Prediction-based delivery or guidance of therapies for diabetes

Abstract

An example system for therapy delivery includes one or more processors configured to: in response to a prediction indicating that a meal event is about to occur, output instructions to an insulin delivery device for delivering a partial therapy dose; output instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose; or output instructions to the insulin delivery device for preparing the partial therapy dose before the meal event occurs; and in response to a determination indicating that the meal event is occurring (e.g., based on movement characteristics of a patient's arm), output instructions to the insulin delivery device for delivering a remaining therapy dose; output instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or output instructions to the insulin delivery device for preparing the remaining therapy dose.

Description

[0001] This application claims priority to U.S. Application No. 17 / 004,951, filed on August 27, 2020, which claims the benefit of U.S. Provisional Application No. 62 / 893,717, filed on August 29, 2019, and U.S. Provisional Application No. 62 / 893,722, filed on August 29, 2019, the entire contents of which are incorporated herein by reference. Technical Field

[0002] The present disclosure relates to medical systems, and more particularly to medical systems for therapy for diabetes. Background Art

[0003] Patients with diabetes receive insulin from a pump or injection device to control the glucose level in his or her blood stream. Due to insufficient insulin production and / or due to insulin resistance, naturally produced insulin may not be able to control the glucose level in the blood stream of a diabetic patient. In order to control glucose levels, the patient's therapy routine may include a basal insulin dose and a bolus insulin dose. Basal insulin is also referred to as background insulin, which tends to keep blood glucose levels at a consistent level during fasting and is a long-acting or intermediate-acting insulin. Bolus insulin can be specifically taken at meal times or other times when relatively rapid changes in glucose levels may occur or near meal times or other times, and therefore can be used as a short-acting or quick-acting form of insulin dosage. Summary of the invention

[0004] Devices, systems and techniques for managing the glucose level of a patient are described. For example, one or more processors (e.g., in one or more servers in a network cloud, in a patient device and / or on a pump for insulin delivery) can determine that a meal event is about to occur or is occurring. In response to the determination that a meal event is about to occur, a patient can take a portion of the insulin to be delivered to the patient before the meal occurs. For example, the one or more processors can output instructions to a pump, indicating that the pump delivers a partial therapy dose (e.g., a portion of insulin) or output instructions to the patient device, indicating that the patient device outputs a notification to the patient to inject a partial therapy dose. The one or more processors can be configured to determine the amount and timing of delivering the partial therapy dose, such as based on past patient behavior. The patient can then take the remaining therapy dose (e.g., the remaining portion of the insulin of the meal) after the meal. By loading at least a portion of the insulin (e.g., pre-dosing before the meal), the chance of an undesirably high glucose level immediately after the meal is reduced. In addition, because the patient takes a portion of the therapy dose of insulin, rather than the entire dose of insulin, the variation of an undesirable low glucose level is also reduced (e.g., when the patient does not eat).

[0005] In one example, the present disclosure describes a system for therapy delivery, the system comprising one or more processors configured to predict that a meal event is about to occur, and in response to the prediction indicating that the meal event is about to occur, perform at least one of the following: (1) output instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs; determine that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; and in response to the determination indicating that the meal event is occurring, perform at least one of the following: (1) output instructions to the insulin delivery device for delivering a remaining therapy dose; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0006] In one example, the present disclosure describes predicting with one or more processors that a meal event is about to occur, and in response to the prediction indicating that the meal event is about to occur, performing with the one or more processors at least one of the following: (1) outputting instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs; determining with the one or more processors that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; and in response to the determination indicating that the meal event is occurring, performing with the one or more processors at least one of the following: (1) outputting instructions to the insulin delivery device for delivering a remaining therapy dose; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0007] In one example, the present disclosure describes a computer-readable storage medium storing instructions that, when executed, cause one or more processors to predict that a meal event is about to occur, and in response to the prediction indicating that the meal event is about to occur, perform at least one of the following: (1) output instructions to the insulin delivery device for delivering a partial therapy dose before the meal event occurs; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs, determine that the meal event is occurring based on one or more movement characteristics of the patient's arm movement, and in response to the determination indicating that the meal event is occurring, perform at least one of the following: (1) output instructions to the insulin delivery device for delivering a remaining therapy dose; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0008] The details of one or more aspects of the disclosure are set forth in the drawings and description below. Other features, objects, and advantages of the disclosure will become apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a block diagram illustrating an example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure.

[0010] Figure 2 is a block diagram illustrating another example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure.

[0011] Figure 3 is a block diagram illustrating another example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure.

[0012] Figure 4 is a block diagram illustrating an example of a patient device according to one or more examples described in the present disclosure.

[0013] Figure 5 is a block diagram illustrating an example of a wearable device according to one or more examples described in the present disclosure.

[0014] Figure 6 is a flowchart illustrating an example method of operation according to one or more examples described in the present disclosure.

[0015] Fig. 7A and 7B is a flowchart illustrating another example method of operation according to one or more examples described in the present disclosure. DETAILED DESCRIPTION

[0016] Devices, systems, and techniques for managing a patient's glucose level are described in the present disclosure. Patients with diabetes may take basal insulin (e.g., slow-acting or intermediate-acting insulin) and supplement the basal insulin with bolus insulin (e.g., rapid-acting or short-acting insulin). For example, a patient may take a therapeutic dose of bolus insulin after, before, or during a meal or some other activity, in which case the patient's glucose level may increase relatively quickly to an undesirable high glucose level, resulting in hyperglycemia. However, taking an excessively large therapeutic dose of bolus insulin may result in an undesirable low glucose level, resulting in hypoglycemia.

[0017] In some cases, the patient may forget to take a bolus insulin dose before, during or after a meal, or may take a bolus insulin dose, but forget that it took a bolus insulin dose, and then accidentally take another bolus insulin dose. The present disclosure describes an example technology that can predetermine whether a patient is to receive insulin therapy and the amount of therapy to be received before a meal event or other activity based on a patient pattern. For example, one or more processors (e.g., one or more servers in a network cloud, in a patient device and / or on a pump for insulin delivery) can utilize artificial intelligence such as a machine learning model to predict that a patient is going to eat. For example, if a patient tends to eat at a fixed time, the one or more processors can determine that the patient is going to eat based on the time of day at least in part. If the patient's location, such as a global positioning system (GPS) location (e.g., based on an output from a patient device) indicates that the patient is close to a restaurant, a cafeteria or other dining location, one or more processors can determine that the patient is going to eat based on the location.

[0018] Based on the determination that a meal event is about to occur, the one or more processors may output instructions to an insulin delivery device (e.g., a pump or injection device) for causing the insulin delivery device to automatically deliver a partial therapy dose before a meal event, or output an alarm (e.g., instructions) to the device for notifying the patient to use an insulin delivery device (e.g., a pump or injection device) to take the partial therapy dose before a meal even occurs. As described below, the device may be a device including the one or more processors. If the patient is about to take an X amount of bolus insulin associated with a meal event, the partial therapy dose may be an amount of Y of the bolus insulin, where Y is less than X.

[0019] By delivering or pre-administering insulin before a meal, the chance of postprandial high glucose levels (i.e., high glucose levels after a meal) can be reduced. The example range of the time period before a meal includes 5 minutes, 10 minutes, 15 minutes, 20 minutes, 25 minutes, or 30 minutes. However, other ranges are also possible. In some instances, the amount of time before a meal can be determined based on the type of meal that the patient is predicted to eat. For example, if the patient is predicted to eat a meal with a relatively high amount of carbohydrate, the amount of time before a meal for a partial therapy dose of insulin received by the patient may be different from the amount of meal time for a relatively low amount of carbohydrate that the patient is predicted to eat.

[0020] Furthermore, by delivering a partial therapy dose, rather than an entire therapy dose, the chance of adverse effects such as hypoglycemia occurring if the patient does not eat is reduced. In some examples, the one or more processors may confirm that the patient consumed a meal and deliver the remainder of the therapy dose in response.

[0021] There are multiple ways to enable an insulin delivery device to deliver a partial therapy dose prior to a meal event. As an example, the one or more processors can specify the amount of bolus insulin to be delivered to the insulin delivery device, and in response, the insulin delivery device can deliver the specified amount of insulin. In some cases, the specified amount of insulin can be a specific fixed bolus unit, and the one or more processors can specify the unit of bolus insulin to be delivered. As another example, the one or more processors can specify a glucose level to the insulin delivery device, and in response, the insulin delivery device can deliver insulin determined to be sufficient to bring the patient to the specified glucose level.

[0022] In one or more instances, one or more processors may determine that a meal event is occurring. For example, one or more processors of a wearable device (e.g., a smartwatch) may detect one or more movement characteristics associated with the movement of a patient's hand, such as values ​​associated with the instantaneous or time-lapse frequency, magnitude, trajectory, location, speed, acceleration, and / or pattern of the movement. The frequency of the patient's arm movement may refer to how many times the patient repeats the movement within a certain period of time (e.g., the frequency of moving back and forth between two locations). The one or more processors may receive information about one or more movement characteristics of the patient's hand and determine based on the received information that the patient is eating (e.g., the frequency and manner of the patient's hand movement are consistent with the frequency and manner of movement of the person who is eating). In response to the determination indicating that the meal event is occurring, the one or more processors may perform at least one of the following: outputting instructions for delivering the remaining therapy dose to an insulin delivery device, outputting instructions for delivering the recommended therapy dose to at least one of the therapy delivery devices in the therapy delivery device, or outputting instructions to the device for notifying the patient to use an insulin delivery device to ingest the remaining therapy dose. For example, if the patient is to take X amount of bolus insulin, and the partial therapy dose is Y amount of bolus insulin, then the remaining therapy dose (Z) is the difference between X and Y (ie, Z=X-Y). In some instances, Z is greater than Y.

[0023] Figure 1 is a block diagram illustrating an example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure. Figure 1A system 10A is shown that includes a patient 12, an insulin pump 14, tubing 16, an infusion set 18, a sensor 20 (e.g., a glucose sensor), a wearable device 22, a patient device 24, and a cloud 26. Cloud 26 represents a local wide area computing network or a global computing network that includes one or more processors 28A-28N ("one or more processors 28"). In some examples, the various components can determine a change in therapy based on a determination of the glucose level of sensor 20, and thus system 10A can be referred to as a continuous glucose monitoring (CGM) system 10A.

[0024] Patient 12 may have diabetes (e.g., type 1 diabetes or type 2 diabetes), and therefore, the glucose levels of patient 12 may not be controlled without the delivery of supplemental insulin. For example, patient 12 may not produce enough insulin to control glucose levels, or the amount of insulin produced by patient 12 may be insufficient due to insulin resistance that patient 12 may have developed.

[0025] In order to receive supplemental insulin, the patient 12 can carry an insulin pump 14 connected to a pipeline 16 for delivering insulin to the patient 12. An infusion set 18 can be connected to the skin of the patient 12 and include a cannula for delivering insulin to the patient 12. A sensor 20 can also be coupled to the patient 12 to measure the glucose level of the patient 12. The insulin pump 14, pipeline 16, infusion set 18 and sensor 20 can form an insulin pump system together. An example of an insulin pump system is the MINIMEDTM 670G insulin pump system of Medtronic, Inc. However, other examples of insulin pump systems can be used, and the example techniques should not be considered to be limited to the MINIMEDTM 670G insulin pump system. For example, the technology described in the present disclosure can be used for an insulin pump system comprising wireless communication capabilities. However, the example techniques should not be considered to be limited to insulin pump systems with wireless communication capabilities, and other types of communications such as wired communications are also possible. In another example, the insulin pump 14, pipeline 16, infusion set 18 and / or sensor 20 can be contained in the same housing.

[0026] The insulin pump 14 can be a relatively small device that the patient 12 can place in different locations. For example, the patient 12 can clip the insulin pump 14 to the waistband of pants worn by the patient 12. In some instances, the patient 12 can place the insulin pump 14 in a pocket for the sake of discretion. In general, the insulin pump 14 can be worn in different places, and the patient 12 can place the insulin pump 14 in a certain location based on the specific clothing that the patient 12 is wearing.

[0027] To deliver insulin, the insulin pump 14 includes one or more reservoirs (e.g., two reservoirs). The reservoir can be a plastic cartridge that holds up to N units of insulin (e.g., up to 300 units of insulin) and locks into the insulin pump 14. The insulin pump 14 can be a battery-powered device powered by replaceable and / or rechargeable batteries.

[0028] Tubing 16, sometimes referred to as a catheter, is connected on a first end to a reservoir in insulin pump 14 and on a second end to infusion set 18. Tubing 16 may carry insulin from the reservoir of insulin pump 14 to patient 12. Tubing 16 may be flexible, allowing looping or bending to minimize concerns about tubing 16 becoming separated from insulin pump 14 or infusion set 18 or about tubing 16 breaking.

[0029] Infusion set 18 can include a thin cannula that patient 12 inserts into the fat layer under the skin (e.g., subcutaneous connection). Infusion set 18 can rest near the stomach of patient 12. Insulin travels from the reservoir of insulin pump 14 through tubing 16, through the cannula in infusion set 18, and into the body of patient 12. In some examples, patient 12 can use an infusion set insertion device. Patient 12 can place infusion set 18 into the infusion set insertion device, and with the button on the infusion set insertion device pressed, the infusion set insertion device can insert the cannula of infusion set 18 into the fat layer of patient 12, and with the cannula inserted into the fat layer of patient 12, infusion set 18 can rest on top of the patient's skin.

[0030] Sensor 20 may include a sensor inserted under the skin of patient 12, such as near the stomach of patient 12 or in the arm of patient 12 (e.g., attached subcutaneously). The sensor of sensor 20 may be configured to measure interstitial glucose levels, which are glucose present in the fluid between the cells of patient 12. Sensor 20 may be configured to continuously or periodically sample glucose levels and the rate of change of glucose levels over time.

[0031] In one or more embodiments, the insulin pump 14 and the sensor 20 and Figure 1The various components shown in can form a closed-loop therapy delivery system together. For example, patient 12 can set a target glucose level on insulin pump 14, which is usually measured in mg / dl. Insulin pump 14 can receive current glucose level from sensor 20, and in response, can increase or decrease the amount of insulin delivered to patient 12. For example, if the current glucose level is higher than the target glucose level, insulin pump 14 can increase insulin. If the current glucose level is lower than the target glucose level, insulin pump 14 can temporarily stop delivering insulin. Insulin pump 14 can be considered as an example of automatic insulin delivery (AID) device. Other examples of AID devices are also possible, and the technology described in the present disclosure can be applicable to other AID devices.

