Incorporating additional sensors for adapting AID systems

Abstract

Techniques, devices, and systems are disclosed that adjust parameter settings of an insulin delivery algorithm based on input from multiple generic sensor devices. A majority of the generic sensor devices provide sensor readings that are not used as input to the drug delivery algorithm. The generic sensor devices may be operable to detect characteristics such as changes in a user's condition. A processor may evaluate the sensor readings provided by a particular sensor against a sensor baseline reading for the particular sensor. Using the results of the evaluation, the processor may calculate parameter settings or setting adjustments for the drug delivery algorithm. The dosage of the drug may be changed based on the parameter settings or setting adjustments.

Description

[Technical Field]

[0001] CROSS-REFERENCE TO RELATED APPLICATIONS This application claims priority to and the benefit of U.S. Application No. 63 / 375,561, filed September 14, 2022, the entire contents of which are incorporated herein by reference. [Background technology]

[0002] Adaptation of an automated insulin delivery (AID) system is important to ensure that each user's insulin therapy is maintained appropriately as the user's insulin needs change over time. Adaptation of an AID system based solely on glucose and insulin delivery history may not provide sufficient precision to allow for controlled outcomes to accurately adapt the AID system. Summary of the Invention [Problem to be solved by the invention]

[0003] It would be beneficial to have a device or algorithm that utilizes available data from multiple sensors that measure or generate data with sufficient accuracy to allow the AID system to make accurate adaptations. [Means for solving the problem]

[0004] This Summary is provided to introduce some of the concepts discussed below in a simplified manner in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended as an aid in determining the scope of the claimed subject matter.

[0005] According to one example of the disclosed subject matter, a system is disclosed having a plurality of sensors, a memory, and a processor. Each sensor of the plurality of sensors may be configured to generate a respective output related to a user's condition. The memory may store a plurality of sensor baseline readings for each sensor of the plurality of sensors. The processor, when executing programming instructions, is operable to obtain a respective sensor reading output from each sensor of the plurality of sensors. Each sensor reading and a respective sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings may be evaluated. Based on the evaluation, an instruction to adjust an insulin delivery algorithm parameter may be generated.

[0006] Another example of a non-transitory computer-readable medium is provided. When executing programming instructions embodied in the non-transitory computer-readable medium, the processor is operable to obtain a respective sensor reading output from each sensor of a plurality of sensors. The respective sensor readings and respective sensor baseline readings corresponding to each sensor in the stored plurality of sensor baseline readings may be evaluated. Based on the evaluation, insulin delivery algorithm parameters may be adjusted, and instructions to adjust the insulin delivery algorithm parameters may be generated.

[0007] An example of a wearable drug delivery device is provided. The wearable drug delivery device may have a memory, a communication circuit, and a processor. The memory may store a sensor baseline reading for each of a number of sensors and a drug delivery algorithm. The communication circuit may be operable to receive wireless signals. The processor may be coupled to the memory and the communication circuit. The processor may be operable to execute programming instructions and, when executing the programming instructions, to obtain sensor readings from one or more of the plurality of sensors. The processor may determine, based on the received sensor readings and corresponding baseline sensor readings, that the received sensor readings from one or more of the plurality of sensors indicate that parameters input to the drug delivery algorithm should be modified. The adaptive parameters may be calculated based on a sum of individual insulin delivery parameters generated for each one or more of the plurality of sensors. The parameter input to the drug delivery algorithm may be modified. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 illustrates an example of a drug delivery system suitable for implementing the subject matter described herein.

[0009] [Figure 2] FIG. 2 illustrates a non-drug delivery related sensor network operable to communicate with a drug delivery system.

[0010] [Figure 3] FIG. 3 is a flowchart illustrating an exemplary process for utilizing the output of each non-drug delivery-related sensor according to embodiments disclosed herein.

[0011] [Figure 4] FIG. 4 is a flowchart illustrating a detailed process for generating adaptive parameters that can be used to modify parameters of a drug delivery algorithm. DETAILED DESCRIPTION OF THE INVENTION

[0012] The following discussion provides a generalized framework for adapting parameters that affect the performance of a drug delivery algorithm (MDA) based on readings provided by a generic sensor other than the sensor that provides the input used to determine drug dosage by the AID system's MDA. The generic sensor readings are used to inform parameters that control how the MDA responds to analyte sensor inputs, such as continuous glucose monitors, ketone monitors, etc. The generic sensor readings, individually, in combination with one or more, or collectively, may indicate that the user is at high or low risk for either hypoglycemic or hyperglycemic glucose concentrations.

[0013] Types of drug delivery algorithms (MDAs) may include systems based on an "artificial pancreas" algorithm, and more generally, artificial pancreas (AP) applications that may be used in AID systems. For ease of discussion, computer programs and computer applications that implement drug delivery algorithms or applications may be referred to herein as "AP applications." AP applications may be configured to provide automated delivery of insulin based on analyte sensor inputs, such as signals received from analyte sensors, such as continuous glucose monitors (CGMs), ketone sensors, etc. The signals from the analyte sensors may include blood glucose readings, timestamps, etc.

[0014] The MDA may include a number of factors used in calculating the dose of insulin to be provided by the automated delivery of insulin. Various parameters may include the basal setting, the set point, the Q:R ratio of the cost function (e.g., the ratio of the cost of a glucose deviation from a target BG level to the cost of an insulin delivery deviation from a predicted delivery amount) and a gain parameter, as well as others.

[0015] Additionally or alternatively, although the disclosed embodiments may be described with reference to closed-loop algorithm implementations (i.e., no user involvement during routine operation), variations of the disclosed embodiments may be implemented to enable open-loop use (i.e., user involvement) or hybrid closed-loop use (i.e., very limited user involvement). Open-loop embodiments enable the use of various modalities of insulin delivery, such as smart pens, syringes, etc. For example, the disclosed AP application and algorithms may be operable to perform various functions associated with open-loop operation, such as generating prompts requesting input of information such as diabetes type, weight, or age. Similarly, insulin dosages may be received from a user via a user interface by the AP application or algorithm. Other open-loop operations may be achieved by adjusting user settings, etc., in the AP application or algorithm.

