be the total dose of long-acting and rapid-acting insulin over the time period. In another embodiment, the rolling insulin metric may be insulin onboard over time since the start of a meal. Such a metric may have different predetermined insulin-related parameters for different mealtime insulin types, such as DIA or duration of insulin action.

[0349] The glucose index used may be a rolling glucose index. In one embodiment, the rolling glucose index may be rolling mean glucose, rolling median glucose, or rolling mode glucose. In another embodiment, the rolling glucose index may be meal start normalized glucose AUC or meal glucose change (meal delta).

[0350] In another exemplary embodiment, as shown in the flowchart of Figure 17F, in step 851 of exemplary method 849, the DGA can determine a first rolling insulin index associated with a first time from insulin dose data. In step 853, the DGA can determine a first rolling glucose index associated with a first time from glucose dose data. The first rolling insulin index and the first rolling glucose index can be associated together to form a first complementary pair.

[0351] Many different complementary pairs can be formed between rolling insulin indices and rolling glucose indices. For example, in one embodiment, the rolling insulin indice of total insulin dose within a rolling time period can be paired with one of the following: rolling mean glucose, rolling median glucose, or rolling mode glucose for the same or similar time window. In another embodiment, complementary pairs such as rolling past 48 hours glucose mode and rolling past 48 hours total insulin dose can also follow the same general procedure outlined above. In yet another embodiment, IOB at a specific time elapsed since the start of a meal can be paired with either meal start normalized glucose AUC or meal delta (e.g., change in glucose due to the meal). Time horizons for pairing IOB and AUC may include, but are not limited to, about 60 minutes, 120 minutes, 150 minutes, or 300 minutes postprandially.

[0352] In step 855, the DGA can refer to a data space containing first, second, and third zones to determine which of the first, second, and third zones contains the first complementary pair. The data space can be defined by multiple complementary pairs, each complementary pair containing rolling insulin and rolling glucose indices associated with the same time period. For multiple complementary pairs, the paired values ​​can be collected at regular time intervals, e.g., approximately every 2 hours, or every 6 hours, or every 12 hours, or every 24 hours, or at other intervals that balance appropriate data density with minimum data retention requirements. The amount of stored complementary pairs can, in some embodiments, be held in a FIFO (First-in-First-Out) buffer implemented in software or hardware. Within the complementary pairs in the FIFO buffer, correlations can be established between the complementary pairs, as well as fitting a curve to a scatter plot created from the insulin and glucose index pairs collected over time. This correlation can be a curve of a predetermined structure (e.g., a cubic polynomial) that potentially has one or more parameters determined based on paired data in a FIFO buffer and one or more parameters predetermined from prior population data. This curve can represent the nominally expected relationship between paired observations. In addition to the nominally expected relationship, two safety boundary curves with predetermined structures can also be constructed above and below the curve of the nominally expected relationship. Some parameters can be determined based on paired data in a FIFO buffer, while others can be predetermined from prior population data. To improve numerical stability, the parameter fits of the nominal curve, upper curve, and lower curve for different time horizons can be associated by prior rules. Other instances can be interpolated from existing time horizons to cover this balance check between insulin and glucose. The curve of the nominally expected relationship and the two safety boundary curves can form three zones in the data space. The first zone is defined as the zone between the upper and lower safety boundary curves and includes the curve of the nominally expected relationship.The second zone is defined as the zone above the upper safety boundary curve, and the third zone is defined as the zone below the lower safety boundary curve.

[0353] In step 857, DGA may output a notification to check at least one of SCD102 or MDD152 in response to a determination that a complementary pair including a first rolling insulin index and a first rolling glucose index falls within a second or third zone.