[0032] For example, insulin pump 14 and sensor 20 can be configured to operate together to simulate some of the ways in which a healthy pancreas works. Insulin pump 14 can be configured to deliver basal insulin, which is a small amount of insulin released continuously throughout the day. Sometimes glucose levels can rise, such as due to some other activities carried out by eating or patient 12. Insulin pump 14 can be configured to deliver bolus insulin or correct undesirable high glucose levels in blood flow as required in association with food intake. In one or more instances, if glucose levels rise to more than the target level, insulin pump 14 can increase bolus insulin to solve the rising of glucose levels. Insulin pump 14 can be configured to calculate basal insulin delivery and bolus insulin delivery, and deliver basal insulin and bolus insulin accordingly. For example, insulin pump 14 can determine the amount of basal insulin to be delivered continuously, and then determine the amount of bolus insulin to be delivered to reduce glucose levels in response to the rising of glucose levels caused by eating or some other events.

[0033] Therefore, in some instances, the sensor 20 can sample the glucose level and the rate of change of the glucose level over time. The sensor 20 can output the glucose level to the insulin pump 14 (e.g., connected by a wireless link such as Bluetooth or BLE). The insulin pump 14 can compare the glucose level with the target glucose level (e.g., set by the patient 12 or a clinician), and adjust the insulin dose based on the comparison. In some instances, the sensor 20 can also output a predicted glucose level (e.g., where the expected glucose level will be in the next 30 minutes), and the insulin pump 14 can adjust insulin delivery based on the predicted glucose level.

[0034] As described above, the patient 12 or clinician can set a target glucose level on the insulin pump 14. The patient 12 or clinician can set a target glucose level on the insulin pump 14 in a variety of ways. As an example, the patient 12 or clinician can communicate with the insulin pump 14 using a patient device 24. Examples of patient devices 24 include mobile devices such as smartphones or tablet computers, laptop computers, etc. In some examples, the patient device 24 can be a special programmer or controller for the insulin pump 14. Although Figure 1 One patient device 24 is shown, but in some examples, there may be multiple patient devices. For example, the system 10A may include a mobile device and a controller, each of which is an example of the patient device 24. For ease of description only, the example technology is described with respect to the patient device 24, and it should be understood that the patient device 24 may be one or more patient devices.

[0035] Patient device 24 may also be configured to interface with sensor 20. As one example, patient device 24 may receive information from sensor 20 via insulin pump 14, where insulin pump 14 relays information between patient device 24 and sensor 20. As another example, patient device 24 may receive information (e.g., glucose level or rate of change of glucose level) directly from sensor 20 (e.g., via a wireless link).

[0036] In one or more instances, the patient device 24 can display a user interface that the patient 12 or clinician can use to control the insulin pump 14. For example, the patient device 24 can display a screen that allows the patient 12 or clinician to enter a target glucose level. As another example, the patient device 24 can display a screen that outputs current and / or past glucose levels. In some instances, the patient device 24 can output notifications to the patient 12, such as notifications that the glucose level is too high or too low and notifications of any actions that the patient 12 needs to take. As another example, if the battery of the insulin pump 14 is low, the insulin pump 14 can output a low battery indication to the patient device 24, and the patient device 24 can then output a notification to the patient 12 to replace the battery or charge the battery.

[0037] Controlling the insulin pump 14 through the patient device 24 is an example and should not be considered limiting. For example, the insulin pump 14 may include a user interface (e.g., a button) that allows the patient 12 or a clinician to set various glucose levels of the insulin pump 14. Moreover, in some examples, the insulin pump 14 itself or as a supplement to the patient device 24 can be configured to output notifications to the patient 12. For example, if the glucose level is too high or too low, the insulin pump 14 can output an auditory or tactile output. As another example, if the battery is low, the insulin pump 14 can output a low battery indication on the display of the insulin pump 14.

[0038] The foregoing describes example ways in which insulin pump 14 may deliver insulin to patient 12 based on current glucose levels (e.g., as measured by sensor 20). In some cases, a therapeutic gain may result by proactively delivering insulin to patient 12, rather than reacting when glucose levels become too high or too low.

[0039] The glucose level of patient 12 may increase due to a particular user action. As an example, the glucose level of patient 12 may increase due to patient 12 eating. In some examples, there may be a therapeutic benefit if it can be determined that patient 12 is eating and insulin is delivered based on the determination that patient 12 is eating.

[0040] For example, the patient 12 may forget to make the insulin pump 14 deliver insulin after eating, resulting in insufficient insulin. Alternatively, the patient 12 may make the insulin pump 14 deliver insulin after eating, but it may have forgotten that the insulin pump 14 has previously delivered insulin for the same meal event patient 12, resulting in excessive insulin dosage. Moreover, in the example using the sensor 20, the insulin pump 14 may not take any action until the glucose level is greater than the target level. By actively determining that the patient 12 is eating, the insulin pump 14 can deliver insulin in a manner that makes the glucose level not rise to more than the target level or only rise to slightly higher than the target level (that is, compared with the degree to which the glucose level would rise when not actively delivering insulin, rising less). In some cases, by actively determining that the patient 12 is eating and delivering insulin accordingly, the glucose level of the patient 12 can be increased more slowly.

[0041] Although the above describes actively determining that the patient 12 is eating and delivering insulin accordingly, the example technology is not limited thereto. The example technology can be used to actively determine the activities that the patient 12 is performing (e.g., eating, exercising, sleeping, driving, etc.). The insulin pump 14 can then deliver insulin based on the determination of the type of activity that the patient 12 is performing.

[0042] like Figure 1 As shown in , patient 12 can wear wearable device 22. Examples of wearable device 22 include smart watches or fitness trackers, in some examples, any of which can be configured to be worn on the patient's wrist or arm. In one or more examples, wearable device 22A includes an inertial measurement unit, such as a six-axis inertial measurement unit. The six-axis inertial measurement unit can couple a 3-axis accelerometer with a 3-axis gyroscope. The accelerometer measures linear acceleration, while the gyroscope measures rotational motion. Wearable device 22A can be configured to determine one or more movement characteristics of patient 12. Examples of one or more movement characteristics include values ​​related to the instantaneous or time-dependent frequency, amplitude, trajectory, location, speed, acceleration, and / or pattern of movement. The frequency of the patient's arm movement can refer to how many times the patient 12 repeats the movement within a certain period of time (e.g., the frequency of moving back and forth between two locations).

[0043] Patient 12 may wear wearable device 22 on his or her wrist. However, the example technology is not limited thereto. Patient 12 may wear wearable device 22 on a finger, forearm, or bicep. In general, patient 12 may wear wearable device 22 anywhere that can be used to determine a gesture indicating eating, such as movement characteristics of an arm.

[0044] The way that the patient 12 moves his or her arm (i.e., movement characteristics) can refer to the direction, angle, and orientation of the patient's 12 arm movement, including values ​​related to the frequency, magnitude, trajectory, location, speed, acceleration, and / or pattern of the movement, either instantaneously or over time. As an example, if the patient 12 is eating, the patient's 12 arm will be oriented in a particular way (e.g., the thumb faces the patient's 12 body), the angle of the arm movement will be approximately 90 degrees (e.g., starting from the dinner plate to the mouth), and the direction of the arm movement will be in accordance with the path from the dinner plate to the mouth. The forward / backward, up / down, pitch, roll, yaw measurements from the wearable device 22A can indicate the way the patient 12 moves his or her arm. Moreover, the patient 12 may have a certain frequency at which the patient 12 moves his or her arm or a pattern at which the patient 12 moves his or her arm, which is more indicative of eating than other activities such as smoking or e-cigarettes, in which the patient 12 may raise his or her arm to his or her mouth.

[0045] Although the above description describes the wearable device 22 as being used to determine whether the patient 12 is eating, the wearable device 22 can be configured to detect movement of the patient 12's arm (e.g., one or more movement characteristics), and the movement characteristics can be used to determine the activity performed by the patient 12. For example, the movement characteristics detected by the wearable device 22 can indicate whether the patient 12 is exercising, driving, sleeping, etc. As another example, the wearable device 22 can indicate the posture of the patient 12, which can be consistent with the posture of exercising, driving, sleeping, eating, etc. Another term for movement characteristics can be gesture movement. Therefore, the wearable device 22 can be configured to detect gesture movement (i.e., movement characteristics of the patient 12's arm) and / or posture, where the gesture and / or posture can be part of various activities (e.g., eating, exercising, driving, sleeping, etc.).

[0046] In some examples, wearable device 22 may be configured to determine a particular activity that patient 12 is performing based on detected gestures (e.g., movement characteristics of patient 12's arm) and / or postures. For example, wearable device 22 may be configured to determine whether patient 12 is eating, exercising, driving, sleeping, etc. In some examples, wearable device 22 may output information indicating movement characteristics of patient 12's arm and / or patient 12's posture to patient device 24, and patient device 24 may be configured to determine the activity that patient 12 is performing.

[0047] Wearable device 22 and / or patient device 24 may be programmed with information that wearable device 22 and / or patient device 24 uses to determine that patient 12 is performing a particular activity. For example, patient 12 may perform various activities throughout the day, where the movement characteristics of patient 12's arms may be similar to the movement characteristics of patient 12's arms for a particular activity, but patient 12 is not performing the activity. As an example, the movement of patient 12 yawning and cupping his or her mouth may be similar to the movement of patient 12 eating. The movement of patient 12 picking up groceries may be similar to the movement of patient 12 exercising. Likewise, in some instances, patient 12 may be performing a particular activity, but wearable device 22 and / or patient device 24 may not determine that patient 12 is performing the particular activity.

[0048] Thus, in one or more instances, the wearable device 22 and / or the patient device 24 may “learn” to determine whether the patient 12 is performing a particular activity. However, the computing resources of the wearable device 22 and the patient device 24 may not be sufficient to perform the learning required to determine whether the patient 12 is performing a particular activity. The computing resources of the wearable device 26 and the patient device 24 may be sufficient to perform the learning, but for ease of description only, the following description is made with respect to one or more processors 28 in the cloud 26.

[0049] like Figure 1 As shown in , system 10A includes a cloud 26, which includes one or more processors 28. For example, cloud 26 includes multiple network devices (e.g., servers), and each of the multiple devices includes one or more processors. One or more processors 28 can be processors of multiple network devices, and can be located in a single network device in the network device, or can be distributed across two or more network devices in the network device. Cloud 26 represents a cloud infrastructure that supports one or more processors 28 on which applications or operations requested by one or more users run. For example, cloud 26 provides cloud computing to use one or more processors 28 instead of storing, managing and processing data on the network device through patient device 24 or wearable device 22. One or more processors 28 can share data or resources for performing calculations, and can be part of a computing server, a network server, a database server, etc. One or more processors 28 can be in a network device (e.g., a server) in a data center, or can be distributed across multiple data centers. In some cases, the data center can be in different geographical locations.

[0050] The one or more processors 28 and other processing circuit systems described herein may include any one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuit systems, and any combination of such components. The functions attributed to the one or more processors 28 and other processing circuit systems described herein may be embodied herein as hardware, firmware, software, or any combination thereof.

[0051] One or more processors 28 may be implemented as fixed function circuits, programmable circuits, or a combination thereof. Fixed function circuits refer to circuits that provide specific functions and are pre-set on the operations that can be performed. Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functions in the operations that can be performed. For example, a programmable circuit can execute software or firmware that enables the programmable circuit to operate in a manner defined by the instructions of the software or firmware. Fixed function circuits can execute software instructions (e.g., to receive parameters or output parameters), but the type of operation performed by the fixed function circuit is generally immutable. In some instances, one or more of the units may be different circuit blocks (fixed function or programmable), and in some instances, the one or more units may be integrated circuits. One or more processors 28 may include an arithmetic logic unit (ALU), an elementary function unit (EFU), a digital circuit, an analog circuit, and / or a programmable core formed by a programmable circuit. In an instance where software executed by a programmable circuit is used to perform the operation of one or more processors 28, a memory accessible to one or more processors 28 (e.g., on a server) may store the object code of the software received and executed by one or more processors 28.

[0052] In some instances, one or more processors 28 may be configured to determine patterns based on gesture movements (e.g., one or more movement characteristics determined by wearable device 22) and to determine specific activities being performed by patient 12. One or more processors 28 may provide a real-time response cloud service that can determine the activity being performed by patient 12 on a real-time response basis, and in some instances, provide a recommended therapy (e.g., the amount of an insulin dose). Cloud 26 and patient device 24 may communicate via Wi-Fi or via a bearer network.

[0053] For example, as described above, in some instances, the wearable device 22 and / or the patient device 24 may be configured to determine that the patient 12 is performing an activity. However, in some instances, the patient device 24 may output information indicating movement characteristics of the patient 12's arm movements to the cloud 26, and may have other contextual information, such as location or time of day. The one or more processors 28 of the cloud 26 may then determine the activity that the patient 12 is performing. The insulin pump 14 may then deliver insulin based on the determined activity of the patient 12.

[0054] One example in which the one or more processors 28 may be configured to determine that the patient 12 is performing an activity and determine the therapy to be delivered is described in U.S. Patent Publication No. 2020 / 0135320A1. In general, the one or more processors 28 may first undergo an initial "learning" phase in which the one or more processors 28 receive information used to determine the behavior patterns of the patient 12. Some of this information may be provided by the patient 12. For example, the patient 12 may be prompted or the patient himself / herself may input information into the patient device 24 indicating that the patient 12 is performing a particular activity, the duration of the activity, and other such information that the one or more processors 28 may use to predict the behavior of the patient 12. After the initial learning phase, the one or more processors 28 may still update the behavior patterns based on recently received information, but less information from the patient 12 or no information from the patient is required.

[0055] During the initial learning phase, the patient 12 may provide information about the dominant hand of the patient 12 (e.g., right or left hand) and where the patient 12 wears the wearable device 22 (e.g., around the wrist of the right hand or the left hand). The patient 12 may be instructed to wear the wearable device 22 on the wrist of the hand that the patient 12 uses for eating. The patient 12 may also provide information about the orientation of the wearable device 22 (e.g., whether the face of the wearable device 22 is at the top of the wrist or the bottom of the wrist).

[0056] During the initial learning phase, the patient 12 may actively or in response to a prompt / question input information indicating that the patient 12 is consuming a meal (e.g., via the patient device 24). During this period, the wearable device 22 may continue to determine one or more movement characteristics (e.g., gestures) and / or postures of the patient 12 and output such information to the patient device 24, which relays the information to the one or more processors 28. The one or more processors 28 may store information about one or more movement characteristics of the patient 12's arm movements during eating to later determine whether the patient 12 is eating (e.g., whether the received information about the manner and frequency of the patient 12's arm movements is consistent with the stored information about the manner and frequency of the patient 12's arm movements when it is known that the patient 12 is eating).