[0016] Systems, devices, computer-readable media, and methods according to the present disclosure are described in more detail below with reference to the accompanying drawings, which illustrate one or more examples. The systems, devices, and methods described herein may be embodied in various forms and should not be construed as limited to the examples set forth herein. Instead, these examples are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the technology and apparatus to those skilled in the art. Each of the systems, devices, media, and methods disclosed herein provides one or more advantages over conventional systems, components, and methods.

[0017] FIG. 1 shows a drug delivery system.

[0018] In some examples, a drug delivery system 100 is suitable for delivering insulin to a user according to the disclosed embodiments. The drug delivery system 100 may include a wearable drug delivery device 102, a controller 104, and an analyte sensor 106.

[0019] The wearable drug delivery device 102 may be a wearable device worn on the user's body. The wearable drug delivery device 102 may be a multi-part device. For example, the wearable drug delivery device 102 may have a first part and a second part that are coupled to each other. The first part and / or the second part may fit or slide into a tray or cradle that is secured to the user's body, or the first part and / or the second part may be removable from the tray. When a first part and a second part are used, the first part may include reusable components (e.g., electronic circuitry, a processor, a memory, a pump mechanism, and a potentially rechargeable battery), and the second part may include disposable components (e.g., a reservoir, a needle and / or cannula, a disposable battery, and other parts or components that come into contact with the liquid drug or pharmaceutical). Furthermore, the first part and the second part may include their own housings or may together form a single housing. The wearable drug delivery device 102 may be directly coupled to a user (e.g., via an adhesive, directly, via a tray, attached directly to a body part and / or skin of a user, etc.) In one example, a surface of the wearable drug delivery device 102 or a tray to which the wearable drug delivery device 102 is coupled may include an adhesive to facilitate attachment to the user's skin.

[0020] The wearable drug delivery device 102 may have a processor 114. The processor 114 may be implemented in hardware, software, or any combination thereof. The processor 114 may be, for example, a microprocessor, a logic circuit, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), or a microprocessor coupled to a memory. The processor 114 may be operable to maintain a date and time and perform other functions (e.g., calculations, etc.). The processor 114 may be operable to execute a control application 126 stored in the memory 112, enabling the processor 114 to direct the operation of the wearable drug delivery device 102. The control application 126 may control insulin delivery to a user according to an MDA control approach as described herein. For example, the control application 126 may be an MDA algorithm. The memory 112 may store settings 124 for a user, such as specific factor settings, subjective insulin need parameter settings, MDA settings such as maximum insulin delivery, insulin sensitivity settings, total daily insulin (TDI) settings, insulin decay settings, etc. The memory may store other data 129, such as total daily insulin values, blood glucose measurements from the analyte sensor 106 or controller 104, and insulin doses (both basal and bolus) from the previous minutes, hours, days, weeks, or months. The analyte sensor 106 may be operable to collect user physiological condition data, such as blood glucose measurements and timestamps, which may be shared with the wearable drug delivery device 102, the controller 104, or both. For example, the communication circuitry 142 of the wearable drug delivery device 102 may be operable to communicate with the analyte sensor 106 and the controller 104, as well as the devices 130, 133, and 134. The communication circuitry 142 may be operable to communicate via Bluetooth, cellular communication, and / or other wireless protocols. Although not shown, the memory 112 may include both primary and secondary memory.The memory 112 may include random access memory (RAM), read-only memory (ROM), optical storage devices, magnetic storage devices, removable storage media, solid-state storage devices, and the like.

[0021] The wearable drug delivery device 102 may include a reservoir 120. The reservoir 120 may be operable to store a medicine, drug, or therapeutic agent suitable for automated delivery. A fluid pathway to the user may be provided via tubing and a needle / cannula (not shown). The fluid pathway may include, for example, tubing connecting the wearable drug delivery device 102 to the user (e.g., via tubing connecting the needle or cannula to the reservoir 120). The wearable drug delivery device 102 may be operable, based on a control signal from the processor 114, to expel a drug, drug, or therapeutic agent, such as insulin, from the reservoir 120 to deliver a dose of the drug, drug, or therapeutic agent, such as insulin, to the user via the fluid pathway. The processor 114 may be operable to expel insulin from the reservoir 120.

[0022] For example, there may be one or more communication links 128 with one or more devices of the user and / or the user's caregiver that are physically separate from the wearable drug delivery device 102, including the controller 104 and / or the sensor 106. The communication link 128 may be any wired or wireless communication link operating according to any known communication protocol or standard, such as Bluetooth®, Wi-Fi®, a near field communication standard, a cellular standard, or any other wireless protocol. The analyte sensor 106 may communicate with the wearable drug delivery device 102 via wireless communication link 131 and / or with the controller 104 via wireless communication link 137.

[0023] The wearable drug delivery device 102 may have a user interface 116, such as an integrated display device, to display information to a user and, in some embodiments, to receive information from a user. For example, the user interface 116 may have a touch screen and / or one or more input devices, such as buttons, knobs, or a keyboard, that allow a user to provide input.

[0024] Additionally, the processor 114 may be operable to receive data or information from the analyte sensor 106 as well as other devices that may be operable to communicate with the wearable drug delivery device 102 .

[0025] The wearable drug delivery device 102 may interact with a network 108. The network 108 may include a local area network (LAN), a wide area network (WAN), or a combination thereof. A computing device 132 may interact with the network, and the computing device may be operable to communicate with the wearable drug delivery device 102. A computing device 143 may be a healthcare provider device that communicates with the user's controller 104 and may store settings, etc. An AID algorithm operating as or in cooperation with the controlling application 120 may display a graphical user interface on the computing device 132 that allows for input and display of information related to the AID algorithm.

[0026] The drug delivery system 100 may include an analyte sensor 106 that senses the level of one or more analytes in the user. The analyte level may be used as physiological condition data and transmitted to the controller 104 and / or the wearable drug delivery device 102. The sensor 106 may be coupled to the user, for example, by adhesive or the like, and may provide information or data regarding one or more medical conditions and / or physical attributes of the user. The sensor 106 may be a continuous glucose monitor (CGM) or another type of device or sensor operable to provide blood glucose concentration measurements. The sensor 106 may be physically separate from the wearable drug delivery device 102 or may be an integrated component of the wearable drug delivery device 102. The sensor 106 may provide physiological condition data indicative of the measured or detected blood glucose level of the user to the processor 114 and / or the processor 119. The information or data provided by the sensor 106 may be used to modify the insulin delivery schedule, thereby adjusting the drug delivery operation of the wearable drug delivery device 102.