[0354] Figure 17G shows an example of tracking complementary pairs where the rolling insulin index is the estimated IOB 90 minutes after each meal and the rolling glucose index is the meal-start normalized glucose AUC 90 minutes after each meal. The complementary pair being analyzed 867 (e.g., the most recent complementary pair shown as a solid circle in Figure 17G) has been excluded from fitting the curve of the nominally expected relationship 861 and represents an event of interest, such as the user's glucose-insulin balance state 90 minutes postprandial. The most recent complementary pair 867 is analyzed to determine which zone it corresponds to. By examining its position relative to two safety boundaries 863,865, it can be determined which zone this complementary pair 867 falls into. For example, the solid circle 867 shown in Figure 17G appears "below" the lower safety boundary of a third zone 873. This occurrence could be due to several factors, including (1) the recorded amount of insulin being incorrectly higher than the amount of insulin actually delivered, (2) the glucose reading being skewed towards the low, or (3) other confounding factors such as decreased insulin resistance as a result of exercise, or a significantly different composition of the meal consumed. Depending on the actual combination of events, if the most recent pair falls well below the lower safety threshold, there may be a risk of false notification of imminent hypoglycemia or failure to detect postprandial hyperglycemia.

[0355] In contrast, if the position of the complementary pair of interest is above the upper safety boundary of the second zone 871, one or more opposing scenarios may be occurring, namely (1) the recorded amount of insulin may be incorrectly lower than the actual amount of insulin delivered, including a forgotten meal medication; (2) glucose readings may be biased towards high; or (3) other confounding factors may be present, such as increased insulin resistance as a result of illness, or a significantly different composition of the meal that may have been consumed. Depending on the combination of actual events, if the most recent pair is well above the upper safety boundary, there may be a risk of false notification of imminent hyperglycemia or a risk of failure to detect postprandial hyperglycemia.

[0356] Prior to the conclusion that a consistency check of the DGA100 may be necessary if the complementary pair is mapped to exceed the upper safety threshold in the second zone or fall below the lower safety threshold in the third zone, sufficient research data was used to make this determination. Therefore, the DGA can notify the user to perform self-monitoring of blood glucose (SMBG). If blood glucose (BGM) readings can be linked to the DGS100 or otherwise entered into the DGA, this can be used to determine whether the sensor 102 needs to be replaced using one or more threshold comparisons not covered in this discussion. Otherwise, the DGA can notify the user to check the MDD152 or the cap of the smart insulin pen for possible causes of error.

[0357] Incorporate trends into bolus calculations. Traditional bolus calculators determined the dosage based on the difference between the user's current glucose level and their target glucose level. These traditional bolus calculators treated the current glucose value as a separate snapshot in time, without considering the trend in glucose levels at that point in time. However, during periods of high glucose fluctuations, the recommended dosage can vary significantly because the current glucose level can increase or decrease rapidly from one point in time to the next.

[0358] In December 2018, the Endocrine Society published consensus guidelines for the use of glucose trend arrows in diabetes management (the entire content of which is incorporated herein by reference; see YC Kudva, et al., “Approach to Using Trend Arrows in the Freestyle Libre Flash Glucose Monitoring Systems in Adults,” Journal of the Endocrine Society, vol. 2, pp. 1320-1337, 2018). Glucose trend arrows can be classified into five categories based on the rate of change in glucose: (1) rapidly increasing (increasing by more than 2 mg / dL / min), (2) increasing (1-2 mg / dL / min), (3) slowly changing (no change greater than 1 mg / dL / min), (4) decreasing (decreasing by 1-2 mg / dL / min), and (5) rapidly decreasing (decreasing by more than 2 mg / dL / min).

[0359] To attempt to explain such rapid changes, heuristics can be developed to calculate recommended doses for each trend arrow category, incorporating the rate of change in glucose in addition to the current glucose value. Depending on the reported rate of change, the recommended dose may be increased or decreased to accommodate the dynamic glucose response by utilizing an additional rate of change term. It is expected that developing these heuristics will minimize the incidence of post-medication hypoglycemia and thereby improve glucose control indicators.

[0360] Insulin site rotation The method described here facilitates appropriate site rotation for insulin injections by automatically detecting the injection site of the insulin pen needle and the infusion set.