[0057] Arm movement is described above as a factor in determining whether the patient 12 is eating. However, there may be various other factors that can be used alone or in combination with arm movement to determine whether the patient 12 is eating. As an example, the patient 12 can eat at fixed time intervals. As another example, the patient 12 can eat at certain locations. In the initial learning phase, when the patient 12 enters that he or she is eating (e.g., through the patient device 24), the patient device 24 can output information about the time of day and the location of the patient 12. For example, the patient device 24 can be equipped with a positioning device, such as a global positioning system (GPS) unit, and the patient device 24 can output location information determined by the GPS unit. There may be other ways to determine the location, such as based on a Wi-Fi connection and / or access to 4G / 5G LTE, or some other form of access, such as tracking the device location based on a telecommunications database of the patient device 24. The time of day and location are two examples of contextual information that can be used to determine whether the patient 12 is eating.

[0058] However, there may be other examples of contextual information of patient 12, such as sleep patterns, body temperature, stress level (e.g., based on pulse and respiration), heart rate, etc. In general, there may be various biometric sensors (e.g., for measuring temperature, pulse / heart rate, respiration rate, etc.), which may be part of wearable device 22 or may be separate sensors. In some examples, the biometric sensor may be part of sensor 20.

[0059] The contextual information of patient 12 may include conditional information. For example, patient 12 may eat once every 3 hours, but the exact time when patient 12 eats may be different. In some examples, the conditional information may be to determine whether patient 12 has eaten and whether a certain amount of time (e.g., 3 hours) has passed since patient 12 ate. In general, any information that establishes a behavioral pattern may be used to determine whether patient 12 is eating.

[0060] One or more processors 28 can utilize artificial intelligence such as machine learning or other data analysis techniques to determine whether the patient 12 is eating based on information determined and / or collected by the wearable device 22 and the patient device 24. As an example, during the initial learning phase, the one or more processors 28 can utilize neural network technology. For example, the one or more processors 28 can receive training data from the patient 12 for training the classifier module executed on the one or more processors 28. As described above, when the patient device 24 and / or the wearable device 22 determine that the patient 12 is eating based on the manner and frequency of the patient's 12 arm movements (e.g., gestures consistent with arm movements when eating), the one or more processors 28 can receive the training data based on the patient's confirmation. One or more processors 28 can generate and store labeled data records, which contain characteristics related to movement and other contextual characteristics such as time of day or location. One or more processors 28 can train a classifier on a labeled data set containing multiple labeled data records, and one or more processors 28 can use the trained classifier model to more accurately detect the start of a food intake event.

[0061] Other examples that can be used for neural networks include behavioral patterns. For example, patient 12 may only eat certain foods after exercise, and always eat the certain foods after exercise. Patient 12 may eat at certain times and / or places. There may be various conditions that together indicate a behavioral pattern for patient 12.

[0062] As another example, one or more processors 28 can utilize k-means clustering technology to determine whether patient 12 is eating. For example, during the initial learning phase, one or more processors 28 can receive different types of context information and form clusters, wherein each cluster represents the behavior of patient 12 (e.g., eating, sleeping, walking, exercise, etc.). For example, patient 12 can input information indicating that he or she is walking (e.g., inputting the information into patient device 24). One or more processors 28 can utilize all context information received when patient 12 is walking to form a first cluster associated with walking. Patient 12 can input information indicating that he or she is eating (e.g., inputting into patient device 24). One or more processors 28 can utilize all context information received when patient 12 is eating to form a second cluster associated with eating, and so on. Then, based on the received context information, one or more processors 28 can determine which cluster is aligned with the context information, and determine the ongoing activities of patient 12. As described in more detail, the type of activity and the prediction of when the activity will occur can be used to determine when to deliver insulin therapy. There may be other instances of machine learning, and the example techniques are not limited to any particular machine learning technique.

[0063] There may be various other ways in which one or more processors 28 may determine the activity that patient 12 is performing. This disclosure provides some example techniques for determining the activity that patient 12 is performing, but the example techniques should not be considered limiting.

[0064] During the initial learning phase, the patient 12 may also input information about activities that the patient 12 is performing. For example, in the case of eating, the patient 12 may input information indicating what the patient 12 is eating and / or how many carbohydrates are in the food that the patient 12 is eating. As an example, at 9:00 a.m. each morning, the patient 12 may input that he or she is eating a bagel or that the patient 12 is consuming 48 grams of carbohydrates.

[0065] In some instances, the one or more processors 28 can be configured to determine the amount of insulin delivered to the patient 12 (e.g., a therapeutic dose of bolus insulin). As an example, a memory accessible to the one or more processors 28 can store patient parameters (e.g., weight, height, etc.) of the patient 12. The memory can also store a query table indicating the amount of bolus insulin to be delivered for different patient parameters and different types of food. The one or more processors 28 can access the memory and can determine the amount of bolus insulin to be received by the patient 12 based on the type of food that the patient 12 is eating and the patient parameters.

[0066] Thus, in one or more instances, the one or more processors 28 may utilize information regarding movement characteristics of arm movements, eating speed, amount of food consumed, food content, etc., while also tracking other contextual information. Examples of contextual information include location information, time of day, wake-up time, amount of time since last eating, calendar events, information regarding people that the patient 12 may be meeting, etc. The one or more processors 28 may identify patterns and correlations between all of these various factors to determine that the patient 12 is performing an activity, such as eating.

[0067] After the initial learning phase, one or more processors 28 can automatically and with minimal input from the patient 12 determine that the patient 12 is performing a specific activity, such as eating, and determine the amount of bolus insulin to be delivered based on the determination. One or more processors 28 can output a recommendation for the amount of bolus insulin to be delivered to the patient device 24. The patient device 24 can then control the insulin pump 14 to deliver the determined amount of insulin. As an example, the patient device 24 can output the bolus insulin amount to be delivered to the insulin pump 14 with or without user confirmation. As another example, the patient device 24 can output a target glucose level, and the insulin pump 14 can deliver insulin to achieve the target glucose level. In some instances, one or more processors 28 can output information indicating the target glucose level to the patient device 24, and the patient device 24 can output the information to the insulin pump 16. All of these examples can be considered as examples of one or more processors 28 determining the amount of insulin to be delivered to the patient 12.

[0068] Described above are example ways to determine whether patient 12 is engaging in activity, determine the amount of insulin to be delivered, and cause the amount of insulin to be delivered. Example techniques may require little to no intervention from patient 12. In this way, the likelihood that patient 12 will receive the correct dose of insulin at the correct time is increased, and the likelihood of human error causing problems (e.g., patient 12 forgets to log a meal, forgets to use insulin, or uses insulin but forgets that it has been used) is reduced.

[0069] While the above example techniques may be beneficial for patients 12 who receive insulin at the right time, the present disclosure describes example techniques for further proactively delivering insulin to patients 12. As described above, patients 12 may experience an increase in glucose levels after a meal, which is referred to as a postprandial (i.e., post-meal) glucose level. As an example, the present disclosure describes example techniques that may further limit the increase in postprandial glucose levels, but the example techniques are also applicable to other times when glucose levels may change.

[0070] In one or more instances, using the above techniques, instead of determining when the patient 12 eats, one or more processors 28 can be configured to determine (e.g., predict) that the patient 12 is going to eat (e.g., that a meal event is going to occur). For example, one or more processors 28 can utilize contextual information, such as time of day, location, sleep patterns, etc., and based on the behavioral patterns of the patient 12, determine (e.g., predict) that a meal event is going to occur before the meal event actually occurs. One or more processors 28 can also determine the type of food and / or amount of carbohydrates that the patient 12 will consume during the meal event. For example, as described above, the patient 12 may consume 48 grams of carbohydrates as part of breakfast at 9:00 am every day. Based on the behavioral patterns, time of day, and location, one or more processors can determine that the patient 12 will consume 48 grams of carbohydrates at 9:00 am.

[0071] According to one or more example techniques described in the present disclosure, one or more processors 28 may determine that a meal event is about to occur. One or more processors 28 may receive contextual information that one or more processors 28 use to determine that a meal event is about to occur. As an example, one or more processors 28 may receive information indicating at least one of a time of day or a location of patient 12, and determine that a meal event is about to occur based on the received information.

[0072] In response to the determination indicating that a meal event is about to occur, the one or more processors 28 may output instructions to the insulin pump 14 (e.g., via the patient device 24) for delivering a portion of the therapy dose prior to the meal event. For example, the one or more processors 28 may determine the amount of bolus insulin that the patient 12 is to receive, as described above (e.g., based on patient behavior and patterns). The one or more processors 28 may determine a portion of the bolus insulin amount that the patient 12 is to receive, and the insulin pump 14 may deliver the determined portion.

[0073] In one or more instances, before a meal event can be a time before the movement characteristics indicate that the patient 12 is eating. That is, one or more movement characteristics of the patient 12 may not indicate that the patient 12 is eating or starting to eat. However, other contextual information such as the time of day and location can indicate that the patient 12 is about to eat. One or more processors 28 can be configured to output instructions to the insulin pump 14 for delivering a partial therapy dose before the movement characteristics of the patient 12 indicate that the patient 12 is eating or just starting to eat. The amount of time before the meal event when the one or more processors 28 output instructions to the insulin pump 14 can be immediately before the meal starts, 1 hour before the predicted meal starts to immediately start the meal, 1 hour before the predicted meal starts to 30 minutes, 30 minutes to the predicted meal starts before, and preferably 15 minutes to the predicted meal starts before, such as 30 minutes to 15 minutes before the predicted meal starts, or less than 15 minutes before the predicted meal starts.

[0074] Generally speaking, the patient 12 may receive a partial therapy dose about 15 minutes before a meal. This is generally beneficial for a balanced meal of carbohydrates, protein, and fat. If the patient 12 is predicted to consume a high-fat meal, the patient 12 may receive a partial therapy dose closer to the meal event and the remainder of the therapy dose an hour or so later. However, for very fast-acting carbohydrates, such as apple juice, the patient 12 may receive a partial therapy dose more than 15 minutes before a meal and still reduce postprandial glucose levels.

[0075] Thus, in one or more instances, the type of meal that is predicted to be consumed by the patient 12 may affect when the patient 12 receives a partial therapy dose. For example, if the patient 12 is predicted to eat a meal that is balanced in carbohydrates, proteins, and fats, the patient 12 may receive a partial therapy dose at least a first time period (e.g., 15 minutes) before the meal. If the patient 12 is predicted to eat a meal that is high in fat or protein and low in carbohydrates, the patient 12 may receive a partial therapy dose at a second time period before the meal that is shorter than the first time period (e.g., about 5 minutes or less). If the patient 12 is predicted to eat a high-carbohydrate meal that is low in fat or protein, the patient 12 may receive a partial therapy dose more than the first time period (e.g., 15 minutes) before the meal. In general, delivering a partial therapy dose before a meal can reduce postprandial glucose levels regardless of the carbohydrate, fat, and protein content of the meal.

[0076] For example, one or more processors 28 may determine that patient 12 is consuming a meal or is about to consume a meal (e.g., a meal event is occurring or a meal event is about to occur), and then determine recommendations for optimal timing, dosage, and / or settings of insulin for patient 12 based on historical trends (e.g., patient behavior and patterns) and / or based on a physiological model in order to optimize glucose control for patient 12. For example, one or more processors 28 may determine the amount of a partial therapy dose and the time to take the partial therapy dose based on a physiological model.

[0077] One example of a physiological model is a "digital twin." One or more processors 28 may be configured to utilize a "digital twin" of patient 12 to determine the amount of bolus insulin for patient 12 to receive. The digital twin may be a digital replica or model of patient 12. The digital twin may be software executed on one or more processors 28. The digital twin may receive as input information about what patient 12 has eaten. Because the digital twin is a digital replica of patient 12, the output from the digital twin may be information about what patient 12's glucose levels may be after eating and a recommendation on how much bolus insulin to deliver to patient 12 to control elevated glucose levels.

[0078] For example, the digital twin may indicate what the correct dosage should have been for a meal that patient 12 has consumed in the past. In one or more instances, patient 12 may input information indicating the food that patient 12 consumed, and one or more processors 28 may receive information about glucose levels. Using the information indicating the food that patient 12 consumed and the glucose levels, one or more processors 28 may use the digital twin to determine what the insulin dosage should have been (e.g., based on how the digital twin models how the food will affect the patient's glucose levels). Then, at a subsequent time when patient 12 is predicted to consume the same meal, one or more processors 28 may determine what the insulin dosage should be based on the insulin dosage that the digital twin has previously determined.

[0079] In this example, the determined portion of the amount of bolus insulin is a partial therapy dose that the insulin pump 14 can deliver before a meal event (e.g., before eating). For example, the partial therapy dose can be in the range of 1% to 5%, 1% to 9%, 10% to 19%, 20% to 29%, 30% to 39%, or 40% to 50%. The partial therapy dose may exceed 50% of the amount of bolus insulin delivered for a given meal event, but in some instances, the partial therapy dose is less than 50% of the amount of insulin to be delivered. For example, if X grams of bolus insulin is delivered to the patient 12 based on the amount of carbohydrates that the patient 12 will consume in a meal event (e.g., as determined by one or more processors 28), the insulin pump 14 can deliver Y grams of bolus insulin, where Y is less than 0.5*X.

[0080] In some examples, the value of Y may be based on the amount of carbohydrates, protein, and / or fat predicted to be present in the meal. For example, if it is predicted based on the patient's behavior pattern that patient 12 will eat a high-fat meal, the value of Y may be less than if it is predicted based on the patient's behavior pattern that patient 12 will eat a high-carbohydrate meal that is low in fat, protein, or fiber (e.g., a fast-carbohydrate meal such as juice).

[0081] In some instances, the value of Y can be a fixed value regardless of the carbohydrate content of the meal. The value of Y can be based on the patient's age and weight. In instances where the value of Y is fixed, the risk of hypoglycemia can be reduced if the prediction of the amount of carbohydrates, fat, protein, or fiber in the meal is incorrect.

[0082] By delivering a partial therapy dose, the post-meal glucose level may not increase as much or may increase more slowly, so that the glucose level of patient 12 does not spike due to meal consumption. Also, because insulin pump 14 may deliver a partial therapy dose instead of a full amount of the therapy dose, in situations where patient 12 does not consume food (e.g., there is no meal event), the glucose level of patient 12 may not drop as low, and the chance of patient 12 experiencing the effects of low glucose levels may be minimized.