[0027] The drug delivery system 100 may include a controller 104. In the depicted example, the controller 104 may include a processor 119 and a memory 118. The controller 104 may be a dedicated device, such as a dedicated personal diabetes manager (PDM) device. The controller 104 may also be a programmed general-purpose device, e.g., any portable electronic device including a dedicated controller, such as a microcontroller, a smartphone, a smartwatch, a fitness device, a tablet, etc. The controller 104 may be used to program or coordinate the operation of the wearable drug delivery device 102 and / or the sensor 106. The processor 119 may execute processes to manage the user's blood glucose levels and control the delivery of drugs or therapeutic agents from the wearable drug delivery device 102. The processor 119 may be operable to execute program code stored in the memory 118. For example, the memory 118 may be operable to store a control application 120, such as an AID algorithm, for execution by the processor 119. The control application 120 may be responsible for controlling the wearable drug delivery device 102, including the automatic delivery of insulin, based on recommendations and instructions from the AID algorithm, such as those described herein.

[0028] The memory 118 may store one or more applications, such as the control application 120, and settings 121 for the insulin delivery device 102, as described above. Additionally, the memory 118 may be operable to store other data and / or computer programs 126, such as drug delivery history, blood glucose measurements over a period of time, total daily insulin values, etc. For example, the memory 118 is coupled to the processor 119 and operable to store programming instructions, such as the control application 120 and settings 121, and data, such as other data 126 related to the user's blood glucose measurements and / or data related to the amount of insulin dispensed by the wearable drug delivery device 102.

[0029] The controller 104 may have a user interface (UI) 123 for communicating with a user. The user interface 123 may have a display, such as a touchscreen, for displaying information. If the user interface 123 is a touchscreen, the touchscreen may be used to receive input. The user interface 123 may also have input elements, such as a keyboard, buttons, knobs, etc. In an operational example, the user interface 123 may have a touchscreen display controllable by the processor 119 and operable to display a graphical user interface, and in response to received input, the touchscreen display may be operable to generate a signal indicative of the subjective insulin need parameter. The touchscreen display may be operable, under control of the processor 119, to receive input to a computer application, such as a consumer food tracker, a carbohydrate calculator, a mapping application based on the user's GPS, Wi-Fi, or Bluetooth location, etc.

[0030] The controller 104 may communicate with a network, such as a LAN or WAN, or a combination of such networks, that provides one or more servers or cloud-based services 110 via a wireless communication link 128 via communication circuitry 122. A communication device 122, which may have transceivers 127 and 125, may be coupled to the processor 119. The communication circuitry 122 may be operable to transmit communication signals (e.g., command and control signals) to the wearable drug delivery device 102 and the analyte sensor 106 and to receive communication signals (e.g., via the transceiver 127 or 125). In one example, the communication device 122 may have a first transceiver, such as 125, that is a Bluetooth transceiver operable to communicate with the communication device 122 of the wearable drug delivery device 102, and a second transceiver, such as 127, that is a cellular or Wi-Fi transceiver operable to communicate with the computing device 143 or the cloud-based service 110 via the network 108.

[0031] The cloud-based service 110 may be operable to store user history information such as blood glucose readings over a period of time (e.g., days, months, years), drug delivery history, etc., including insulin delivery amounts (both basal and bolus), insulin delivery times, types of insulin delivered, indicated or detected meal times, trends or deviations in blood glucose readings or other user-related diabetes treatment information, specific factor settings including default settings, current settings, and past settings, etc.

[0032] Other devices, such as smart accessory devices 130 (e.g., smart watches, etc.), fitness devices 133, and other wearable devices 134, may be part of the drug delivery system 100. For example, the other sensor devices 134 may be at least one of a heart rate monitor, an oxygen sensor, a carbohydrate calculator, a pedometer, a food tracking application, a blood glucose sensor, a ketone sensor, etc. These devices 130, 133, and 134 may communicate with the wearable drug delivery device 102 to provide the wearable drug delivery device 102 with sensor readings and other values ​​related to the readings generated by the respective sensor devices. These devices 130, 133, and 134 may execute computer programming instructions to perform some of the control functions otherwise performed by the processor 114 or the processor 119. These devices 130, 133, and 134 may have a user interface, such as a touchscreen display, for displaying information such as accelerometer data, step counts, and heart rate, as described with reference to the examples of FIGS. 1-3. The display may be operable to display a graphical user interface that receives inputs such as meal size, estimated carbohydrate count of a meal, etc. These devices 130, 133, and 134 may have a wireless communication connection with the sensor 106 to receive blood glucose data directly or in parallel with displaying a graphical user interface such as that shown in FIG. 1. Additionally, the smart accessory device 130 may be operable to run one or more programming applications that display information about when the user ate, how much sleep the user had, the amount of screen time the user had, as well as applications related to stress levels, how many times the user checked their blood glucose level, meal size, fat content of meals, frequency of meals, weekly restaurant visits in a week, number of sick days, number of stressed days, number of days participating in meditation and calming exercises, medications and supplements used by the user, etc.Examples of other devices 134 may include a smart scale (such as a Renfo® Bluetooth® scale), an exercise monitor / timer, a heart rate and / or heart rate variability monitor, a blood oxygen monitor, etc.

[0033] In an operational example, a processor such as 114 or 119 of the drug delivery system may be operable to receive physiological data input via communication circuitry (such as 142 of the wearable drug delivery device 102 or 122 of the controller 104) from devices such as 133, 130 external to the drug delivery system and other devices 134. The processor may use the physiological data input to validate an evaluation of glucose measurements over a period of time, as described in more detail with reference to the examples below.

[0034] In another example of operation, the controller 104 may be operable to execute program code that causes the processor 119 of the controller 104 to perform various functions. For example, the processor 119 of the controller 104 may execute an AID algorithm, which is one of the control applications 120 stored in the memory 112 or the memory 118. The processor may be operable to present a user interface, which is at least one component of the user interface 123. The user interface 123 may be a touchscreen display controlled by the processor 119, which is operable to present a graphical user interface that provides input of subjective insulin need parameters that can be used by the AID algorithm. The processor 119 may also cause the presentation of a graphical user interface that provides an input device that allows input of the subjective insulin need parameters. The AID algorithm may generate instructions for the pump 118 to deliver basal insulin to the user, etc.

