Gesture-based Control of Diabetes Therapy

Abstract

Describes devices, systems, and techniques for controlling the delivery of diabetes therapies. In one example, the system includes: a wearable device configured to generate user activity data associated with a user's arm; and one or more processors configured to: identify, based on the user activity data, at least one gesture indicative of preparing an insulin injection using an injection device; generate, based on the at least one identified gesture, information indicative of at least one of an amount or type of an insulin dose in the insulin injection performed by the injection device; compare the generated information with a standard for an appropriate insulin injection; and, based on the comparison, output information indicative of whether the standard is met.

Description

[0001] This application claims priority to U.S. Application No. 17 / 004,969, filed Aug. 27, 2020, which claims the benefit of U.S. Provisional Application No. 62 / 893,717, filed Aug. 29, 2019, and U.S. Provisional Application No. 62 / 893,722, filed Aug. 29, 2019, the entire contents of each of which are hereby incorporated by reference. TECHNICAL FIELD

[0002] This disclosure relates to medical systems, and more particularly to medical systems for therapies for diabetes. BACKGROUND

[0003] Diabetic patients receive insulin via a pump or an injection device to control the glucose level in their bloodstream. Due to insufficient insulin production and / or due to insulin resistance, the naturally produced insulin may not be able to control the glucose level in the bloodstream of a diabetic patient. To control the glucose level, a patient's regular treatment may include doses of basal insulin and bolus insulin. Basal insulin, also known as background insulin, tends to keep the blood glucose level at a consistent level during fasting periods and is a long-acting or intermediate-acting insulin. Bolus insulin can be used at mealtimes or other times when the glucose level may change relatively rapidly or near mealtimes or other times, and can thus be used as a short-acting or rapid-acting form of insulin dose. SUMMARY

[0004] Devices, systems, and techniques for gesture-based control of diabetes therapies are described. In various examples, gesture-based control is configured to prevent a patient from being administered an inappropriate and / or ineffective diabetes therapy by a patient device configured to deliver a diabetes therapy to the patient. One or more processors (e.g., in a patient device such as an injection device for insulin delivery, a pump for insulin delivery, or another device; in a mobile computing device or a desktop computing device; and / or in one or more servers in a network cloud) can be configured to detect an impending delivery of a patient's diabetes therapy. In at least one example, the one or more processors can determine that an insulin injection is impending based on the patient's (recent) activity that includes movement of the patient (e.g., hand movement). Various hardware / software components (e.g., accelerometers, optical sensors, gyroscopes, etc.) can capture and record the patient's activity as user activity data, and by detecting certain gestures in the user activity data, the one or more processors can predict the occurrence of an insulin injection.

[0005] Certain gestures are equivalent to insulin injections that include the gesture, where the patient uses an injection device in a certain manner. If any of the patient's activities are sufficiently similar to these gestures, the patient is likely preparing to inject insulin into himself / herself. However, before the patient injects insulin, it may be beneficial to ensure that the correct amount of the type of insulin is being injected. As described in more detail, the one or more processors may generate information indicating the amount of insulin and / or the type of insulin dose in the insulin injection that the patient is most likely preparing based on the gesture. The one or more processors may compare the information indicating the amount or type of insulin dose with criteria for a proper insulin injection (such as dose, whether sufficient time has elapsed between insulin injections, whether food has been eaten between insulin injections, whether the patient is using basal insulin or bolus insulin based on the time of day, and other such examples). If the criteria are not met, the one or more processors may output an alert so that the patient does not inject himself / herself, or more generally, perform some modification to correct an impropriety associated with the insulin injection or improve the efficacy of the insulin injection.

[0006] Although the above examples have been described with respect to a patient, the technology is not limited thereto. Example techniques may be performed by a caregiver (e.g., at home or in a hospital), and the example techniques may be used for the caregiver. Generally, the technology may be applicable to a user, where user is a general term referring to one or both of the patient and the caregiver in combination.

[0007] In one example, the present disclosure describes a system having a wearable device configured to generate user activity data associated with a user's arm, and one or more processors configured to: identify at least one gesture indicative of preparing an insulin injection using an injection device based on the user activity data; generate information indicative of at least one of the amount or type of insulin dose in the insulin injection to be performed by the injection device based on the at least one identified gesture; compare the generated information with criteria for a proper insulin injection; and based on the comparison, output information indicating whether the criteria are met.