[0083] In some examples, the one or more processors 28 may cause the patient device 24 and / or the wearable device 22 to output a notification confirming whether the patient 12 is about to eat. If the patient 12 indicates through the wearable device 22 or the patient device 24 that he or she is not going to eat, the one or more processors 28 may not output instructions for the insulin pump 14 to deliver the partial therapy dose. Such a notification confirming whether the patient 12 is about to eat is not required in all examples.

[0084] The one or more processors 28 can then determine that a meal event is occurring based on the frequency and pattern of the patient 12's arm movements. For example, the one or more processors of the wearable device 22 can be configured to determine one or more movement characteristics of the patient 12 (e.g., detecting gesture movements as described above). The one or more processors 28 can receive information indicating gesture movements (e.g., one or more movement characteristics) and determine whether the gesture movements are consistent with the patient 12's movements for eating. If the gesture movements are consistent with the patient 12's movements for eating, the one or more processors 28 can determine that the patient 12 is indeed eating (i.e., determine that a meal event is occurring).

[0085] In response to determining that a meal event is occurring, one or more processors 28 may output instructions to the insulin pump 14 (e.g., via the patient device 22) for delivering the remaining therapy dose with or without user confirmation. One or more processors 28 may output instructions for delivering the remaining therapy dose while the patient 12 is eating or after the patient 12 has finished eating (e.g., based on the patient 12's arm not moving or no longer moving in accordance with the patient 12 eating). The remaining therapy dose may be a Z gram bolus of insulin, where Z is approximately equal to XY. For example, if Y is equal to 0.2*X, then Z is equal to 0.8*X.

[0086] There are a variety of ways to determine whether patient 12 has finished eating. As an example, movement characteristics of patient 12's arm may indicate that patient 12 is no longer eating. Additionally, in some examples, processor(s) 28 may determine during an initial learning phase the amount of time patient 12 typically eats or the amount of bites patient 12 typically takes to ingest a meal. Processor(s) 28 may utilize such information to determine whether patient 12 has finished eating.

[0087] As described above, in some examples, the partial therapy dose is less than half the amount of the therapy dose (e.g., Y is less than 0.5*X). Thus, the amount of insulin for the partial therapy dose may be less than the amount of insulin for the remaining therapy dose (e.g., Y is less than 0.5*X). <Z)。

[0088] In the above example, one or more processors 28 can determine how much bolus insulin will be delivered by the insulin pump 14 (e.g., determine the amount of the therapy dose), and then determine the amount of the partial therapy dose. However, the example technology is not limited to this. In some examples, instead of determining the amount of the therapy dose or in addition to determining the amount of the therapy dose, one or more processors 28 can output instructions for causing the insulin pump 14 to deliver a set amount for the partial therapy dose based on the determination that a meal event is about to occur. Then, in response to the occurrence of a meal event, one or more processors 28 can deliver the remaining therapy dose based on the type of meal consumed by the patient 12 or based on the current glucose level (e.g., determined by the sensor 20).

[0089] In instances where the one or more processors 28 determine an amount of insulin to be delivered to the patient to accommodate the consumption of a meal or the one or more processors 28 output instructions to deliver a partial therapy dose to the insulin pump 14, the partial therapy dose may be a portion of the amount of insulin to be delivered to the patient to accommodate the consumption of the meal. The remaining therapy dose may be the remaining portion of the patient's amount of insulin to be delivered to the patient to accommodate the consumption of the meal (e.g., after the meal or during the meal, such as at the midpoint of the meal based on a prediction of when the patient 12 will finish eating).

[0090] There may be multiple instances of instructions for one or more processors 28 to output a therapy dose for the insulin pump 14 to deliver. As an example, one or more processors 28 may output instructions specifying the amount of therapy dose to be delivered. As another example, one or more processors 28 may output instructions specifying a target glucose level. In response to the specified target glucose level, based on feedback from the sensor 20 to the current glucose level, the insulin pump 14 may deliver a bolus of insulin to reach the target glucose level. In each of these examples, one or more processors 28 may be considered to output instructions to the insulin pump 14 for causing the insulin pump 14 to deliver a partial therapy dose before a meal event or to deliver the remaining therapy dose (e.g., during a meal event or after a meal event).

[0091] Example techniques are described above with respect to one or more processors 28. However, the example techniques are not limited thereto. The example techniques may be performed by one or more processors of patient device 24. The example techniques may be performed by one or more processors of wearable device 22. The example techniques may be performed by one or more processors of insulin pump 14. In some instances, any combination of one or more processors 28, one or more processors of patient device 24, one or more processors of wearable device 22, or one or more processors of insulin pump 14 may be configured to perform the example techniques described in the present disclosure.

[0092] As an example, one or more processors 28 may be a first set of processors. The second set of processors may be one or more processors of a wearable device 22 worn by a patient 12. To determine that a meal event is occurring, the second set of processors may be configured to detect one or more movement characteristics of the patient 12. At least one of the first set of processors or the second set of processors may be configured to determine that a meal event is occurring based on the movement characteristics. As another example, the second set of processors of the wearable device 22 may output information indicating the movement characteristics to a third set of processors of the patient device 24, and the third set of processors may be configured to determine that a meal event is occurring based on gesture movement.

[0093] For ease of description, the example techniques are described with respect to one or more processors 28. However, the example techniques should not be considered limited to one or more processors. For example, the one or more processors configured to perform the example techniques described in this disclosure may be one or more processors 28, one or more processors of a patient device 24, one or more processors of a wearable device 22, one or more processors of an insulin pump 14, or any combination thereof.

[0094] Figure 2 is a block diagram illustrating another example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure. Figure 2 Shows something like Figure 1 In system 10B, however, patient 12 may not have insulin pump 14. Instead, patient 12 may utilize a manual injection device (e.g., an insulin pen or syringe) to deliver insulin. For example, rather than insulin pump 14 automatically delivering insulin, patient 12 (or perhaps a caregiver of patient 12) may fill a syringe with insulin or set a dose in an insulin pen and inject himself or herself.

[0095] exist Figure 2 In the example, Figure 1 Similarly, one or more processors 28 may determine that a meal event is about to occur. Figure 2In response to the determination indicating that a meal event is about to occur, one or more processors 28 may output instructions to a device (e.g., patient device 24) for notifying patient 12 to use a syringe or insulin pen to take a partial therapy dose before the meal event occurs. The instructions to patient device 24 for notifying patient 12 to use a syringe or insulin pen to take a partial therapy dose may include a reminder of the amount of insulin to be injected and / or may specify the amount of insulin to be injected. In some instances, patient device 24 may output instructions to the insulin pen for automatically setting the recommended insulin dose. One or more processors 28 may then determine that a meal event is occurring based on movement characteristics of patient 12's arm. In response to the determination indicating that a meal event is occurring, one or more processors 28 may output instructions to a device (e.g., patient device 24) for notifying patient 12 to use a syringe or insulin pen to take the remaining therapy dose. In Figure 2 In the example of notifying the patient 12 to use a syringe or an insulin pen, the description covers the example of the patient or the caregiver using the syringe, insulin pen to deliver a partial therapy dose and / or a remaining therapy dose. That is, any notification to the patient 12 includes an example of a separate notification to the caregiver or the caregiver reading a notification on the patient device 24 that the patient 12 will receive a therapy dose (e.g., a partial therapy dose or a remaining therapy dose).

[0096] Figure 3 is a block diagram illustrating another example system for delivering or directing a dose of therapy according to one or more examples described in the present disclosure. Figure 3 Shows something like Figure 1 System 10A and Figure 2 In system 10C, patient 12 may not have insulin pump 14. Instead, patient 12 may utilize injection device 30 to deliver insulin. For example, rather than insulin pump 14 automatically delivering insulin, patient 12 (or perhaps a caregiver of patient 12) may utilize injection device 30 to inject himself or herself.

[0097] As described above, the injection device 30 may be different from a syringe or a basal insulin pen, because the injection device 30 may be a device that can communicate with the patient device 24 and / or other devices in the system 10C. Moreover, the injection device 30 may include a reservoir, and may be able to measure so much insulin for delivery based on information indicating how much therapy dose is to be delivered. In some instances, the injection device 30 may be similar to an insulin pump 14, but is not worn by the patient 12. An example of the injection device 30 is an insulin pen, which is sometimes also referred to as a smart insulin pen. Another example of the injection device 30 may be an insulin pen with a smart cap, wherein the smart cap may be used to set a specific insulin dose.

[0098] exist Figure 3 In the example, Figure 1 Similarly, one or more processors 28 may determine that a meal event is about to occur. Figure 3 In response to the determination indicating that a meal event is about to occur, the one or more processors 28 may output instructions to a device (e.g., the patient device 24) for notifying the patient 12 to use the injection device 30 to take a partial therapy dose before the meal event occurs. The patient device 24 may output information indicating the amount for the partial therapy dose to the injection device 30 so that the injection device 30 may prepare the correct amount of insulin for delivery with little or no intervention from the patient 12 (e.g., the injection device 30 may automatically set the amount of insulin based on the information received from the patient device 24). In this way, in response to the prediction indicating that a meal event is about to occur, the one or more processors 28 may output instructions to the injection device 30 for causing the injection device 30 to prepare a partial therapy dose (e.g., load the required amount of insulin so that the patient 12 can inject the partial therapy dose for himself / herself).

[0099] The one or more processors 28 may determine that a meal event is occurring based on the movement characteristics of the patient's arm movement. In response to the determination indicating that a meal event is occurring, the one or more processors 28 may output instructions to a device (e.g., patient device 24) for notifying the patient 12 to use the injection device 30 to take the remaining therapy dose. The patient device 24 may output information indicating the amount of the remaining therapy dose to the injection device 30, so that the injection device 30 may prepare the correct amount of insulin for delivery with little or no intervention from the patient 12 (e.g., the injection device 30 may automatically set the amount of insulin based on the information received from the patient device 24). In this way, in response to a prediction indicating that a meal event is occurring, the one or more processors 28 may output instructions to the injection device 30 for causing the injection device 30 to prepare the remaining therapy dose (e.g., loading the required amount of insulin so that the patient 12 can inject the remaining therapy dose for him / herself).

[0100] and Figure 2 Similar, in Figure 3 In the example of notifying the patient 12 to use the injection device 30, the description of notifying the patient 12 to use the injection device 30 encompasses the example of the caregiver using the injection device 30 to deliver a partial therapy dose and / or a remaining therapy dose. That is, any notification to the patient 12 includes the example of separately notifying the caregiver or the caregiver reading a notification on the patient device 24 that the patient 12 will receive a therapy dose (e.g., a partial therapy dose or a remaining therapy dose).

[0101] exist Figure 2 and 3In an example of , one or more processors 28 can determine when a meal event is about to occur and determine (e.g., based on information from a digital twin) the amount of a partial therapy dose and / or a remaining therapy dose based on when the meal event is about to occur and behavioral pattern data indicating the type of food that the patient 12 will consume. The one or more processors 28 can also determine a time to ingest the partial therapy dose and / or the remaining therapy dose. The one or more processors 28 can output instructions to the patient device 24 for notifying the patient 12 about the amount of the therapy dose and the time for delivering the therapy dose. Figure 3 In the example of , the patient device 24 may further output information of the amount of the therapy dose and the time for delivering the therapy dose to the injection device 30 .

[0102] After the patient 12 takes insulin from the syringe or injection device 30 based on the notification, the patient 12 can log into the patient device 24 that he or she has taken the therapy dose. The one or more processors 28 can confirm that the meal event has actually occurred based on the gesture movement (e.g., one or more movement characteristics indicating that the patient 12 did not move the arm in a manner consistent with a meal), and then output a notification to the patient 12 through the patient device 24 to take the remaining therapy dose. As described above, there can be a variety of ways to determine when the patient 12 has finished eating. Figure 1-3 In any of the examples, if patient 12 stops eating earlier than expected (e.g., based on patient 12 no longer moving their arm in a manner or frequency indicative of eating), one or more processors 28 may output a notification via patient device 24 requesting patient 12 to eat more to avoid the effects of hypoglycemia. If patient 12 continues to eat for longer than expected (e.g., based on patient 12 moving their arm in a manner or frequency indicative of eating), one or more processors 28 may output a notification via patient device 24 requesting patient 12 to take more insulin. Figure 1 In an example of , the one or more processors 28 may cause the insulin pump 14 to deliver more insulin, with or without notifying the patient 12, by lowering the target glucose level and / or by instructing the insulin pump 14 to deliver more insulin.

[0103] The above examples describe the insulin pump 14, the syringe, and the injection device 30 as example ways of delivering insulin. In the present disclosure, the term "insulin delivery device" may generally refer to any device for delivering insulin. Examples of insulin delivery devices include the insulin pump 14, the syringe, and the injection device 30. As described, the syringe may be a device for injecting insulin, but may not necessarily be able to communicate or administer a specific amount of insulin. However, the injection device 30 may be a device for injecting insulin, and may be able to communicate with other devices (e.g., via Bluetooth, BLE and / or Wi-Fi) or may be able to administer a specific amount of insulin. The injection device 30 may be a powered (e.g., battery-powered) device, and the syringe may be a device that does not require electricity.

[0104] Because there may be different ways to deliver insulin, in one or more instances, in response to a determination indicating that a meal event is about to occur, one or more processors 28 may do at least one of the following: (1) output instructions to an insulin delivery device (e.g., insulin pump 14) for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) output instructions to a device (e.g., patient device 24) for notifying the patient to use an insulin delivery device (e.g., a syringe or injection device 30) to take a partial therapy dose before the meal event occurs; or (3) output instructions to an insulin delivery device (e.g., injection device 30) for causing the insulin delivery device to prepare a partial therapy dose (e.g., preload a determined amount of insulin so that the patient 12 can deliver the partial therapy dose) before the meal event occurs. In addition, in response to a determination indicating that a meal event is occurring, the one or more processors 28 may perform at least one of the following: (1) outputting instructions to the insulin delivery device (e.g., insulin pump 14) for delivering the remaining therapy dose; (2) outputting instructions to the device (e.g., patient device 24) for notifying the patient to use the insulin delivery device (e.g., syringe or injection device 30) to ingest the remaining therapy dose; or (3) outputting instructions to the insulin delivery device (e.g., injection device 30) for causing the insulin delivery device to prepare the remaining therapy dose. Although described with respect to one or more processors 28, the example techniques may be performed by one or more processors 28, one or more processors of a patient device 24, one or more processors of a wearable device 22, one or more processors of an insulin pump 14, or any combination thereof.