[0035] The processor 119 may also be operable to collect physiological condition data related to the user from sensors such as the analyte sensor 106 or the heart rate monitor of the fitness device 133 or the smart accessory device 130. In one example, the processor 119 executing the AID algorithm may determine a dose of insulin to deliver based on certain factors determined based on the collected physiological condition and subjective insulin need parameters of the user. The processor 119 may output a control signal to the wearable drug delivery device 102 via one of the transceivers 125 or 127. The output signal may cause the processor 114 to send a command signal to the pump 118 to deliver to the user an amount of medication related to the determined dose of insulin in the reservoir 120 based on the output of the AID algorithm.

[0036] The drug delivery system 100 functions according to an operational cycle that is repeated after a time period or upon completion of a previous cycle. As described above, during each operational cycle, the analyte sensor 106 of the drug delivery system 100 may obtain one or more measurements of an analyte in the user's blood, such as blood glucose and / or ketone levels. During the operational cycle, the analyte measurement(s) may be transmitted by a communication circuit (not shown) of the analyte sensor 106 to a processor (e.g., the processor 119 of the controller 104 or the processor 114 of the wearable drug delivery device 102, or both). The processor 119 or 114 may evaluate the received analyte measurements and, according to an algorithm executed by the processor 119 or 114, may recommend a dosage of a liquid medication, such as those enumerated herein, for delivery to the user. The wearable drug delivery system 100 is operable to deliver the recommended dosage to the user. Upon completion of delivery of the recommended dosage, the current operational cycle ends and a new operational cycle begins in which the above process is repeated. An operating cycle may have a duration of about 5 minutes, although other durations are also possible, such as 2 minutes, 10 minutes, etc. In some examples, the analyte sensor 106 may provide multiple analyte measurements during an operating cycle, and the processor 119 or 114 may or may not process each analyte measurement received.

[0037] The wearable drug delivery device 102 typically has a life cycle based on the amount of liquid medication stored in the reservoir 120 of the wearable drug delivery device 102 and / or the amount of liquid medication delivered to the user. The AID application or algorithm may use multiple parameters, such as blood glucose measurements, total daily insulin amount, on-board insulin amount, etc., when making a determination of the amount of liquid medication to deliver. In an operational example, the processor 119 of the controller 104 may be operable to evaluate the effectiveness of the control of the AID algorithm of the drug delivery device 102. For example, the processor 119 may be operable to utilize carbohydrate indications to determine customized glycemic index values ​​for various food items or combinations of food items (e.g., meals such as breakfast, lunch, or dinner, as well as snacks or sandwiches, etc.), and may use programming code to perform functions or calculations described in more detail with reference to the examples of FIGS. 2 and 3.

[0038] Although system 100 is described with reference to the delivery of insulin and the use of an AID algorithm, system 100 may be operable to implement drug delivery regimens according to drug delivery algorithms using a variety of liquid or therapeutic drugs. The liquid drugs may be or include any drug in liquid form that can be administered by a drug delivery device via a subcutaneous cannula, including, for example, insulin, glucagon-like peptide-1 (GLP-1), pramlintide, co-formulations of two or more of glucagon, GLP-1, pramlintide, and insulin, as well as pain relievers such as opioids or narcotics (e.g., morphine, etc.), methadone, arthritis medications, hormones such as estrogen and testosterone, blood pressure medications, chemotherapy medications, and fertility medications.

[0039] FIG. 2 illustrates an example ecosystem of sensors that generate sensor readings or tracking information that generate data values ​​(e.g., sensor readings or tracking information other than blood glucose measurements) that are not (typically) used by the AID system and MDA according to examples disclosed herein. In some embodiments, a majority of the system's sensors are not (typically) used by the AID system or MDA, and in particular, a majority relates to more than half of the sensors. For example, sensor ecosystem 200 may have multiple general-purpose sensors that provide a wide range of sensor readings. The general-purpose sensors may include, for example, an accelerometer, a gyroscope, a pedometer, an activity monitor, a blood oxygen (O2) sensor, a heart rate monitor, a sleep monitor, a stress monitor, a caffeine intake tracker, an alcohol intake tracker, a water intake tracker, a meal count counter, a meal calculator, a carbohydrate calculator, a clock, an ambient light detector, a screen time tracker, an ambient temperature monitor, a moisture sensor, a sweat sensor, etc.

[0040] For example, sensor ecosystem 200 may include consumer food tracker 211, drug delivery system 212, consumer fitness devices and applications 215, weight scale 217, medications and supplements 219, consumer applications and circadian rhythm data 222, etc. Drug delivery system 212 may include an analyte sensor, drug delivery device 216, and controller 218 similar to those described with reference to FIG.

[0041] One or more components of the drug delivery system 212 have communication circuitry (not shown in this example) operable to communicate with the data network 220 and / or to communicate directly with one or more of the devices in the sensor ecosystem 200 via a direct wireless connection 220a (e.g., Bluetooth, Wi-Fi, etc.). For example, the consumer food tracker 211 and consumer fitness devices and applications 215 and other wearable devices 213 may provide data such as accelerometer sensor readings, GPS information enabling sensor readings related to restaurant co-location frequency or weekly restaurant visit frequency (number in the last week / 7 days), meal frequency, meal size, meal carbohydrate content, meal fat content, meal protein content, caffeine intake, number of sleep hours, etc. (as shown in Table 2 below). These types of data are typically not included as inputs for setting parameter values ​​as used in the drug delivery algorithm (or AID system). The provided data may be used to adapt parameter settings such as glucose control goals, clinical input parameters (e.g., TDI), cost function parameters (such as the R(t) value of the Q:R cost function ratio), insulin-to-carbohydrate ratios, or correction factors (e.g., insulin sensitivity). Other factors such as basal dose (e.g., B(t)) and system gain (e.g., K(t)) may also be adapted using the techniques described herein.

[0042] Returning to FIG. 2, scale 217 and analyte sensor 214 may measure physiological attributes of the user or may receive as input from the user information related to the user's physiological attributes into their respective devices.

[0043] In the process described with reference to FIG. 3 et seq., a generic sensor n receives a reading S that deviates from the baseline sensor reading for that particular sensor. n(i.e., generic sensor n values) over time and may provide an indication that the user is currently experiencing or is likely to experience a particular hypoglycemic or hyperglycemic event. The generated indication may be based solely on the deviation of the particular sensor or may be combined with deviations of other sensors from baseline.