[0361] The most common method of insulin delivery is administration into the subcutaneous tissue via individual injections or continuous infusions. Proper placement of both insulin injections and infusion sets requires "rotation" of injection sites; that is, rotating between different locations on the body, thereby avoiding local skin reactions caused by repeated and sustained needle insertions. Two common consequences associated with insufficient injection site rotation are scar tissue formation and lipoplasia. Scar tissue is characterized by the formation of fibrous tissue resulting from repeated trauma or improper healing of the initial wound, and is avascular tissue rich in collagen. Lipoplasia is clinically defined as a local accumulation of fat deposits at the insulin injection site. While scar tissue is a problem prevalent throughout injection therapy, lipoplasia is a symptom seen almost alone in relation to subcutaneous insulin administration. Both manifest as hard nodules under the skin and are associated with localized areas that are primarily avascular, negatively impacting systemic insulin uptake and action. Therefore, these effects on insulin absorption are often considered together. These effects include decreased insulin absorption (up to 40%), increased total daily insulin dose (TDD), and poor blood glucose control. The prevalence is also high, with an estimated 50% of people receiving insulin therapy experiencing these symptoms.

[0362] Currently, there is no technical solution to the problem of ineffective site rotation. Site rotation relies on patient education by physicians and diabetes educators, and subsequent patient adherence.

[0363] As described herein, the DGS100 may include a site rotation application that can be configured to detect common injection sites and provide guidance to the user to rotate to a new injection site if the same site is repeatedly detected. By presenting site rotation information to the user as part of a dose guidance regimen, the DGS100 can promote better injection habits, greater insulin efficacy, and a wider time-in-range.

[0364] In one embodiment, as shown in Figures 18A and 18B, in an exemplary method 275 beginning in step 276, the part rotation application may be configured to determine a first distance 270 between the electronic device, such as a display device 120 (e.g., a smartphone), and the SCD 102, and a second distance 272 between the electronic device and the MDD 152. In one embodiment, the part rotation application may employ Bluetooth communication (BLE) between three separate devices, namely (1) a display device 120 such as a smartphone, (2) the SCD 102, and (3) an MDD 152 such as a connected pen needle. As shown in Figure 18A, the display device 120 may be configured to function as a central connection point for communication. When dose guidance is requested from the DGA, the display device 120 can determine a first distance 270 between the display device 120 and the SCD 102, and a second distance 272 between the display device 120 and the MDD 152. In one embodiment, the first distance 270 can be determined by the first signal strength between the display device 120 and the SCD 102, and the second distance 272 can be determined by the second signal strength between the display device 120 and the MDD 152.

[0365] In step 278, the part rotation application can be configured to calculate a third distance 274 between SCD102 and MDD152, where SCD102 is located in a fixed location on the subject. Since the display device 120 is not fixed in one location, it can triangulate the first and second signals to determine the third distance 274 between SCD102 and MDD152, which are located in fixed locations on the subject's body. The calculated third distance 274 between MDD152 and SCD102 can then be recorded in the part rotation application of the display device 120.

[0366] In step 282, the site rotation application may be configured to output a message recommending that the MDD be moved to a new injection site in response to a determination that the calculated third distance is substantially similar to a previously calculated third distance. In one embodiment, if the calculated third distance 274 between SCD 102 and MDD 152 is repeatedly exceeded by a predetermined threshold, the site rotation application may be configured to provide a guidance message suggesting that the user inject insulin at the new site location. The threshold may be one, two, or three times. In one embodiment, the site rotation application may further be configured to provide the user with a list of acceptable site locations to present ideas for new injection sites. These alternative areas may include the arm, thigh, abdomen, and buttocks.