[0105] therefore, Figure 1-3An example is shown in which a wearable device 22 worn on the wrist of a patient 12 can be used to detect the occurrence of a meal event (e.g., the patient 12 eating). The wearable device 22 can include a six-axis inertial measurement unit, which includes an accelerometer and a gyroscope. The system 10A-10C includes one or more processors 28, which can be configured to determine a meal dose of insulin (e.g., how much insulin is delivered to the patient 12 to accommodate the consumption of the meal). The one or more processors 28 can also be configured to detect food consumption achieved by eating or drinking based on one or more movement characteristics, such as gesture movement (e.g., the manner and frequency of the patient 12's arm movement).

[0106] One or more processors 28, wearable device 22, and / or patient device 24 can detect when patient 12 is consuming food. One or more processors 28, wearable device 22, and / or patient device 24 can determine the amount of insulin to be delivered to accommodate the meal (e.g., the amount of insulin required to offset the increase in glucose levels caused by consuming the meal), and communicate information indicating the amount of insulin to be delivered to the insulin pump 14, wearable device 22, and / or patient device 24. In some instances, the amount of insulin may be predetermined or fixed, in which case it may or may not be necessary to communicate the information indicating the amount of insulin. The patient device 24, wearable device 22, and / or insulin pump 14 can output a notification of the amount of insulin to be delivered, and can also provide a reminder to patient 12 for insulin (e.g., as in a notification message). Figure 2 and 3 In some examples, the patient device 24 may output information to the injection device 30 indicating the amount of insulin to be delivered.

[0107] According to one or more examples described in the present disclosure, in contrast to waiting to deliver all insulin (e.g., bolus insulin) after or before a meal event, a patient 12 can receive a portion of insulin (e.g., a partial therapy dose) before a meal event occurs to reduce postprandial glucose levels, but with a sufficiently low dose to reduce any negative effects in the case where the patient 12 chooses not to eat. As described above, before a meal event can be before one or more movement characteristics indicating that the patient 12 is eating or starting to eat, and can be a certain amount of time before a meal event or before a meal event is about to begin. Then, the patient 12 can receive the remaining therapy dose after confirming that the patient 12 is actually eating (i.e., a meal event is occurring) based on a prediction of movement characteristics or how long the meal will take. Some example methods of utilizing the technology described in the present disclosure are described below.

[0108] As described above, based on the manual recording of food items and the data uploaded to the one or more processors 28 in the cloud 26, the one or more processors 28 can determine patterns of meal behavior. For example, the one or more processors 28 can utilize machine learning (e.g., updating a classifier or k-means clustering, as two examples) to determine the temporal pattern of the patient 12's eating. In addition, the one or more processors 28 can determine patterns in the amount of carbohydrates consumed by the patient 12.

[0109] Once the temporal pattern of eating and the possible amount of carbohydrates are determined (e.g., as part of an initial learning phase), in response to a determination indicating that a meal event is about to occur, one or more processors 28 can determine the amount of a partial therapy dose and the time to deliver the partial therapy dose and output instructions to an insulin delivery device (e.g., insulin pump 14) for causing the insulin delivery device (e.g., automatically or with minimal user intervention) to deliver the partial therapy dose before the meal event. As an example of instructions for the insulin pump 14, one or more processors 28 can output instructions to the insulin pump 14 (e.g., through the patient device 24) for lowering the glucose target before consuming the meal, which in turn causes the insulin pump 14 to deliver a bolus of insulin to try and achieve a lower glucose target with or without patient confirmation at the insulin pump 14. One or more processors 28, the insulin pump 14, and / or the patient device 24 can determine an amount of insulin that is safe for the patient 12 so as to increase active insulin (i.e., bolus insulin) without increasing the risk of hypoglycemia. In this way, high postprandial glucose levels can be reduced by delivering insulin to the patient 12 more quickly.

[0110] The one or more processors 28 may determine that a meal event is occurring based on one or more movement characteristics of the patient's 12 arm movement (e.g., based on hand gesture movement detected by the wearable device 22) to confirm that the patient 12 is actually eating. In response to the determination indicating that a meal event is occurring, the one or more processors 28 may output instructions to the insulin pump 14 (e.g., via the patient device 24) for delivering the remaining therapy dose. The insulin pump 14 may deliver the remaining therapy dose (e.g., during the meal or after the meal is confirmed to be over based on the wearable device 22 no longer detecting movement of the finger feeding).

[0111] For example, at noon, the patient 12 may typically eat a sandwich consisting of 55 grams of carbohydrates. The one or more processors 28 may output instructions to the insulin pump 14 for causing the insulin pump 14 to lower the glucose target 20 minutes before a typical meal is consumed (e.g., to deliver a partial therapy dose). At noon, the one or more processors 28 may determine that a meal is being eaten (e.g., based on the movement characteristics of the patient's 12 arm, a meal event is occurring) and may output instructions to the insulin pump 14. The insulin pump 14 may deliver the remaining therapy dose during the meal or after the meal is consumed.

[0112] In the above example, one or more processors 28 output instructions for reducing the target glucose level as a way to deliver a partial therapy dose before a meal event occurs. In some examples, one or more processors 28 may output instructions defining the amount of a partial therapy dose to be delivered before a meal event occurs (e.g., including the number of fixed insulin units to be delivered). For example, as described above, the patient 12 may consume a sandwich consisting of 55 grams of carbohydrates at noon. One or more processors may output instructions to the insulin pump 14 for delivering a small amount of pre-meal bolus insulin before a typical meal is consumed.

[0113] The above example describes the time of day (e.g., noon) as a factor in determining when and whether to deliver a partial therapy dose before a meal event. In some instances, one or more processors 28 may utilize location information (e.g., instead of the time of day or in combination with the time of day). For example, one or more processors 28 may utilize machine learning to determine a pattern and associate the type of food and / or the amount of food with the location where the food is purchased or consumed. After one or more processors 28 determine the meal behavior pattern for time and location (e.g., as part of an initial learning phase), one or more processors 28 may output instructions that cause the insulin pump 14 to deliver an amount of insulin (e.g., a partial therapy dose) that does not cause hypoglycemia before consuming a meal. As described, in some instances, one or more processors 28 may cause the patient device 24 and / or wearable device 22 to output a notification requesting confirmation that the patient 12 will eat. One or more processors 28 may cause the patient device 24 and / or wearable device 22 to output such a notification based on the location of the patient 12.

[0114] As an example, patient 12 may be eating bagels from the same bagel shop. If one or more processors 28 determine that patient 12 is near the bagel shop based on the location of patient 12, one or more processors 28 may output instructions for delivering a portion of the therapy dose before patient 12 enters the bagel shop. After one or more processors 28 determine that patient 12 is eating (e.g., after determining that a meal event is occurring), one or more processors 28 may output instructions for causing insulin pump 14 to deliver the remainder of the therapy dose.

[0115] The above-mentioned example technology based on the time of day and location. In some examples, one or more processors 28 can use the time of day, location and other contextual information, such as a combination of sleep patterns, calendar information, temperature, heart rate, etc. to determine whether to deliver and when to deliver so that the insulin pump 14 delivers a partial therapy dose. By using multiple factors to determine whether the patient 12 is about to eat and / or whether it is eating (e.g., using multi-factor meal recognition), the example technology can more accurately determine (e.g., predict) when the patient 12 is about to eat. One or more processors 28 can reduce the false positive rate of meal detection events by combining two or more detection inputs, which can allow a more aggressive partial therapy dose to be delivered before the meal. For example, because the patient 12 is more likely to eat, if multiple contextual information items (e.g., time and location of the day) indicate that a meal event is about to occur, compared to if fewer contextual information items indicate that a meal event is about to occur, one or more processors 28 can be more certain that a meal event is about to occur, and therefore a higher partial therapy dose can be provided, and the chance of hypoglycemia is smaller.

[0116] As an example, if only one context indicates that patient 12 is about to consume food (e.g., only one context indicates that a meal event is about to occur), one or more processors 28 may have limited options for the manner and amount of the partial therapy dose (e.g., lowering the auto basal set point, lowering the auto correction bolus target, or raising the auto basal insulin limit).

[0117] The automatic basal set value refers to the closed-loop target glucose. For example, the closed-loop automatic basal delivery rate (e.g., the rate at which the insulin pump 14 continuously delivers basal insulin) is reduced when the measured glucose level is below the automatic basal set value. The closed-loop automatic basal delivery rate is increased to the automatic basal limit when the measured glucose is above the automatic basal set value. The automatic correction bolus target refers to the glucose target for the correction bolus. The basic correction bolus equation is (current glucose-correction target) / correction factor-active insulin. The lower the correction target, the larger the correction bolus will be for a given current glucose value. The automatic basal limit refers to the maximum basal rate allowed to be controlled by the closed-loop automatic basal controller. This is a safety feature intended to prevent excessive delivery of insulin due to time delays in measurements from the sensor 20 and possible sensor errors. Temporarily raising this limit may provide more effective control in the case of consuming a meal.

[0118] However, if multiple contexts (e.g., multiple context information items) indicate that the patient 12 is about to consume food (e.g., multiple context information items indicate that a meal event is about to occur), the one or more processors 28 can execute any of a lower automatic basal set point, a lower automatic correction bolus target, or an increased automatic basal insulin limit, and output instructions to cause the insulin pump 14 to deliver a fixed pre-meal bolus equivalent for a small meal (e.g., for a 30-gram carbohydrate meal).

[0119] In general, if only a few contextual information items (e.g., one or two) indicate that a meal event is about to occur (e.g., the confidence that a meal event is about to occur is low), one or more processors 28 can determine a first amount of a partial therapy dose to be delivered. However, if more contextual information items indicate that a meal event is about to occur (e.g., the confidence that a meal event is about to occur is high), one or more processors can determine a second amount of a partial therapy dose to be delivered. For example, a machine learning algorithm can be configured to generate a confidence value indicating the confidence that a patient 12 is about to consume a meal based on learning of the patient's behavior. The second amount of the partial therapy dose can be greater than the first amount of the partial therapy dose. For example, the second amount of the partial therapy dose can be a preselected amount, while the first amount of the partial therapy dose can be determined based on an assumption of how much carbohydrates the patient 12 is going to consume. In this way, the higher the confidence that the patient 12 will consume a meal, the more aggressive the insulin therapy will be (i.e., more insulin can be delivered before the meal).

[0120] Moreover, the above-mentioned example technology is described with respect to the insulin pump 14. However, the example technology can be extended to the instance that the patient 12 does not have an automatic insulin delivery (AID) device like the insulin pump 14. In the instance that the patient 12 does not have the insulin pump 14 but uses the syringe or injection device 30, the patient 12 can be regarded as using the multiple daily injection (MDI) insulin therapy scheme. For example, similar to the above, one or more processors 28 can determine whether a meal event is about to occur (e.g., based on various scenarios). In response to the determination indicating that the meal event will occur, one or more processors can output to the device (e.g., the patient device 24) an instruction for notifying the patient to use the insulin delivery device (e.g., the syringe or injection device 30) to take a portion of the therapy dose before the meal event occurs. One or more processors 28 can determine that the meal event is occurring based on the movement characteristics of the patient's 12 arm. In response to the determination indicating that the meal event is occurring, one or more processors 28 can output to the device (e.g., the patient device 24) an instruction for notifying the patient 12 to use the insulin delivery device (e.g., the syringe or injection device 30) to take the remaining therapy dose.

[0121] In this way, insulin dosage guidance can be provided to patient 12 based on automatic meal detection based on gesture movement (e.g., movement characteristics). One or more processors 28 can determine the correct dosage and time based on automatic detection of meals, including determining a partial therapy dose to be taken before the meal.

[0122] In addition to reducing the increase of postprandial glucose levels, there are also benefits associated with automatic meal detection and the delivery of partial therapy doses. In some instances, patient 12 can follow normal behavior patterns, but sometimes may include some "tag along" food items, such as desserts or beverages. There may be a delay between patient 12 completing the meal and having desserts or beverages after the meal. In some instances, patient 12 may not consider the accompanying food. Utilizing automatic meal detection, one or more processors 28 can determine that patient 12 eats more than he or she usually does. For example, one or more processors 28 can determine that patient 12 eats again shortly after a meal event. Due to the partial therapy dose that patient 12 has taken, even in the case of accompanying food, the chance that glucose level will become undesirably high can be reduced. In addition, due to meal detection, one or more processors 28 can output instructions for further increasing the bolus insulin dose to consider the accompanying food.

[0123] As explained, there are various types of insulin delivery devices (e.g., insulin pump 14, syringe, or injection device 30). In the case of injection device 30, patient 12 may be asked to set the insulin level to be delivered, and the patient can then use injection device 30 to deliver insulin at set times or at expected events (e.g., meals).

[0124] One or more processors 28 may be configured to utilize patient behavior information and meal detection to determine the amount of insulin and the time of delivering insulin. One or more processors 28 may output information indicating the amount and time of delivering insulin to the patient device 24. In some instances, the patient device 24 may be configured to perform such example techniques without assistance from one or more processors 28. In some instances, one or more processors 28 may utilize a physiological model (e.g., a patient computer model indicating how therapy will affect the patient, such as a digital twin) to determine the amount of insulin and the time of delivering insulin.

[0125] In some cases, one or more processors 28 may determine the amount of insulin to be taken and the time to take the insulin based on a prediction of what the patient 12 will eat. However, the patient 12 may add "accompanying" foods, such as desserts or beverages. The one or more processors 28 may determine whether the patient 12 has already injected himself or herself with insulin using the injection device 30 based on the movement detected by the wearable device 22 to ensure that the patient 12 does not inject himself or herself more than once. Moreover, the one or more processors 28 may determine whether the patient 12 is eating additional foods that were not accounted for (e.g., based on additional hand movements beyond those expected for a basic meal) to adjust the amount of insulin to be taken by the patient.

[0126] In some examples, the operation of sensor 20 may also be altered based on the detection that patient 12 is eating. In some cases, the glucose level of patient 12 may increase, and in some cases increase at a higher rate, during times when patient 12 is eating compared to when patient 12 is not eating. Therefore, it may be beneficial to determine the glucose level when patient 12 is eating more frequently than at other times so that therapy can be delivered in a more timely manner.