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

[0009] Figure 1 is a block diagram showing an example system for delivering or guiding a therapeutic dose in accordance with one or more examples described in the present disclosure.

[0010] Figure 2is a block diagram showing another example system for delivering or guiding a therapeutic dose according to one or more examples described in the present disclosure.

[0011] Figure 3 is a block diagram showing another example system for delivering or guiding a therapeutic dose according to one or more examples described in the present disclosure.

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

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

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

[0015] Figure 7A and 7B is a flowchart showing 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. There may be situations where the administration of diabetes therapy inadvertently affects the patient's health, for example, such that the patient receives an ineffective or incorrect amount or type of insulin. Since some patients manage their diabetes therapy themselves (e.g., via an injection device for delivering a dose of insulin), these patients have ample opportunity to affect (e.g., counteract) their glucose levels. Given that most people's lives are busy, a patient may be preoccupied with other things and completely forget to inject insulin at the recommended time. Sometimes, several minor disruptions throughout the day can interrupt the patient's recommended injection schedule. Even if the patient remembers the scheduled insulin injection, the patient may still forget the appropriate dose or type of insulin to administer. The patient may forget which settings to apply on the injection device to prepare to inject the appropriate amount and / or type of insulin. Even if the patient hires a caregiver to assist him / her with self-injecting insulin or performing insulin injections, the caregiver may make an error in administering the diabetes therapy.

[0017] It should be noted that a variety of injection devices are described herein as being applicable to the devices, systems, and techniques of the present disclosure. Some injection devices may be manual injection devices (e.g., syringes), while other injection devices (e.g., "smart" injection devices) may be equipped with processing circuitry and / or sensing technologies. In some instances, a "smart" cap may be configured to attach to a syringe or fit over an insulin pen. It should be noted that cloud services (e.g., running on a server in a network cloud) can provide many benefits to patients, including telemedicine services, managed care, and / or access to a network of healthcare professionals. Cloud services can operate with multiple devices (e.g., patient devices, caregiver devices, injection devices, and / or any other compatible computing device) to provide a remote monitoring system (e.g., CARELINK TM ), through which users can be notified of pending inappropriate diabetes therapies (e.g., inappropriate insulin injections), general and diabetes-specific health problems including health problems caused by inappropriate diabetes therapies, and other critical transmissions via alerts (e.g., CARE ALERT TM notification).

[0018] In the present disclosure, devices, systems, and techniques for managing a patient's glucose level include devices, systems, and techniques for gesture-based control of diabetes therapies. As described herein, gesture-based control involves protecting patients from the consequences of receiving incorrect and / or ineffective diabetes therapies in the form of, for example, inappropriate insulin injections. By detecting one or more gestures indicating that an insulin injection is about to occur or is occurring, devices, systems, and techniques for gesture-based control can determine whether certain aspects of the injection are inappropriate and have sufficient time to notify the user (e.g., the patient or caregiver) of one or more inadequacies in the user's pending injection (e.g., the settings of the injection device) before the user completes the insulin injection. In this way, the user has the opportunity to stop the insulin injection and / or modify the settings of the device to eliminate at least one inadequacy.

[0019] To illustrate by way of example, if a patient forgets a recent insulin injection and attempts to inject insulin at an inappropriate time and / or with an insufficient interval between injections, the devices, systems, and techniques described herein can output an alert indicating an inappropriate insulin injection. As an alternative, if a patient forgets an injection schedule and is about to miss a scheduled injection, the devices, systems, and techniques described herein can output an alert indicating a missed injection. One or more processors (e.g., in a mobile computing device referred to as a patient device, in a network cloud server providing cloud services, or in the injection device itself) can generate an alert containing any content type (e.g., video, audio, text) and output the alert by any mechanism (e.g., an electronic display, a tactile response (e.g., vibration), etc.).