[0367] Additional exemplary embodiments Additional exemplary embodiments related to drug delivery are also described herein. These embodiments are described in the context of an insulin pen, but are not limited to such embodiments. In many embodiments, the MDD152 (e.g., an insulin pen) can communicate directly with the SCD102, and thus no additional reader device may be required. In some embodiments, the reader device can also communicate with a sensor control device that is communicating with the MDD152. In these embodiments, the reader device can also communicate with the MDD152. In other embodiments, the reader device can communicate with the MDD152, and the MDD152 itself communicates with the SCD102, which does not communicate with the reader device. In other embodiments, the SCD102 communicates with the reader device, and the reader device itself communicates with the MDD152, but the MDD152 does not communicate with the SCD102. These various communication schemes allow any type of information (e.g., analyte measurements, alarms, user information or settings, dose guidance, etc.) to be communicated from one device to another in the system via an intermediate device. Communication can be conducted via Bluetooth, Bluetooth Low Energy, or another wireless protocol (e.g., NFC, RFID, Wi-Fi). Communication may be sustained (e.g., active Bluetooth pairing) or intermittent (e.g., NFC proximity scanning).

[0368] In some embodiments, the SCD102 or display device 120, e.g., a reader device (RD), may check whether the MDD152 is maintaining a wireless connection with the SCD102 or reader device for safety purposes, such as notifying the user if the MDD152 is potentially outside the immediate vicinity. If the SCD102 or RD detects a loss of connection, an alarm is generated on the SCD102 (if configured to generate an audible or visual alarm) or the RD (or the SCD102 can notify the RD to generate an alarm). Similar alarms may be generated when a priming problem or failure, or drug supply depletion (e.g., low cartridge) is detected. If the SCD102, RD, or MDD152 detects a high analyte condition (e.g., high blood glucose), the SCD102 or RD (via communication with the MDD152), or the MDD152 itself, may determine whether the dose was recently administered and refrain from generating an alarm (on the SCD102, RD, or MDD152).

[0369] Other notifications or alarms that can be generated for the user may relate to the remaining amount of medication in the pen, including estimating and / or reminding the user that there is enough medication remaining to administer within a certain time period (e.g., one day). If it is determined that the next scheduled dose is greater than the remaining amount of medication, a message recommending the use of a new pen or the loading of a new cartridge may be output. The MDD152 can be configured to monitor the amount of medication and generate an alarm or notification if the expected amount does not match the actual (sensed) amount. The MDD152 can also be configured to monitor the duration the delivery button is pressed to ensure complete delivery and notify the user if incomplete delivery is suspected. If the MDD152 or DGS100 detects that the button has been pressed for too short a time, the MDD152 or DGS100 may assume that the user has administered a smaller dose than recommended. The DGA or MDD152 may output a query to the user to verify whether the administered dose is an incomplete dose or an intended low dose. If the MDD152 or DGS100 detects that the delivery button has been pressed for too long (for example, that too long it takes to administer the recommended dose or the dosage indicated in the dose guidance), the MDD152 or other system device (e.g., a DGA installed in the display device 120) may notify or alert the user that an overdose may have been administered. In one embodiment, the MDD152 may be configured to output an audible notification (e.g., a beep), a tactile notification (e.g., a vibration or click), and / or a visual notification (e.g., an LED, light) when the dose is complete, so that the user can stop pressing the actuator or button.After a dose is administered, the SCD102 or RD can be configured to send a blackout time to the MDD152, so that if the MDD152 is disconnected or unable to communicate with the SCD102 or RD120, which is otherwise configured to provide dose guidance, the MDD152 knows that further dose administration should be prevented or limited, at least during the blackout period. The proposed feed data can be sent to the integrated pen based on the latest best estimates.

[0370] If the connection between the MDD152 and the SCD102 and / or RD120 is lost and then re-established, the user may be prompted to enter the amount of any dose administered during the period of disconnection. In embodiments where the MDD152 monitors the duration of time the injection or delivery button is pressed, it may include an accelerometer or other press-sensing mechanism. Based on the press-down time (or the pattern and / or orientation of the pen movement when the button is pressed) measured by the press-sensing mechanism, the MDD152 may determine whether the button was pressed for priming or dose administration purposes. The MDD152 may be configured to distinguish between different types of presses. For example, the MDD152 may assume that a set of short presses is for priming purposes and therefore not counted as dose administration.