[0044] The processor may receive sensor readings as input from a number of different sensors, and based on an evaluation of the received sensor readings, the processor may select one or more generic sensors S n The processor may adjust the AID system by applying different values ​​to various parameters of the AID system / MDA based on the output(s) of the processor. For example, the processor may make changes (e.g., increase or decrease) to one or more of the tuning parameters of the AID system / MDA: tuning parameter settings, glucose control goals, glycemic setpoint SP(t), input clinical parameters (such as total daily insulin (TDI)), the Q:R ratio of the cost function by adjusting the value of the cost function R(t), the insulin-to-carbohydrate (IC) ratio, the correction factor (also called insulin sensitivity), the basal administration rate B(t), the gain K(t), etc. With respect to the Q:R ratio and R(t) of the cost function, the R value represents a coefficient on insulin cost that is a function of time and is determined based on the (potential) deviation of insulin delivery from the predicted insulin delivery.

[0045] 3 shows a process for determining whether to adjust insulin delivery algorithm parameters. Process 300 may be performed by a processor of a drug delivery system. For example, the processor and memory as part of a wearable drug delivery device may be operable to receive input directly or indirectly (e.g., via controller 104) from multiple sensors configured to detect a physiological state of a user (also referred to as a user's state). The memory may be operable to store multiple sensor baseline readings for each of the multiple sensors.

[0046] For example, the processor, when executing programming instructions implementing process 300 of FIG. 3, may monitor each sensor S of the plurality of sensors S. n The processor may be operable to receive each sensor reading from the wearable device (step 310). The processor may be operable to receive each sensor reading continuously, at regular intervals upon request from the processor, or according to a scheduled delivery. For example, some of the sensors may operate continuously and provide near real-time values, such as a heart rate monitor, while other sensors may generate an output (related to the user's condition) every wearable drug delivery operating cycle (e.g., every 5 minutes), such as a blood glucose monitor. Alternatively, the sensors may have threshold settings and transmit an output only when a threshold is reached or exceeded, such as a stress monitor.

[0047] Each sensor reading S n (t) and a respective sensor baseline reading S corresponding to each sensor of the stored plurality of sensor baseline readings. n,baseline For example, the processor may determine a sensor reading difference (the result is a first difference value) between each sensor reading and each sensor baseline reading, and calculate the difference between each sensor baseline reading and the maximum sensor output value (S n,max ) may be used to perform a function to determine the maximum sensor difference (the result is a second difference value). n,max ) may be the maximum output the sensor is expected to output, and the sensor baseline reading S n,baselinemay be the average or median reading (or output value) of the sensor. The average or median reading may be determined over a time frame. The time frame may be hours, days, weeks, months, or years. The time frame may be a rolling window, or may be a determined or specific time frame, for example, the time frame over which the AID setting (such as the Q:R ratio) was determined. The processor may determine the quotient of the first difference value divided by the second difference value. For each sensor S n The weighting factor W specific to n For example, a Fitbit® heart rate output may have a particular weight, but a combination heart rate / blood oxygen monitor may have a different weight for the heart rate monitor output value and an even different weight for the blood oxygen monitor output value. n may be determined from clinical testing or demographic assessment and evaluation of the user history of each sensor to isolate strong predictors of hypoglycemia or hyperglycemia. In some embodiments, the weighting coefficients are determined by regression analysis or machine learning. The weighting coefficient W n The result of multiplication of the quotient and the value of each sensor (S n ) parameter adjustment value P Sn may be.

[0048] An exemplary equation that may be implemented in this process is shown below:

number

[0049] The output received from each generic sensor can be utilized based on normal and upper limits and each sensor's predicted impact on the user's hyperglycemic or hypoglycemic thresholds.

[0050] For example, at 330, based on the evaluation, the processor may adjust insulin delivery algorithm parameters.

[0051] The predicted impact on hyperglycemia or hypoglycemia can be implemented as an adaptive parameter that is multiplied with each of the adjustment parameters of the AID system described above, as follows:

number

[0052] In one particular example, two general-purpose sensors—an accelerometer and a sensor describing a user's frequency of GPS locations near restaurants (e.g., a computer application evaluating GPS locations at locations frequently visited by the user)—can be implemented in an AID system. Such inputs from the accelerometer, the sensor evaluating the GPS signal, or other general-purpose sensors can be utilized by a drug delivery algorithm by applying weighting coefficients to the output of each sensor based on its association with the user's state that drug delivery is designed to control. This weighting methodology provides a robust methodology for incorporating any general-purpose sensor into a drug delivery algorithm without requiring detailed model identification. In the described example, each sensor receives a weighting coefficient, so the result of A(t) is calculated by multiplying each weighting coefficient P Sn (t) is the weighted sum of

[0053] Using the framework described above, Table 1 below shows examples of various readings for each sensor. n can result in, for example, the following probability of each predicted effect on hyperglycemia or hypoglycemia: [Table 1]

[0054] In this example, based on an evaluation of clinical data or user history related to the sensor readings output by the accelerometer or the frequency of co-location of restaurants, a correlation between the sensor readings and the user's blood glucose concentration (also referred to as glucose concentration) may be determined, respectively. For example, the accelerometer may have a negative correlation with glucose concentration, specifically, higher accelerometer readings typically predict a higher likelihood of hypoglycemia. Alternatively, the frequency of co-location of restaurants may have a positive correlation with glucose concentration, specifically, higher frequency of presence (i.e., co-location) at restaurants predicts a higher likelihood of hyperglycemia.