[0127] In one or more instances, one or more processors 28 may determine that the patient is eating or about to eat (e.g., a meal event is occurring or is about to occur). In response, one or more processors 28 may instruct the sensor 20 to determine and output a glucose level at a higher rate than when the patient 12 is not eating or is about to eat. There are multiple ways in which one or more processors 28 may determine that the patient is eating or is about to eat, such as those described above. Therefore, in one or more instances, one or more processors 28 may determine that a meal event is about to occur or is occurring. In response to the determination, one or more processors 28 may instruct the sensor 20 to output the glucose level of the patient 12 at a first rate, which is higher than the second rate at which the sensor 20 outputs the glucose level of the patient 12 when the meal event will not occur or has not occurred. For example, the second rate may be a glucose level measurement once every five minutes, while the first rate may be a glucose level measurement once per minute.

[0128] As information is received at a higher rate during meal events, the one or more processors 28 and / or the insulin pump 14 may be configured to more quickly update changes in therapy dosage (e.g., increase or decrease the amount of bolus insulin to be delivered) based on changes in sensed glucose levels (e.g., faster / more aggressive auto-correction boluses). Moreover, during times when the one or more processors 28 determine that a meal event has not occurred or will not occur, the sensor 20 may be able to output glucose level measurements at a lower rate, which increases the battery life of the sensor 20 and the battery life of the insulin pump 14 because the power consumption of the receiver circuitry (e.g., the radio circuitry) is reduced when a meal is not being consumed.

[0129] As described above, one or more processors 28 may determine a partial therapy dose to be delivered before a meal event and determine a remaining therapy dose that may be delivered during or after a meal event. In some instances, one or more processors 28 may determine therapy to be delivered during a meal, such as based on when patient 12 will nibble or based on a prediction of how much carbohydrates patient 12 will consume. For example, based on patient behavior, one or more processors 28 may predict how many carbohydrates patient 12 will consume. In some instances, one or more processors 28 may also predict how many bites patient 12 will take to consume food.

[0130] For example, as described above, the one or more processors 28 can determine the amount of time it takes for the patient 12 to consume a meal based on the patient's behavior. Additionally, during the eating of the meal, the one or more processors 28 can determine movement characteristics, which can include information about how often the patient 12 moves his or her arms to his or her mouth while eating. Each instance in which the patient 12 moves his or her arms to his or her mouth can be an instance of a bite (e.g., moving a hand to the mouth to bite a sandwich or pizza). In some instances, the one or more processors 28 can determine how many bites the patient 12 will take and how many carbohydrates the patient 12 will consume. Using the information indicating the number of bites and the amount of carbohydrates, the one or more processors 28 can cause the insulin delivery device (e.g., the insulin pump 14) to deliver a small bolus of insulin throughout the meal.

[0131] For example, some example techniques deliver a bolus of insulin after a meal is completed. However, it may be beneficial to deliver a bolus of insulin while patient 12 is eating to avoid sudden increases in glucose levels of patient 12. In some examples, one or more processors 28 may determine whether patient 12 is currently eating and, in response, output instructions for causing an insulin delivery device (e.g., insulin pump 14) to deliver a micro-bolus insulin therapy, which may be on a per-bite basis.

[0132] As an example, the wearable device 22 can detect movement characteristics of the patient's 12 arm, such as how long and when the patient 12 moves his or her arm to his or her mouth during a meal event. The patient 12 moving his or her arm to his or her mouth during a meal event can indicate that the patient 12 has gnawed food. One or more processors 28 can determine that the patient 12 is currently eating based on the movement characteristics (e.g., how fast the movement is and whether the movement is consistent with the movement of one's hand from a plate to a mouth). In response, the one or more processors 28 can cause the insulin pump 14 to deliver a small dose of bolus insulin at a specific frequency. For example, the one or more processors 28 can cause the insulin pump 14 to deliver a small dose of bolus insulin after each instance in which the one or more processors 28 determine that the patient 12 has gnawed (e.g., based on the movement of the arm).

[0133] The one or more processors 28 may be configured to predict how many bites the patient has taken and how much insulin to deliver for each microbolus delivery. For example, based on the patient's behavior pattern, the one or more processors 28 may determine how long the patient eats (e.g., how many bites) and the amount of carbohydrates consumed by the patient. Based on the prediction of the amount of carbohydrates and the number of bites, the one or more processors 28 may determine the amount of microbolus to be delivered (e.g., on a per-bite basis) and / or the entire series of microbolus. In some instances, the one or more processors 28 may ensure that multiple continuous arm movements indicating eating are detected before causing the insulin pump 14 to deliver a microbolus.

[0134] For example, if the patient 12 typically eats a breakfast containing 45 grams to 75 grams of carbohydrates, and typically takes 10 to 15 bites, a conservative bolus of bites can be based on the low end of carbohydrates (e.g., 45 grams) and the high end of the number of bites (e.g., 15 times). In this example, the one or more processors 28 can determine that the patient 12 will consume 3 grams of carbohydrates per bite (e.g., 45 grams / 15 bites). In this example, the one or more processors 28 can determine the amount of insulin delivered for 3 grams of carbohydrates, and in response, the insulin pump 14 can be caused to deliver the determined amount of insulin throughout the meal. In the event that the patient 12 takes more than a threshold amount of bites for a meal or after a threshold amount of time, the delivery of insulin can be stopped to ensure that the patient's 12 glucose level does not become too low.

[0135] In some instances, one or more processors 28, a processor on a patient device 24, a wearable device 22, or some combination thereof may output instructions for causing the insulin pump 14 to deliver a determined amount of insulin during the expected meal duration at each detected bite or at fixed time intervals. For example, in the above example, the patient 12 may consume 3 grams of carbohydrates per bite. One or more processors 28 may determine the amount of insulin to be delivered to account for changes in glucose levels due to 3 grams of carbohydrates. Based on the movement characteristics determined by the wearable device 22, the patient device 24 may determine that the patient 12 is about to bite (e.g., by bringing food close to the mouth). In response, the patient device 24 may cause the insulin pump 14 to deliver the amount of insulin determined by the one or more processors 28. In some instances, in contrast to delivering insulin on a per-bite basis, the insulin pump 14 may deliver insulin during fixed intervals (e.g., every 10 seconds) during a meal.

[0136] In this way, one or more processors 28, a processor of a patient device 24, and / or a processor of a wearable device 22, or a combination thereof, can determine the amount of carbohydrates that the patient 12 will eat during a meal event and the number of bites that the patient 12 will take during the meal event. Based on the determination of the amount of carbohydrates that the patient 12 will eat and the number of bites that the patient 12 will take, the one or more processors 28, the processor of the patient device 24, and / or the processor of the wearable device 22, or a combination thereof, output instructions for causing an insulin delivery device (e.g., an insulin pump 14) to deliver a microbolus or a series of microbolus insulin therapy during a meal event. In some examples, in order to output instructions for causing an insulin delivery device to deliver a series of microbolus, the one or more processors 28, the processor of the patient device 24, and / or the processor of the wearable device 22, or a combination thereof, can be configured to output instructions for causing an insulin delivery device (e.g., an insulin pump 14) to deliver a series of microbolus each time a bite is detected or at fixed time intervals.

[0137] The above examples of delivering a microbolus are described with respect to the one or more processors 28. However, the one or more processors may be the patient device 24, the insulin pump 14, the wearable device 22, one or more processors of the one or more processors 28, or any combination thereof.

[0138] Figure 4 is a block diagram illustrating an example of a patient device according to one or more examples described in the present disclosure. Although the patient device 24 may be generally described as a handheld computing device, the patient device 24 may be, for example, a laptop computer, a cellular phone, or a workstation. In some examples, the patient device 24 may be a mobile device such as a smart phone or a tablet computer. In such examples, the patient device 24 may execute an application that allows the patient device 24 to perform the example techniques described in the present disclosure. In some examples, the patient device 24 may be a dedicated controller for communicating with the insulin pump 14.

[0139] Although the examples are described with one patient device 24, in some examples, the patient device 24 may be a combination of different devices (e.g., a mobile device and a controller). For example, the mobile device may provide access to one or more processors 28 of the cloud 26 via Wi-Fi or a carrier network, and the controller may provide access to the insulin pump 14. In such examples, the mobile device and the controller may communicate with each other via Bluetooth or BLE. Various combinations of mobile devices and controllers that together form the patient device 24 are possible, and the example technology should not be considered limited to any one particular configuration.

[0140] like Figure 4, patient device 24 may include processing circuitry 32, memory 34, a user interface 36, telemetry circuitry 38, and a power source 39. Memory 34 may store program instructions that, when executed by processing circuitry 32, cause processing circuitry 32 to provide the functionality attributed to patient device 24 throughout this disclosure.

[0141] In some examples, memory 34 of patient device 24 may store a plurality of parameters, such as the amount of insulin to be delivered, the target glucose level, the time of delivery, etc. Processing circuitry 32 (e.g., via telemetry circuitry 38) may output the parameters stored in memory 34 to insulin pump 14 or injection device 30 to deliver insulin to patient 12. In some examples, processing circuitry 32 may execute a notification application stored in memory 34 that outputs notifications to patient 12 via user interface 36, such as notifications for taking insulin, the amount of insulin, and the time to take insulin.

[0142] Memory 34 may include any volatile, nonvolatile, fixed, removable, magnetic, optical, or electrical media, such as RAM, ROM, hard disk, removable disk, memory card or stick, NVRAM, EEPROM, flash memory, etc. Processing circuitry 32 may take the form of one or more microprocessors, DSPs, ASICs, FPGAs, programmable logic circuitry, etc., and the functionality attributed herein to processing circuitry 32 may be embodied in hardware, firmware, software, or any combination thereof.

[0143] The user interface 36 may include buttons or a keyboard, a light, a speaker for voice commands, and a display, such as a liquid crystal (LCD). In some instances, the display may be a touch screen. As discussed in the present disclosure, the processing circuit system 32 may present and receive information related to therapy through the user interface 36. For example, the processing circuit system 32 may receive patient input through the user interface 36. The patient input may be input, for example, by pressing a button on a keyboard, entering text, or selecting an icon from a touch screen. The patient input may be information indicating the food that the patient 12 has eaten, such as whether the patient 12 has used insulin (e.g., by a syringe or injection device 30) for the initial learning phase, and other such information.

[0144] In some examples, processing circuitry 32 may include GPS circuitry that may identify the location of patient 12. Processing circuitry 32 may output the location of patient 12 as well as time of day information as part of an initial learning phase to determine when and where patient 12 eats, and then subsequently so that one or more processors 28 may determine whether a meal event is about to occur. Location and time of day are two examples of contextual information used to determine whether a meal event is about to occur and / or is occurring, and the example techniques are not limited to location and time of day as contextual information.

[0145] In some examples, one or more processors configured to perform the example techniques described in the present disclosure may include a processing circuit system 32. For example, the processing circuit system 32 may be configured to determine that a meal event is about to occur. The processing circuit system 32 may receive contextual information, such as at least one of the time of day or location of the patient 12, and determine that a meal event is about to occur based on the received information. In response to the determination indicating that the meal event is about to occur, the processing circuit system 32 may perform at least one of the following: (1) outputting instructions to an insulin delivery device (e.g., an insulin pump 14) for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) outputting instructions to a device (e.g., a user interface 36 or an injection device 30) for notifying the patient 12 to use an insulin delivery device (e.g., a syringe or injection device 30) to take a partial therapy dose before the meal event occurs; or (3) outputting instructions to an insulin delivery device (e.g., an injection device 30) for causing the insulin delivery device to prepare a partial therapy dose before the meal event occurs.

[0146] The processing circuit system 32 can determine that a meal event is occurring based on the movement characteristics of the patient's arm movement. For example, the wearable device 22 can detect the gesture movement of the patient 12, and the processing circuit system 32 can determine that a meal event is occurring based on the gesture movement of the patient 12. In response to the determination indicating that the meal event is occurring, the processing circuit system 32 can perform at least one of the following: (1) output an instruction to the insulin delivery device (e.g., insulin pump 14) for delivering the remaining therapy dose; (2) output an instruction to the device (e.g., user interface 36 or injection device 30) for notifying the patient 12 to use the insulin delivery device to ingest the remaining therapy dose; or (3) output an instruction to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0147] As described above, in some instances, the partial therapy dose may be a portion of the amount of insulin to be delivered to the patient 12 to adapt to the consumption of the meal, and the remaining therapy dose may be the remaining portion of the amount of insulin to be delivered to the patient 12 to adapt to the consumption of the meal. The consumption of the adapted meal may refer to the amount of insulin required to deliver an offset to increase the glucose level caused by the consumption of the meal. In some instances, the partial therapy dose may be a preselected therapy dose, and the processing circuit system 32 may be configured to determine the remaining therapy dose based on one or more of the amount of carbohydrates to be consumed by the patient 12 based on the glucose level measurement result or the prediction. For example, the patient behavior pattern may indicate how much carbohydrates the patient 12 consumes at different times and / or locations, and the processing circuit system 32 may predict the amount of carbohydrates to be consumed by the patient 12. In some instances, the amount of insulin for the partial therapy dose is less than the amount of insulin for the remaining therapy dose.

[0148] There are various ways in which processing circuitry 32 can output instructions for causing an insulin delivery device (e.g., insulin pump 14) to deliver a partial therapy dose. As one example, processing circuitry 32 can output instructions to an insulin delivery device for lowering a patient's glucose target to cause the insulin delivery device to deliver a partial therapy dose.

[0149] The telemetry circuit system 38 includes any suitable hardware, firmware, software, or any combination thereof for communicating with another device such as the cloud 26, the insulin pump 16 or the injection device 30 (if applicable), the wearable device 22, and the sensor 20. The telemetry circuit system 38 can receive communications with the help of an antenna, which can be inside and / or outside the patient device 24. The telemetry circuit system 38 can also be configured to communicate with another computing device via wireless communication technology, or directly communicate via a wired connection. Examples of local wireless communication technologies that can be used to facilitate communication between the patient device 24 and another computing device include RF communication according to IEEE 802.11, Bluetooth or BLE specification sets, infrared communication according to the IrDA standard, or other standard or proprietary telemetry protocols. The telemetry circuit system 38 can also provide a connection to a carrier network to access the cloud 26. In this way, other devices can be able to communicate with the patient device 24.

[0150] The power source 39 provides operating power to the components of the patient device 24. In some examples, the power source 39 may include a battery, such as a rechargeable or non-rechargeable battery. Non-rechargeable batteries may be selected to last for several years, while rechargeable batteries may be inductively charged from an external device (e.g., on a daily or weekly basis). Recharging of the rechargeable battery may be accomplished using an alternating current (AC) outlet or by proximal inductive interaction between an external charger and an inductive charging coil within the patient device 24.