[0371] In one embodiment, the DGS100 (e.g., SCD102, display device 120, or MDD152) can be configured to detect the occurrence of meal consumption and then prompt the user to administer the medication if they have not yet done so. The DGS100 can update dose guidance because analyte data is collected during or immediately after a meal and before dose administration.

[0372] The MDD152 may also include a temperature sensor, allowing the DGS100 to adjust insulin dose guidance based on temperature fluctuations (when insulin effectiveness or insulin onboard (IOB) levels decrease). The system can also be configured to generate notifications when the temperature range is exceeded.

[0373] The SCD102 or RD120 can identify the MDD152 via communication and determine whether the MDD152 is the correct type for dose administration. For example, if the MDD152 contains rapid-acting insulin and the dose guidance concerns long-acting insulin, the SCD102 or RD120 can generate an alarm or notification, or have the MDD102 itself generate the same. The SCD102 or RD120 can support simultaneous connection to multiple different MDD152s, including multiple pens of the same and / or different types.

[0374] Any device within the DGS100 (e.g., a “system device” such as SCD102, RD120, or MDD152) can estimate the time until the next dose is needed and notify the user. The system device can, for example, track the location of MDD152 using a GPS monitor in MDD152 (e.g., geotracking, geofencing) and notify the user of MDD152's location.

[0375] The MDD152 can detect the application of a new needle and prompt the user to apply a new needle if a needle replacement is not detected. The MDD152 can be configured to include a sensor that detects the presence of air or gas in the needle. The MDD152 can be configured to detect whether the needle has been tapped (e.g., using a sensor or accelerometer) and prompt or require the user to tap the needle to remove air or gas. Durable pens can detect the presence of a reservoir or cartridge and prompt the user to input the type of medication (e.g., rapid-acting insulin, long-acting insulin). The MDD152 can be configured to detect whether the medication is properly mixed (e.g., using a sensor or accelerometer) and prompt the user to mix or shake the MDD152 to properly mix the medication.

[0376] The MDD152 can be configured to display the remaining time until the MDD152's battery is depleted or depleted, and / or the remaining time until the medication within the MDD152 is depleted or depleted.

[0377] MDD152 can be configured to lock out the user in certain circumstances. For example, if the user is not authenticated (failure to log in / enter password on the device), if the user's analytic levels are too low or rapidly decreasing, if a large dose has been administered recently, if the insulin in MDD152 is expired or too old, or has been exposed to excessive temperature, if the system status time exceeds the time since the last dose (potentially in combination with glucose levels), any combination of these, or other circumstances.

[0378] A system device, for example, a DGA on a display device 120, can calculate dose guidance and send it to the MDD 152 and / or the cloud 190 (e.g., a trusted server) if the connection is lost or communication fails. The MDD 152 can send a confirmation message that the dose guidance has been received, and if no confirmation message is received, the system device can generate an alarm or notification to the user.

[0379] Before administering a dose, for example, when the user picks up the MDD152 or otherwise activates it, the MDD152 (or any other system device communicating with the MDD152) may prompt the user to verify that the last known dose was correct (e.g., a prompt asking the user to confirm that the last dose, e.g., 5ml@5pm, was correct and that no other doses were taken). This situation may occur if a different MDD152 (e.g., a different pen or pump) is used. If the user indicates that no other doses have been taken, the DGS100 can proceed. If the user indicates that other doses have been taken (e.g., one unknown to the DGS100), the system device can prompt the user to input the dosage, time, and drug type, and determine new dose guidance. The system device may also periodically prompt the user to determine if other pens or drug delivery devices are being used and may request the user to integrate those devices into the system, for example by establishing Bluetooth pairing.