[0055] Next, P n The effect of a drug on hyperglycemia or hypoglycemia can be defined as follows:

number

[0056] The adjustment factor A(t) shown in Equation 2 above can then be calculated as the average of the available influence factors.

number

[0057] The value of −0.0231 can then be translated into adjustments to the user's various adjustment parameters (also referred to as insulin delivery algorithm parameter values) within the AID system as a bias to lower insulin delivery by 2.3% for the current cycle (i.e., a 2.3% increase in glucose target, a 2.3% decrease in input clinical parameter, a 2.3% increase in Q:R ratio, a 2.3% increase in IC ratio, a 2.3% increase in correction factor, etc.). Thus, in some embodiments, adjusting the insulin delivery algorithm parameter value includes evaluating (i.e., selecting) a value for the insulin delivery algorithm parameter value to be adjusted and, in response to evaluating that the insulin delivery algorithm parameter should be adjusted, generating a signal identifying the insulin delivery algorithm parameter value to be adjusted. Furthermore, in some embodiments, adjusting the insulin delivery algorithm parameter value further includes evaluating other respective sensor readings received from other respective sensors of the plurality of sensors, particularly in response to the signal. Furthermore, the respective insulin delivery parameter value for each other sensor of the plurality of sensors may be established based on the other respective sensor readings. Additionally, the insulin delivery parameter value and all respective insulin delivery parameter values ​​of the other respective sensors of the plurality of sensors may be used to generate adaptive parameters that can be used by the drug delivery algorithm, and in particular, the adaptive parameters can be used by the drug delivery algorithm to recalculate parameter settings of the drug delivery algorithm. In some embodiments, adjusting the insulin delivery algorithm parameter value comprises evaluating the value of the insulin delivery algorithm parameter value to be adjusted, and in response to evaluating that the insulin delivery algorithm parameter should be adjusted, adjusting the insulin delivery algorithm parameter, and in particular, adjusting the insulin delivery algorithm parameter includes generating a signal identifying the insulin delivery algorithm parameter value to be adjusted.

[0058] Different sensors have different effects and may be assigned different sensor effects that the processor may adjust over time as it receives more output from the respective sensors. For example, as shown in Table 2, the processor may adjust the sensor baseline readings (S n,baseline ) may be used to calibrate the sensor output from the sensor as shown in Table 2. [Table 2] Thus, in some embodiments, the output generated by the sensor(s) related to the user's condition includes at least one of the user's stress level, the user's moving speed, the number of times the user has checked their blood glucose level, the number of glucose measurements, the number of caffeine intakes, the amount of food eaten, the amount of fat in the food eaten, the frequency of meals eaten, the number of restaurant visits (per week), the number of sick days, the number of stressed days, the number of days participating in meditation and calming exercises, medications and supplements used by the user and / or the amount of sleep.

[0059] As seen in Table 2 above, the outputs from each sensor may be different from each other and may have different units from each other. FIG. 4 shows a flowchart for performing a process for evaluating each sensor reading and each sensor baseline reading corresponding to each sensor of a stored plurality of sensor baseline readings, according to an example discussed herein. Process 400 follows additional exemplary steps for implementing Equation 1, which is reproduced below for convenience. In one example, Equation 1 can be modified to calculate the sensor reading (S) at time t as follows: n ) resulting parameter values ​​(P n ) may be used to characterize

number

[0060] The parameter value P from Eq. Sn (t) is determined for each sensor and used to adapt the parameter settings of the AID system / MDA. In step 450, the processor may generate adaptation parameters for use by the drug delivery algorithm or AID system. For example, Equation 2 (reproduced below for convenience) may be used to determine adaptation parameters that may be applied to each adjustable AID system / MDA parameter setting. The adaptation parameters A(t) may be calculated according to Equation 2.

number

[0061] The calculated adaptive parameters A(t) are applied to each adjustable parameter of the AID system / MDA as described above. In a general overview, each sensor gets a weighting factor, and then a weighted sum of each weighting factor (to combine all sensors) is obtained.

[0062] Specific examples of the present disclosure have been described above. However, it is expressly noted that the present disclosure is not limited to these examples; rather, additions and modifications to those explicitly described herein are intended to be included within the scope of the disclosed examples. Furthermore, it is understood that the features of the various examples described herein are not mutually exclusive, and that various combinations and permutations of the features may exist even if such combinations and permutations are not explicitly stated herein without departing from the spirit and scope of the disclosed examples. Indeed, variations, modifications, and other implementations of what is described herein will occur to those skilled in the art without departing from the spirit and scope of the disclosed examples. Thus, the disclosed examples are not defined solely by the foregoing illustrative description.

[0063] It is emphasized that the Abstract of the Disclosure is provided to allow the reader to quickly grasp the nature of the technical disclosure. This Abstract of the Disclosure is submitted with the understanding that it will not be used to interpret or limit the scope or meaning of the claims. Moreover, in the foregoing Detailed Description, various features are grouped together in a single embodiment for streamlining the disclosure. This method of disclosure is not to be interpreted as reflecting an intention that the claimed embodiments require more features than are expressly recited in each claim. Rather, as the following claims reflect, novel subject matter lies in fewer than all features of a single disclosed embodiment. Accordingly, the following claims are hereby incorporated into this specification, with each claim standing on its own as a separate embodiment. In the appended claims, the terms "comprising" and "in which" are used as plain-language equivalents of the terms "comprising" and "wherein," respectively. Furthermore, the terms "first," "second," "third," etc. are used merely as labels and are not intended to impose numerical requirements on their subject matter.

[0064] The description of the foregoing embodiments has been presented for purposes of illustration and description. It is not intended to be exhaustive or to limit the disclosure to the precise form disclosed. Many modifications and variations are possible in light of this disclosure. It is intended that the scope of the disclosure be limited not by this detailed description, but rather by the claims appended hereto. Future applications claiming priority to this application may claim the disclosed subject matter in different ways, and may generally include any set of one or more features as variously disclosed or otherwise illustrated herein.