[0151] Figure 5 2 is a block diagram illustrating an example of a wearable device according to one or more examples described in the present disclosure. As shown, the wearable device 22 includes a processing circuit system 40, a memory 42, a user interface 44, a telemetry circuit system 46, a power supply 48, and an inertial measurement unit 50. The processing circuit system 40, the memory 42, the user interface 44, the telemetry circuit system 46, and the power supply 48 can be similar to Figure 3 The processing circuit system 32, memory 34, user interface 36, telemetry circuit system 38 and power supply 39 are provided.

[0152] The inertial measurement unit 50 may include accelerometers and gyroscopes and / or various components for determining the pitch-roll-yaw and xyz coordinates of the wearable device 22. In some instances, the inertial measurement unit 50 may be considered to be a six-axis inertial measurement unit. For example, the inertial measurement unit 50 may couple a 3-axis accelerometer with a 3-axis gyroscope. The accelerometer may measure linear acceleration, while the gyroscope may measure rotational movement. The processing circuit system 40 may be configured to determine one or more movement properties based on values ​​from the inertial measurement unit 50. For example, the processing circuit system 40 may determine whether the patient 12 is moving his or her arm up, down, left, right, forward, backward, or some combination thereof based on values ​​from the inertial measurement unit 50, the values ​​including values ​​related to the frequency, amplitude, trajectory, positioning, speed, acceleration, and / or pattern of the movement. Processing circuit system 40 can determine the orientation of patient 12's arm based on values ​​from inertial measurement unit 50, such as whether the back of the hand or the front of the hand is facing patient 12 or whether the side of the hand is facing patient 12 so that the thumb is facing patient 12 and the side of the index finger is visible.

[0153] As an example, when patient 12 is eating with chopsticks, patient 12 may orient his or her wrist in a particular way, which may be different if patient 12 is holding a sandwich. For different types of food, the frequency with which patient 12 moves his or her arm from a position where he or she holds the food to a position where he or she puts the food into his or her mouth may be different. For example, the frequency and movement pattern of eating with a fork may be different from the frequency and movement pattern of eating with a spoon or a knife and fork, which may be different from eating with the hands (such as a sandwich or pizza). For all of these different food items, the movement characteristics may be different, and the output values ​​from inertial measurement unit 50 may also be different. However, for all movement characteristics, one or more processors (including processing circuit system 40 in some instances) can be configured to determine that patient 12 is eating.

[0154] Inertial measurement unit 50 may output this information (e.g., pitch-roll-yaw and xyz coordinates) of the arm of patient 12 to processing circuitry 40. Telemetry circuitry 46 may then output the information from processing circuitry 40 to patient device 24. Patient device 24 may forward the information to one or more processors 28, which may use the information to determine whether patient 12 is eating (e.g., whether a meal event is occurring).

[0155] Figure 6 is a flowchart illustrating an example method of operation according to one or more examples described in the present disclosure. Figure 6 The one or more processors may be one or more processors 28, one or more processors of patient device 24 (e.g., processing circuitry 32), one or more processors of wearable device 22 (e.g., processing circuitry 40), one or more processors of insulin pump 14 (if applicable), or any combination thereof.

[0156] The one or more processors may predict that a meal event is about to occur (60). For example, the one or more processors may be a first set of one or more processors (e.g., one or more processors 28 on one or more servers of cloud 26) that receive information indicating at least one of a time of day or a location of patient 12 and determine (e.g., predict) that a meal event is about to occur based on the received information.

[0157] In response to a prediction (e.g., determination) indicating that a meal event is about to occur, the one or more processors may perform at least one of the following: (1) outputting instructions to an insulin delivery device (e.g., insulin pump 14) for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) outputting instructions to a device (e.g., patient device 24 or injection device 30) for notifying the patient to use the insulin delivery device to take a partial therapy dose before the meal event occurs; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare a partial therapy dose before the meal event occurs (62). In this way, patient 12 may receive a partial amount of insulin to reduce the chance of an increase in postprandial glucose levels.

[0158] One or more processors may determine that a meal event is occurring based on one or more characteristics of the arm movement of patient 12 (64). The one or more characteristics may be associated with one or more different forms of eating (e.g., the manner and frequency of the arm movement is consistent with the manner and frequency of the arm movement when patient 12 is eating). For example, the second group of processors (e.g., processing circuit system 40 and inertial measurement unit 50) may be configured to determine the movement characteristics of patient 12. The first group of processors or the second group of processors may receive information on the one or more movement characteristics and may determine whether the movement characteristics are consistent with movement characteristics of eating. If the movement characteristics are consistent with movement characteristics when patient 12 is eating, one or more processors (e.g., the first group of processors and / or the second group of processors) may determine that a meal event is occurring.

[0159] In some instances, one or more processors may utilize contextual information in addition to or in lieu of one or more characteristics of patient 12's arm movement to determine that a meal event is occurring. For example, when one or more characteristics of patient 12's arm movement indicate that patient 12 is eating, contextual information, such as time of day or location, may provide additional confidence that patient 12 is eating. As an example, if it is noon and patient 12 is in a restaurant, and one or more characteristics of patient 12's arm movement indicate that patient 12 is eating, the confidence that patient 12 is eating is higher than if only one or more characteristics of patient 12's arm movement indicate that patient 12 is eating.

[0160] In response to a determination indicating that a meal event is occurring, one or more processors may perform at least one of the following: (1) outputting instructions to the insulin delivery device (e.g., insulin pump 14, injection device 30) for delivering the remaining therapy dose (with or without additional user input at the insulin delivery device); (2) outputting instructions to the device (e.g., patient device 24 and / or injection device 30) for notifying the patient 12 to use the insulin delivery device to administer the remaining therapy dose (e.g., via an insulin pen or syringe); or outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the portion of the remaining dose (66). In some examples, the portion of the therapy dose may be a portion of the amount of insulin to be delivered to the patient to accommodate the consumption of the meal, and the remaining therapy dose may be the remainder of the amount of insulin to be delivered to the patient to accommodate the consumption of the meal. As described above, accommodating the consumption of a meal may refer to delivering the amount of insulin required to offset the increase in glucose levels resulting from the consumption of the meal. In some examples, the partial therapy dose may be a preselected therapy dose, and the one or more processors may be configured to determine the remaining therapy dose based on one or more of a glucose level measurement (e.g., from sensor 20) or a predicted amount of carbohydrates (predicted based on behavior or pattern) to be consumed by patient 12. In some examples, the amount of insulin for the partial therapy dose is less than the amount of insulin for the remaining therapy dose.

[0161] Fig. 7A and 7B is a flowchart illustrating another example method of operation according to one or more examples described in the present disclosure. Figure 6 , Fig. 7A and 7B The one or more processors and the patient are described. The one or more processors may be one or more processors 28, one or more processors of patient device 24 (e.g., processing circuitry 32), one or more processors of wearable device 22 (e.g., processing circuitry 40), one or more processors of insulin pump 14 (if applicable), or any combination thereof.

[0162] like Fig. 7A As shown in , one or more processors may predict (e.g., determine) whether a meal event is about to occur (70). For example, one or more processors may determine whether a meal event is about to occur based on contextual information such as the time of day and / or location of patient 12. If one or more processors determine that a meal event is not about to occur (the "no" branch of 70), then there may be no change in insulin delivery, and patient 12 may continue to deliver basal insulin (72). Fig. 7AAs shown in , during delivery of basal insulin (eg, baseline therapy), one or more processors may continuously determine (eg, predict) whether a meal event is about to occur ( 70 ).

[0163] If one or more processors predict that a meal event is about to occur (the "yes" branch of 70), the one or more processors may determine a partial therapy dose (74). For example, the one or more processors may determine the amount of the partial therapy dose and the time for delivering the partial therapy dose. In general, if only a few contextual information items (e.g., one or two) indicate that a meal event is about to occur, the one or more processors may determine a first amount of the partial therapy dose to be delivered. However, if more contextual information indicates that a meal event is about to occur, the one or more processors may determine a second amount of the partial therapy dose to be delivered. The second amount of the partial therapy dose may be greater than the first amount of the partial therapy dose. As an example, the second amount of the partial therapy dose may be equal to the first amount of the partial therapy dose plus a preselected additional amount of bolus insulin.

[0164] Therefore, in order to predict that a meal event is about to occur, one or more processors may receive one or more contextual information of the patient and determine the amount of the partial therapy dose based on the received multiple contextual information. In some instances, one or more processors may determine the amount of the partial therapy dose based on the quantity and / or quality of the contextual information of patient 12. For example, certain types of contextual information may be more predictive of meal events than other types of contextual information. As an example, the time of day may be more predictive of meal events than the location. In some instances, if the contextual information of patient 12 indicates the time of day, one or more processors may set a higher dose amount for the partial dose compared to the case where the contextual information of patient 12 is only the location.

[0165] In some examples, one or more processors may utilize the digital twin of patient 12 to determine the amount of a partial therapy dose and the time for delivering the partial therapy dose. For example, the digital twin may have previously determined a therapy dose based on how much carbohydrates patient 12 consumed, and the one or more processors may predict how much carbohydrates patient 12 is expected to consume and when the carbohydrates are consumed, and determine the partial therapy dose and when the partial therapy dose should (or should) be delivered based on the therapy dose previously determined by the digital twin.

[0166] If an insulin pump 14 is available, such as Figure 1In the step (the yes branch of 76), the one or more processors may cause the insulin pump 14 (e.g., via the patient device 24) to deliver the partial therapy dose (78). In some examples, the one or more processors may request confirmation or rejection of the partial therapy dose before the insulin pump 14 administers the partial therapy dose. If the insulin pump 14 is not available (the no branch of 76), but the injection device 30 is available (the yes branch of 80), as in Figure 3 If the patient device 24 is configured to receive the partial therapy dose, the one or more processors may output information for the partial therapy dose to the injection device 30 (82). The injection device 30 may then prepare for the injection (e.g., automatically load the correct amount of insulin) without additional user input, and the patient 12 may use the injection device 30 to administer the injection to himself or herself. In addition, the patient device 24 may also output time information for when the patient 12 takes the partial therapy dose, and notify the patient 12 to take the partial therapy dose.

[0167] If the injection device 30 is not available (the no branch of 80), the patient 12 may utilize a syringe or insulin pen to deliver a partial therapy dose. For example, one or more processors may output information for a partial therapy dose to the patient device 24, the wearable device 22, and / or the smart insulin pen cap, and the patient 12 may then use the syringe or insulin pen to deliver the partial therapy dose based on the information output by the patient device 24 through the user interface 36. In some examples, the output information may include the time when the patient 12 takes the partial therapy dose.

[0168] Steering Figure 7B , after patient 12 receives a partial therapy dose prior to a meal event, one or more processors may determine whether a meal event is occurring (86). For example, one or more processors may determine whether a meal event is occurring based on one or more movement characteristics detected by wearable device 22. If a meal event is not occurring (no branch of 86), one or more processors may output a prompt (e.g., via patient device 24) to instruct patient 12 to eat (88). However, such a prompt may not be necessary because the amount of the partial therapy dose may not be high enough to cause negative effects caused by low glucose levels.

[0169] If a meal event is occurring (the "yes" branch of 86) and the insulin pump 14 is available (the "yes" branch of 90), the one or more processors may cause the insulin pump 14 to deliver the remaining therapy dose (92). If the insulin pump 14 is not available (the "no" branch of 90) and the injection device 30 is available (the "yes" branch of 94), the one or more processors may output information for the remaining therapy dose (96) to the injection device 30, the wearable device 22, and / or the smart insulin pen cap, and the patient 12 may use the injection device 30 to inject himself or herself. If the injection device 30 is not available (the "no" branch of 94), the one or more processors may output information for the remaining therapy dose (98) to the patient device 24, and the patient 12 may use a syringe or insulin pen to inject himself or herself.

[0170] Various example techniques are described above. As another technique, the type of activity in which patient 12 participates may affect the amount of glucose in the patient's bloodstream. As an example, if patient 12 participates in aerobic exercise, patient 12 tends to use glucose in his or her blood, and the overall glucose level in the bloodstream may decrease. However, if patient 12 participates in anaerobic exercise, patient 12 tends to release glucose from muscles into the bloodstream, which may increase the overall glucose level in the bloodstream. Therefore, if patient 12 is participating in or will participate in aerobic exercise, the amount of insulin that patient 12 is to receive can be reduced or delayed until after the exercise. However, if patient 12 is participating in or will participate in anaerobic exercise, the amount of insulin that patient 12 is to receive can be increased.

[0171] One or more processors 28 may sense the type of exercise that patient 12 is or will be engaging in, but any combination of processors may be utilized. For example, wearable device 24 may output information indicating movement characteristics, and one or more processors 28 may determine the type of exercise that patient 12 is engaging in based on the information indicating movement characteristics. As another example, one or more processors 28 may predict whether patient 12 will exercise and the type of exercise that the patient will engage in based on patient behavior patterns. As another example, one or more processors 28 may determine that patient 12 is engaging in exercise based on heart rate.

[0172] In one or more examples, there may be a sensor on patient 12 for measuring heart rate (e.g., via wearable device 22). One or more processors 28 may determine with high confidence that an exercise event has begun (e.g., based on heart rate information or other movement characteristics from wearable device 22). One or more processors 28 may determine whether aerobic exercise is being performed or whether anaerobic exercise is being performed. For aerobic exercise, one or more processors 28 may increase the glucose target level, and for anaerobic exercise, one or more processors 28 may decrease the glucose target level.

[0173] In some instances, one or more processors 28 can determine whether patient 12 has fallen asleep (e.g., based on an inertial measurement unit in wearable device 22). One or more processors 28 can automatically adjust settings based on patient 12 falling asleep. For example, one or more processors 28 can adjust glucose target levels for sleep patterns. One or more processors 28 can also reduce alarms to only those determined for safety. Although described with one or more processors 28, the example techniques can be performed by any one or more processors of the various components described in this disclosure or a combination of one or more processors.

[0174] As mentioned above, there may be various sensors for measuring different situational information. Some example ways in which sensor information can be utilized are provided below. For example, based on mobile characteristics, one or more processors 28 can determine how much insulin to deliver and when to deliver insulin. In some instances, one or more processors 28 can refuse prompts to the patient 12 based on sensor data, such as low battery, or other types of alarms, such as whether glucose is slightly out of range, such as when the patient 12 is driving or sleeping, then refuse prompts. The sensor can indicate a change in temperature, and one or more processors 28 can set a target glucose level based on temperature. The sensor can indicate that the patient 12 is exercising, and one or more processors 28 can set a target glucose level based on whether the patient 12 is exercising and whether the patient 12 is performing aerobic exercise or anaerobic exercise.