[0380] In many embodiments, a method is provided for parameterizing a patient's medication habits to constitute a dose guidance setting, comprising the steps of: classifying, using at least one processor, based on time-correlated data characterizing the patient's analytes and drug doses received during an analysis period, wherein each drug dose is classified into a drug class; grouping, using at least one processor, each dose into one of a set of mealtime groups; creating, at least partially, patient dose parameters by applying the data from each mealtime group to a model; and storing the dose parameters in computer memory and constituting a dose guidance setting, using at least one processor.

[0381] In some embodiments, the classification step of the method further includes creating a feature matrix that correlates a set of classification features to each dose. The method may further include classification features selected from a group that includes the time of administration for each dose, the time-filtered analyte value, the rate of change of the analyte value closest to the time of administration, the left AUC (area under the curve) showing the integral of the difference between the analyte value and the analyte value closest to the time of administration over the interval before the time of administration, the right AUC showing the integral of the difference between the analyte value and the analyte value closest to the time of administration over the interval after the time of administration, the elapsed time between administrations, the probability that a meal is started within a defined interval before the time of administration, the most likely elapsed time interval since the most recent meal, the probability that a meal is started within a defined interval after the time of administration, and the most likely time interval until the next meal. The method may further include a step of estimating the time of each meal taken by the patient during the analysis period. The method may further include a step of creating a feature matrix based on time-correlated analyte data, wherein the feature matrix correlates a set of analyte data features into distinct regions classified as ascending, pre-descending, and descending. The method may further include a step of creating the estimated meal times based on the feature matrix using an algorithm. The method may further specify that the set of analyte data features is selected from a group including the maximum analyte rate of change, maximum analyte acceleration, analyte value at the point of maximum analyte acceleration, region duration, region height, maximum deceleration, me...

Claims

1. A method for providing a pre-meal correction coefficient in response to analyte data, wherein the method is The process involves determining the analyte pattern type for at least one time-of-day (TOD) period by executing a pattern analysis algorithm that takes patient time-correlated analyte data acquired during the analysis period as input, using at least one processor; The steps include: determining a pre-meal correction coefficient based on the analyte pattern type and the patient's defined medication strategy during the analysis period using at least one processor that executes the algorithm; The steps include: using at least one processor to store a pre-meal correction indicator in computer memory and outputting it to the user or at least one of the medication dispensing devices; Methods that include...

2. The method according to claim 1, wherein the pattern analysis algorithm is a glucose pattern analysis (GPA) algorithm.

3. The method according to claim 2, wherein the GPA algorithm outputs a display of a low glucose pattern, and the method further comprises the step of determining by the at least one processor whether the meal dose of the defined medication strategy includes a pre-meal correction.

4. The method according to claim 3, further comprising the step of including, by at least one processor, a portion of the analyte data only for days on which a meal administration was performed and no bolus administration or pre-meal correction was forgotten.

5. The method according to claim 4, further comprising the step of testing whether at least one processor has enough data remaining to achieve a minimum confidence level.

6. The method according to claim 5, further comprising the step of using a portion of the analyte data with the at least one processor to run the GPA algorithm only on days when a meal administration was performed and no bolus administration or pre-meal correction was forgotten, provided that sufficient data remains.

7. The method according to claim 6, further comprising the step of determining whether the glucose pattern from the GPA algorithm is low using the at least one processor, and if it is low, reducing the recommended values ​​for the dietary portion of each dose for the associated TOD period.

8. The method according to claim 7, further comprising the step of reducing a pre-meal correction factor by at least one processor when the glucose pattern is not low.

9. The method according to claim 5, further comprising the step of including data from the day on which pre-meal correction was performed if insufficient data remains, by the at least one processor.

10. The method according to claim 9, further comprising the step of testing whether there is enough data to achieve a minimum confidence level, including data from the day on which pre-meal correction was performed, using the at least one processor.

11. The method according to claim 10, further comprising the step of running a second GPA algorithm using analytic data, which includes data from a day in which one or more pre-meal corrections were performed as input, by the at least one processor.