[0065] While the invention is defined in the appended claims, it should be understood that the invention may (alternatively) be defined according to the following embodiments. 1. A plurality of sensors, each configured to generate a respective output related to a state of a user; a memory that stores a plurality of sensor baseline readings for each of the plurality of sensors; A processor operable to execute programming instructions, wherein the processor, when executing the programming instructions, obtaining a respective sensor reading output from each sensor of the plurality of sensors; evaluating each sensor reading and a respective sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings; a processor operable to adjust insulin delivery algorithm parameters based on said evaluation; A system comprising: 2. when the processor evaluates each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, determining a sensor reading difference between each sensor reading and each sensor baseline reading; Utilizing each sensor baseline reading to determine the maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; 2. The system of embodiment 1, wherein the system is operable to establish an insulin delivery parameter value for each sensor by applying a weighting to the calculated preliminary parameter values. 3. When the processor evaluates each sensor reading and each sensor baseline reading: assessing the value of the insulin delivery algorithm parameter value to be adjusted; 3. The system of embodiment 1 or 2, further operable to generate a signal identifying the insulin delivery algorithm parameter value to be adjusted in response to assessing that the insulin delivery algorithm parameter should be adjusted. 4. evaluating other respective sensor readings received from other respective sensors of said plurality of sensors, particularly in response to a signal; establishing a respective insulin delivery parameter value for each other respective sensor of said plurality of sensors; A system described in any one of embodiments 1 to 3, further operable to generate adaptive parameters that can be used by a drug delivery algorithm using the insulin delivery parameter value and each of the other respective insulin delivery parameter values ​​of the plurality of sensors, and in particular, to enable the adaptive parameters to be used by the drug delivery algorithm to recalculate parameter settings of the drug delivery algorithm. 5. calculating an insulin delivery parameter value for each of the plurality of sensors based on the output of the respective sensor readings received from each of the plurality of sensors; using the insulin delivery parameter value for each of the plurality of sensors to calculate an adaptation parameter; 5. The system of any one of embodiments 1 to 4, further operable to recalculate parameter settings of a drug delivery algorithm based on the adaptive parameters. 6. A system described in any one of embodiments 1 to 5, wherein the memory is further operable to store a drug delivery algorithm and the processor is further operable to execute the drug delivery algorithm. 7. The system described in any one of embodiments 1 to 6, further comprising a wearable drug delivery device having the memory, the processor and communication circuitry, the communication circuitry operable to wirelessly communicate with one or more of the plurality of sensors. 8. A system described in any one of embodiments 1 to 7, further comprising a control device having the memory, the processor, and a communication circuit, the communication circuit operable to wirelessly communicate with one or more of the plurality of sensors. 9. A plurality of sensors configured to detect a state of a user 9. The system of any one of claims 1 to 8, comprising at least one of a wearable fitness monitor, a heart rate monitor, an oxygen sensor, a carbohydrate calculator, a pedometer, a meal tracker application, a blood glucose detector, or a ketone detector. 10. One or more of the plurality of sensors: 9. A system described in any one of embodiments 1 to 8, further comprising a communication circuit operable to transmit sensor readings indicative of respective detected conditions. 11. A system described in any one of embodiments 1 to 9, wherein the sensor readings of the majority of the plurality of sensors are not used as direct inputs to the drug delivery algorithm or medication delivery algorithm of the AID system. 12. When executed by a processor, obtaining respective sensor readings output from the sensors; evaluating each sensor reading and a respective sensor baseline reading corresponding to each sensor of the plurality of sensor baseline readings; adjusting insulin delivery algorithm parameters based on said evaluation; A non-transitory computer-readable medium having embedded thereon programming instructions that cause the processor to execute the 13. The non-transitory computer-readable medium of embodiment 12, wherein the output of the sensor readings of each of the plurality of sensors is not used as a direct input to a drug delivery algorithm or a medication delivery algorithm of the AID system. 14. When evaluating each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, determining a sensor reading difference between each sensor reading and each sensor baseline reading; utilizing each sensor baseline reading to determine a maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; establishing an insulin delivery parameter value for each sensor by applying weightings to the calculated preliminary parameter values; 14. The non-transitory computer-readable medium of embodiment 12 or 13, which causes the processor to execute: 15. When evaluating each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, assessing the value of the insulin delivery algorithm parameter value to be adjusted; generating a signal identifying the insulin delivery algorithm parameter value to be adjusted in response to assessing that the insulin delivery algorithm parameter should be adjusted; 15. A non-transitory computer-readable medium according to any one of embodiments 12 to 14, which causes the processor to execute: 16. evaluating other respective sensor readings received from other respective sensors of said plurality of sensors, particularly in response to the signal; establishing a respective insulin delivery parameter value for each other respective sensor of said plurality of sensors; using said insulin delivery parameter value and all respective insulin delivery parameter values ​​of other respective sensors of said plurality of sensors to generate adaptive parameters that can be used by a drug delivery algorithm, in particular said adaptive parameters can be used by said drug delivery algorithm to recalculate parameter settings of said drug delivery algorithm; 16. A non-transitory computer-readable medium according to any one of embodiments 12 to 15, which causes the processor to execute: 17. calculating an insulin delivery parameter value for each of the plurality of sensors based on a respective sensor reading output received from each of the plurality of sensors; using the insulin delivery parameter value for each of the plurality of sensors to calculate an adaptation parameter; recalculating parameter settings of a drug delivery algorithm based on the adaptive parameters; 17. A non-transitory computer-readable medium according to any one of embodiments 12 to 16, which causes the processor to execute the following: 18. A memory that stores a plurality of sensor baseline readings for each of the plurality of sensors and a drug delivery algorithm; a communication circuit operable to receive a wireless signal; a processor coupled to the memory and the communication circuitry, operable to execute programming instructions, wherein when executing the programming instructions: obtaining sensor readings from one or more of the plurality of sensors; determining, based on the received sensor readings and corresponding baseline sensor readings, that the sensor readings received from one or more of the plurality of sensors indicate that a parameter input to a drug delivery algorithm should be modified; calculating an adaptive parameter based on a sum of the individual insulin delivery parameters generated for each of one or more of the plurality of sensors; a processor operable to modify parameter inputs to the drug delivery algorithm; A wearable drug delivery device comprising: 19. The processor, for each of the received sensor readings: determining a sensor reading difference between each sensor reading and each sensor baseline reading; Utilizing each sensor baseline reading to determine the maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; A wearable drug delivery device as described in embodiment 18, operable to establish an insulin delivery parameter value for each sensor by applying weighting to the calculated preliminary parameter values, such that the insulin delivery parameter value for each sensor is included in the sum. 20. The communication circuit receiving a signal from a sensor external to the body of a user of the wearable device; A wearable drug delivery device as described in embodiment 18 or 19, operable to supply the received signal to the processor, the received signal representing a sensor reading that is not used as a direct input to a drug delivery algorithm executed by the processor.

Claims

1. a plurality of sensors, each configured to generate a respective output related to a state of the user; a memory that stores a plurality of sensor baseline readings for each of the plurality of sensors; A processor operable to execute programming instructions, wherein the processor, when executing the programming instructions, obtaining a respective sensor reading output from each sensor of the plurality of sensors; evaluating each sensor reading and a respective sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings; a processor operable to adjust insulin delivery algorithm parameters based on said evaluation; A system comprising:

2. When the processor evaluates each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, determining a sensor reading difference between each sensor reading and each sensor baseline reading; Utilizing each sensor baseline reading to determine the maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; The system of claim 1 , operable to establish an insulin delivery parameter value for each sensor by applying a weighting to the calculated preliminary parameter values.