[0175] In some examples, when the patient device 24 and / or wearable device 22 outputs information (e.g., broadcasts) to the one or more processors 28 can be based on contextual information of the patient 12, such as biometrics, location, and time of day. In some examples, the patient device 24 and / or wearable device 22 can output information in a manner that conserves power (e.g., broadcasts can be reduced during sleep).

[0176] There may be other ways to utilize location information of patient 12 to help control glucose levels. As one example, patient device 24 may output information of foods or food companies that provide products that help treat diabetes based on the location of patient 12 being patient 12 at a grocery store.

[0177] Various examples are described below that may be used together or in combination.

[0178] Example 1: A system for therapy delivery includes one or more processors configured to: predict that a meal event is about to occur, and in response to the prediction indicating that the meal event is about to occur, perform at least one of the following: (1) output instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs; determine that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; and in response to the determination indicating that the meal event is occurring, perform at least one of the following: (1) output instructions to the insulin delivery device for delivering a remaining therapy dose; (2) output instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) output instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0179] Example 2: A system according to Example 1, wherein the one or more processors include a first group of one or more processors on one or more servers and a second group of one or more processors on a wearable device worn by the patient, wherein in order to predict that a meal event is about to occur, the first group of one or more processors is configured to: receive one or more contextual information of the patient, and determine that the meal event is about to occur based on the received information, wherein in order to determine that the meal event is occurring, at least one of the first group of processors or the second group of processors is configured to determine that the meal event is occurring based on the one or more movement characteristics.

[0180] Example 3: A system according to any of Examples 1 and 2, wherein the partial therapy dose comprises a portion of the amount of insulin to be delivered to the patient to accommodate consumption of a meal, and wherein the remaining therapy dose comprises a remainder of the amount of insulin to be delivered to the patient to accommodate consumption of the meal.

[0181] Example 4: The system of any one of Examples 1 to 3, wherein the amount of insulin for the partial therapy dose is less than the amount of insulin for the remaining therapy dose.

[0182] Example 5: A system according to any one of Examples 1 to 4, wherein the instructions to the insulin delivery device for causing the insulin delivery device to deliver the partial therapy dose include instructions to the insulin delivery device for reducing a patient's glucose target so that the insulin delivery device delivers the partial therapy dose.

[0183] Example 6: A system according to any of Examples 1 to 5, wherein the portion of the therapy dose comprises a preselected therapy dose, and wherein the one or more processors are configured to determine the remaining therapy dose based on one or more of a glucose level measurement or a predicted amount of carbohydrates to be consumed by the patient.

[0184] Example 7: The system of any one of Examples 1 to 6, further comprising a patient device, wherein at least one of the one or more processors is a processor of the patient device.

[0185] Example 8: A system according to any one of Examples 1 to 7, wherein in order to predict that the meal event is about to occur, the one or more processors are configured to receive one or more contextual information of the patient, wherein the one or more processors are configured to determine an amount of a partial therapy dose based on the received multiple contextual information.

[0186] Example 9: The system of any one of Examples 1 to 8, further comprising the insulin delivery device, wherein the insulin delivery device comprises at least one of an insulin pump or an injection device.

[0187] Example 10: A system according to any one of Examples 1 to 9, further comprising: a glucose sensor, wherein the one or more processors are configured to, in response to the determination that the meal event is occurring, instruct the glucose sensor to output the patient's glucose level at a first rate, the first rate being higher than a second rate at which the glucose sensor outputs the patient's glucose level when the meal event is not occurring.

[0188] Example 11: A system according to any of Examples 1 to 10, wherein the one or more processors are configured to: determine an amount of carbohydrates that the patient will consume during the meal event and a number of bites that the patient will take during the meal event; and based on the determination of the amount of carbohydrates that the patient will consume and the number of bites that the patient will take, output instructions for causing the insulin delivery device to deliver a micro-bolus injection or a series of micro-bolus injections of insulin therapy during the meal event.

[0189] Example 12: A system according to Example 11, wherein in order to output the instructions for causing the insulin delivery device to deliver the series of micro-boluses, the one or more processors are configured to output the instructions for causing the insulin delivery device to deliver the series of micro-boluses each time a bite is detected or at fixed time intervals.

[0190] Example 13: A method comprising: predicting with one or more processors that a meal event is about to occur, and in response to the prediction indicating that the meal event is about to occur, performing with the one or more processors at least one of the following: (1) outputting instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose before the meal event occurs; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs; determining with the one or more processors that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; and in response to the determination indicating that the meal event is occurring, performing with the one or more processors at least one of the following: (1) outputting instructions to the insulin delivery device for delivering a remaining therapy dose; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0191] Example 14: A method according to Example 13, wherein the one or more processors include a first group of one or more processors on one or more servers and a second group of one or more processors on a wearable device worn by the patient, wherein predicting that a meal event is about to occur includes: receiving one or more contextual information of the patient using the first group of one or more processors; and determining that the meal event is about to occur using the first group of one or more processors based on the received information, wherein determining that the meal event is about to occur includes determining that the meal event is occurring based on the one or more movement characteristics using at least one of the first group of one or more processors or the second group of one or more processors.

[0192] Example 15: A method according to any one of Examples 13 and 14, wherein the partial therapy dose comprises a portion of the amount of insulin to be delivered to the patient to accommodate consumption of a meal, and wherein the remaining therapy dose comprises the remainder of the amount of insulin to be delivered to the patient to accommodate consumption of the meal.

[0193] Example 16: The method of any one of Examples 13 to 15, wherein the amount of insulin for the partial therapy dose is less than the amount of insulin for the remaining therapy dose.

[0194] Example 17: A method according to any one of Examples 13 to 16, wherein the instructions to the insulin delivery device for causing the insulin delivery device to deliver the partial therapy dose include instructions to the insulin delivery device for reducing a patient's glucose target so that the insulin delivery device delivers the partial therapy dose.

[0195] Example 18: A method according to any one of Examples 13 to 17, wherein the portion of the therapy dose comprises a preselected therapy dose, the method further comprising determining the remaining therapy dose using the one or more processors based on one or more of glucose level measurements or a predicted amount of carbohydrates to be consumed by the patient.

[0196] Example 19: A method according to any one of Examples 13 to 18, wherein predicting that the meal event will occur includes receiving one or more contextual information of the patient, and the method further includes determining an amount of the partial therapy dose based on the received multiple contextual information.

[0197] Example 20: A computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to perform the following: predicting that a meal event is about to occur, performing at least one of the following in response to the prediction indicating that the meal event is about to occur: (1) outputting instructions to the insulin delivery device for delivering a partial therapy dose before the meal event occurs; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose before the meal event occurs; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose before the meal event occurs, determining that the meal event is occurring based on one or more movement characteristics of the patient's arm movements, and performing at least one of the following in response to the determination indicating that the meal event is occurring: (1) outputting instructions to the insulin delivery device for delivering a remaining therapy dose; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose.

[0198] Various aspects of these techniques may be implemented within one or more processors, including one or more microprocessors, DSPs, ASICs, FPGAs, or any other equivalent integrated or discrete logic circuitry, and any combination of such components, embodied in a programmer, such as a physician or patient programmer, an electrical stimulator, or other device. The term "processor" or "processing circuitry" may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry or any other equivalent circuitry.

[0199] In one or more instances, the functions described in the present disclosure may be implemented in hardware, software, firmware, or any combination thereof. If executed in software, the functions may be stored as one or more instructions or codes on a computer-readable medium and executed by a hardware-based processing unit. The computer-readable medium may include a computer-readable storage medium forming a tangible non-temporary medium. The instructions may be executed by one or more processors, such as one or more DSPs, ASICs, FPGAs, general-purpose microprocessors, or other equivalent integrated or discrete logic circuit systems. Therefore, as used herein, the term "processor" may refer to any of the aforementioned structures or one or more structures in any other structure suitable for implementing the technology described herein.

[0200] In addition, in some aspects, the functions described herein may be provided within dedicated hardware and / or software modules. Depicting different features as modules or units is intended to highlight different functional aspects, and does not necessarily imply that such modules or units must be implemented by separate hardware or software components. On the contrary, the functions associated with one or more modules or units may be performed by separate hardware or software components, or integrated in shared or separate hardware or software components. Similarly, the technology may be implemented entirely in one or more circuits or logic elements. The technology disclosed herein may be implemented in various devices or apparatuses, including one or more processors 28 of the cloud 26, one or more processors of the patient device 24, one or more processors of the wearable device 22, one or more processors of the insulin pump 14, or some combination thereof. One or more processors may be one or more integrated circuits (ICs) and / or discrete circuit systems residing at various locations in the example system described in the present disclosure.

[0201] One or more processors or processing circuit systems used for example in the example technology described in the present disclosure may be implemented as fixed-function circuits, programmable circuits, or a combination thereof. Fixed-function circuits refer to circuits that provide specific functions and are pre-set on the operations that can be performed. Programmable circuits refer to circuits that can be programmed to perform various tasks and provide flexible functions in the operations that can be performed. For example, a programmable circuit can execute software or firmware that enables the programmable circuit to operate in a manner defined by the instructions of the software or firmware. Fixed-function circuits can execute software instructions (for example, to receive parameters or output parameters), but the type of operation performed by the fixed-function circuit is generally immutable. In some instances, one or more of the units may be different circuit blocks (fixed function or programmable), and in some instances, the one or more units may be integrated circuits. The processor or processing circuit system may include an arithmetic logic unit (ALU), an elementary function unit (EFU), a digital circuit, an analog circuit, and / or a programmable core formed by a programmable circuit. In an instance where software executed by a programmable circuit is used to perform the operation of a processor or processing circuit system, a memory accessible to the processor or processing circuit system may store the object code of the software received and executed by the processor or processing circuit system.

[0202] Various aspects of the disclosure have been described. These and other aspects are within the scope of the following claims.

Claims

1. A system for therapy delivery, the system comprising: One or more processors configured to: Predicting meal events are about to occur; determining an amount of insulin to deliver to the patient to accommodate consumption of the meal; In response to the prediction indicating that the meal event is about to occur, at least one of: (1) outputting instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose prior to the meal event; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose prior to the meal event; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose prior to the meal event, wherein the partial therapy dose comprises a portion of the determined amount of insulin to be delivered to the patient to accommodate consumption of the meal; determining that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; and In response to the determination indicating that the meal event is occurring, at least one of the following is performed: (1) an instruction for delivering a remaining therapy dose to the insulin delivery device; (2) an instruction for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) an instruction for causing the insulin delivery device to prepare the remaining therapy dose, wherein the remaining therapy dose includes a remainder of the determined amount of insulin to be delivered to the patient to accommodate consumption of the meal.

2. The system according to claim 1, wherein the one or more processors include a first set of one or more processors on one or more servers and a second set of one or more processors on a wearable device worn by the patient, In order to predict that a meal event is about to occur, the first group of one or more processors is configured to: receiving one or more context information of the patient; and Determining based on the received information that the meal event is about to occur, In order to determine that the meal event is occurring, at least one of the first group of processors or the second group of processors is configured to determine that the meal event is occurring based on the one or more movement characteristics.

3. The system of any one of claims 1 and 2, wherein the partial therapy dose is less than the remaining therapy dose.

4. The system of any one of claims 1 and 2, wherein the instructions to the insulin delivery device for causing the insulin delivery device to deliver the partial therapy dose include instructions to the insulin delivery device for reducing a patient's glucose target to cause the insulin delivery device to deliver the partial therapy dose.

5. A system according to any one of claims 1 and 2, wherein the partial therapy dose comprises a preselected therapy dose, and wherein the one or more processors are configured to determine the remaining therapy dose based on one or more of a glucose level measurement or a predicted amount of carbohydrates to be consumed by the patient.

6. The system of any one of claims 1 and 2, further comprising a patient device, wherein at least one of the one or more processors is a processor of the patient device.

7. A system according to any one of claims 1 and 2, wherein in order to predict that the meal event is about to occur, the one or more processors are configured to receive one or more contextual information of the patient, wherein the one or more processors are configured to determine the amount of the partial therapy dose based on the received multiple contextual information.

8. The system of any one of claims 1 and 2, further comprising the insulin delivery device, wherein the insulin delivery device comprises at least one of an insulin pump or an injection device.

9. The system according to any one of claims 1 and 2, further comprising Glucose sensor, Wherein the one or more processors are configured to, in response to the determination that the meal event is occurring, instruct the glucose sensor to output the patient's glucose level at a first rate that is higher than a second rate at which the glucose sensor outputs the patient's glucose level when the meal event is not occurring.

10. The system of any one of claims 1 and 2, wherein the one or more processors are configured to: determining an amount of carbohydrates that the patient will consume during the meal event and a number of bites that the patient will take during the meal event; and Based on the determination of the amount of the carbohydrates that the patient will consume and the number of the bites that the patient will take, instructions are output for causing the insulin delivery device to deliver a micro-bolus or series of micro-bolus insulin therapy during the meal event.

11. The system of claim 10, wherein to output the instructions for causing the insulin delivery device to deliver the series of micro-boluses, the one or more processors are configured to output the instructions for causing the insulin delivery device to deliver the series of micro-boluses each time a bite is detected or at fixed time intervals.

12. A computer-implemented method comprising: predicting, using one or more processors, that a meal event is about to occur; determining, with the one or more processors, an amount of insulin to deliver to the patient to accommodate consumption of the meal; In response to the prediction indicating that the meal event is about to occur, at least one of the following is performed using the one or more processors: (1) outputting instructions to an insulin delivery device for causing the insulin delivery device to deliver a partial therapy dose prior to the meal event; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the partial therapy dose prior to the meal event; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the partial therapy dose prior to the meal event, wherein the partial therapy dose comprises a portion of the determined amount of insulin to be delivered to the patient to accommodate consumption of the meal; determining, using the one or more processors, that the meal event is occurring based on one or more movement characteristics of the patient's arm movement; as well as In response to the determination indicating that the meal event is occurring, at least one of the following is performed using the one or more processors: (1) outputting instructions to the insulin delivery device for delivering the remaining therapy dose; (2) outputting instructions to the device for notifying the patient to use the insulin delivery device to ingest the remaining therapy dose; or (3) outputting instructions to the insulin delivery device for causing the insulin delivery device to prepare the remaining therapy dose, wherein the remaining therapy dose comprises a remaining portion of the determined amount of insulin to be delivered to the patient to accommodate consumption of the meal.

13. A computer-readable storage medium having stored thereon instructions which, when executed, cause one or more processors to perform the operations performed by the system of any one of claims 1 to 7 and 9 to 11.

Images