12. The method according to claim 11, further comprising the step of determining whether the glucose pattern from the second GPA algorithm is low using the at least one processor, and if it is low, reducing the recommended values ​​for the dietary portion of each dose for the associated TOD period.

13. The method according to claim 12, further comprising the step of using at least one processor to execute a third GPA algorithm using analyte data including dietary dose data as input when the glucose pattern from the second GPA algorithm is low.

14. The method according to claim 13, further comprising the step of determining whether the glucose pattern from the third GPA algorithm is low using the at least one processor, and if it is low, reducing the recommended value for pre-meal correction.

15. The method according to claim 14, further comprising the step of reducing the recommended value of the dietary portion of each dose for the associated TOD period when the glucose pattern from the third GPA algorithm is low, by the at least one processor.

16. The method according to claim 2, wherein the GPA algorithm outputs a display of a high glucose pattern, further comprising the step of using at least one processor to determine whether the analyte data includes pre-meal corrected meal doses, and if not, excluding from the original dataset the data for the day the bolus was forgotten and the data for the day the pre-meal corrected dose was performed, and then running the GPA algorithm based thereon.

17. The method according to claim 16, further comprising the step of determining whether the glucose pattern determined by the GPA algorithm is high using the at least one processor, and if it is not high, increasing the pre-meal correction factor.

18. The method according to claim 16, further comprising the step of using at least one processor to determine whether the glucose pattern determined by the GPA algorithm is high, and if it is high, increasing the recommended values ​​for the dietary portion of each dose during the associated TOD period.

19. The method according to claim 2, wherein the GPA algorithm outputs a display of a high glucose pattern, further comprising the step of using at least one processor to determine whether the analyte data includes pre-meal corrected meal doses, and if so, from the original dataset, including data for the day the meal dose and pre-meal correcting were performed, excluding data for the day the bolus was forgotten, and then running the GPA algorithm based thereon.

20. The method according to claim 19, further comprising the step of using at least one processor to determine whether the glucose pattern determined by the GPA algorithm is high, and if it is high, excluding from the original dataset the data for days when pre-meal correction was performed and the data for days when bolus administration was forgotten, and running the GPA algorithm based thereon.

21. The method according to claim 20, further comprising the step of determining whether the glucose pattern determined by the GPA algorithm is high using the at least one processor, and if it is not high, increasing the pre-meal correction factor.

22. The method according to claim 20, further comprising the step of determining whether the glucose pattern determined by the GPA algorithm is high using the at least one processor, and if it is high, increasing the recommended values ​​for the dietary portion of each dose in the associated TOD period.

23. The method according to claim 2, wherein the GPA algorithm outputs a display of a high glucose pattern, further comprising the step of using at least one processor to determine whether the analyte data includes pre-meal corrected meal doses, and if not, excluding data from the original dataset for days on which pre-meal correcting was performed and days on which boluses were forgotten, and then running the GPA algorithm based thereon.

24. The method according to claim 23, further comprising the step of determining whether the glucose pattern determined by the GPA algorithm is high using the at least one processor, and if it is high, increasing the recommended values ​​for the dietary portion of each dose in the associated TOD period.

25. The method according to claim 23, further comprising the step of determining whether the glucose pattern determined by the GPA algorithm is high using the at least one processor, and if it is not high, increasing the pre-meal correction factor.

26. The method according to claim 1, wherein the analyte data includes an indicator of glucose levels, and the drug of the defined drug administration strategy includes insulin.

27. The method according to claim 1, wherein the pattern analysis algorithm is a TIR algorithm.

28. The step of executing the TIR algorithm is performed by the at least one processor to achieve a time (t) below the target of at least one TOD period. ＢＴ ) and the time to exceed the target (t ＡＴ The method according to claim 27, comprising the step of determining ).

29. The step of executing the TIR algorithm is performed by at least one processor in a time (t) below the target time. ＢＴ ) and the time to exceed the target (t ＡＴ The method according to claim 28, further comprising the step of evaluating at least one of a hypoglycemia risk index or hyperglycemia risk based on ).

Images