3. When the processor evaluates each sensor reading and each sensor baseline reading, assessing the value of the insulin delivery algorithm parameter value to be adjusted; 3. The system of claim 1, further operable to generate a signal identifying the insulin delivery algorithm parameter value to be adjusted in response to an assessment that the insulin delivery algorithm parameter should be adjusted.

4. In particular, in response to the signal, evaluating each other sensor reading received from each other sensor of the plurality of sensors; establishing a respective insulin delivery parameter value for each other respective sensor of said plurality of sensors; A system as described in any one of claims 1 to 3, further operable to use the insulin delivery parameter value and all respective insulin delivery parameter values ​​of other respective sensors of the plurality of sensors to generate adaptive parameters that can be used by a drug delivery algorithm, and in particular the adaptive parameters can be used by the drug delivery algorithm to recalculate parameter settings of the drug delivery algorithm.

5. calculating an insulin delivery parameter value for each of the plurality of sensors based on the respective sensor reading output received from each of the plurality of sensors; using the insulin delivery parameter value for each of the plurality of sensors to calculate an adaptation parameter; The system of any one of claims 1 to 4, further operable to recalculate parameter settings of a drug delivery algorithm based on the adaptive parameters.

6. The system of any one of claims 1 to 5, wherein the memory is further operable to store a drug delivery algorithm and the processor is further operable to execute the drug delivery algorithm.

7. The system of any one of claims 1 to 6, further comprising a wearable drug delivery device having the memory, the processor and communication circuitry, the communication circuitry operable to wirelessly communicate with one or more of the plurality of sensors.

8. 8. The system of claim 1, further comprising a control unit having the memory, the processor and communication circuitry, the communication circuitry operable to wirelessly communicate with one or more of the plurality of sensors.

9. The plurality of sensors configured to detect a state of the user include: The system of any one of claims 1 to 8, comprising at least one of a wearable fitness monitor, a heart rate monitor, an oxygen sensor, a carbohydrate calculator, a pedometer, a meal tracker application, a blood glucose detector, or a ketone detector.

10. One or more of the plurality of sensors A system according to any preceding claim, further comprising a communications circuit operable to transmit sensor readings indicative of respective detected conditions.

11. The system of any one of claims 1 to 9, wherein sensor readings of a majority of the plurality of sensors are not used as direct inputs to a drug or medication delivery algorithm of an AID system.

12. When executed by a processor, obtaining respective sensor readings output from the sensors; evaluating each sensor reading and a respective sensor baseline reading corresponding to each sensor of the plurality of sensor baseline readings; adjusting insulin delivery algorithm parameters based on said evaluation; A non-transitory computer-readable medium having embedded thereon programming instructions that cause the processor to execute the

13. 13. The non-transitory computer-readable medium of claim 12, wherein an output of a sensor reading of each of the plurality of sensors is not used as a direct input to a drug delivery algorithm or a medication delivery algorithm of an AID system.

14. When evaluating each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, determining a sensor reading difference between each sensor reading and each sensor baseline reading; utilizing each sensor baseline reading to determine a maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; establishing an insulin delivery parameter value for each sensor by applying weightings to the calculated preliminary parameter values; The non-transitory computer-readable medium of claim 12 or 13, which causes the processor to execute:

15. When evaluating each sensor reading and each sensor baseline reading corresponding to each sensor of the stored plurality of sensor baseline readings, assessing the value of the insulin delivery algorithm parameter value to be adjusted; generating a signal identifying the insulin delivery algorithm parameter value to be adjusted in response to assessing that the insulin delivery algorithm parameter should be adjusted; The non-transitory computer-readable medium of any one of claims 12 to 14, which causes the processor to execute:

16. evaluating other respective sensor readings received from other respective sensors of said plurality of sensors, particularly in response to the signal; establishing a respective insulin delivery parameter value for each other respective sensor of said plurality of sensors; using said insulin delivery parameter value and all respective insulin delivery parameter values ​​of other respective sensors of said plurality of sensors to generate adaptive parameters that can be used by a drug delivery algorithm, in particular said adaptive parameters can be used by said drug delivery algorithm to recalculate parameter settings of said drug delivery algorithm; The non-transitory computer-readable medium of any one of claims 12 to 15, which causes the processor to execute:

17. calculating an insulin delivery parameter value for each of the plurality of sensors based on a respective sensor reading output received from each of the plurality of sensors; using the insulin delivery parameter value for each of the plurality of sensors to calculate an adaptation parameter; recalculating parameter settings of a drug delivery algorithm based on the adaptive parameters; The non-transitory computer-readable medium of any one of claims 12 to 16, which causes the processor to execute:

18. a memory that stores a plurality of sensor baseline readings for each of the plurality of sensors and a drug delivery algorithm; a communication circuit operable to receive a wireless signal; a processor coupled to the memory and the communication circuitry, operable to execute programming instructions, wherein when executing the programming instructions: obtaining sensor readings from one or more of the plurality of sensors; determining, based on the received sensor readings and corresponding baseline sensor readings, that the sensor readings received from one or more of the plurality of sensors indicate that a parameter input to a drug delivery algorithm should be modified; calculating an adaptive parameter based on a sum of the individual insulin delivery parameters generated for each of one or more of the plurality of sensors; a processor operable to modify parameter inputs to the drug delivery algorithm; A wearable drug delivery device comprising:

19. The processor, for each of the received sensor readings, determining a sensor reading difference between each sensor reading and each sensor baseline reading; Utilizing each sensor baseline reading to determine the maximum set difference; calculating a preliminary parameter value using the determined sensor reading difference and the determined maximum set difference; 20. The wearable drug delivery device of claim 18, operable to establish an insulin delivery parameter value for each sensor by applying a weighting to the calculated preliminary parameter values, such that the insulin delivery parameter value for each sensor is included in the sum.

20. The communication circuit receiving a signal from a sensor external to the body of a user of the wearable device; 20. A wearable drug delivery device as described in claim 18 or 19, operable to provide the received signal to the processor, the received signal representing a sensor reading that is not used as a direct input to a drug delivery algorithm executed by the processor.

Images