[0020] One or more processors can generate an alert to notify any user of the injection device, including notifying the patient via the patient device or the injection device or notifying a home caregiver of the patient via a caregiver device. A caregiver can be a home caregiver (e.g., a family member or friend, a nurse, etc.), a healthcare professional (e.g., a doctor or a nurse) in a healthcare institution (e.g., a hospital), or another professional responsible for the patient's health. One or more processors can transmit the alert from the handheld patient device to the injection device, the network cloud server, and / or the caregiver device. As an alternative, one or more processors can transmit the alert from the network cloud server to the injection device, the patient device, and / or the caregiver device. In some instances where the processing circuitry within the injection device executes logic (e.g., processor-executable instructions or code) for gesture-based control, the injection device can generate an alert for display on an electronic display of the injection device itself and / or transmit the alert to the patient device, the network cloud server, the caregiver device, and / or another external device to notify the patient, the cloud service, and / or the caregiver.

[0021] Even if the user prepares an insulin injection at the appropriate time, the user may be able to prepare an injection with an ineffective dose and / or type of insulin. Some example patient gestures correspond to setting the dose and / or type on the injection device, and by detecting these gestures, the actual dose and / or type can be determined. For example, if the injection device has a dial for setting the dose, the patient can make a gesture of moving the dial and clicking it several times, where each click increases the amount of insulin loaded into the chamber of the injection device. This gesture can be detected by one or more sensors in a wearable device attached to the user's body, an activity monitor, and / or the injection device itself. If the detected dose does not match the recommended dose but is within a certain range, the detected dose can be considered ineffective, while a detected dose outside a certain range can be considered lethal. In some instances, compared to a lethal dose, a patient may not face serious consequences from receiving an ineffective dose of insulin. In response to a prediction of an upcoming injection of an ineffective or lethal dose, gesture-based control devices, systems, and techniques can notify the patient by displaying an alert configured to present various types of content (e.g., text, graphical content, video content, etc.) on an electronic display, as well as tactile and audible alerts. In some instances, gesture-based control devices, systems, and techniques can display data informing the patient which device settings to modify to correct the ineffective dose.

[0022] Depending on which injection device a given diabetic patient uses, the injection device can implement one or more techniques to detect an insulin injection (during preparation or after it occurs), record various information about each injection, and / or notify the patient (e.g., via a text warning or a sound alert) if there is a problem (e.g., improper) with any particular injection. Some manufacturers equip their injection devices with one or more sensors to perform the detection, recording, and notification described above; however, some patients use injection devices equipped with a minimal level of sensing technology or no sensing technology at all, leaving the patient or the patient's caregiver responsible for properly administering the patient's diabetes therapy. An external device with sensing technology (e.g., a wearable device, a patient device, or another mobile computing device) can provide sensor data for identifying one or more gestures indicative of an insulin injection. Some of the injection devices described herein (e.g., insulin pens or syringes) can be retrofitted with sensing technology (e.g., in a smart insulin pen cap).

[0023] Except for the injection devices described herein, other injection devices cannot provide gesture control and protection of patient health. These devices are limited in many areas, including understanding the appropriate diabetes therapy for a patient in terms of dose, insulin type (e.g., bolus insulin), dosing schedule, and other parameters. Even though some injection devices can detect the dose or insulin type in various ways, none of them can operate with a wearable device or another external device to identify the dose or insulin type.

[0024] The devices, systems, and techniques described herein are configured to mitigate or completely eliminate the limitations of the injection devices described above. In some instances, one or more sensors in a device can provide data describing various user activities (e.g., patient activities or caregiver activities) to one or more processors (e.g., processing circuitry) in the same device or a different device, the data including the movement of the user's hand and / or arm and / or the posture (e.g., positioning and / or orientation) of the user's hand when holding the injection device. Some example sensors can be communicatively coupled to one or more processors, while some sensors are directly coupled to one or more processors.

[0025] Accordingly, one or more processors can receive user activity data from one or more internal sensors, one or more sensors in the injection device, and / or one or more sensors in another device such as a wearable device attached to a body part of the patient. In one instance, a wearable device (referred to as a smartwatch) can be attached to a patient's hand and equipped with an inertial measurement unit (e.g., one or more accelerometers) that can capture user activities (e.g., user movement and / or user posture) including gestures equivalent to insulin injection. If the injection device is poorly configured or not configured with sensing technology, the accelerometer in the wearable device or another external device can provide user activity data that can predict insulin injection and / or injection device data that can confirm (or reject) the insulin injection prediction.

[0026] In some instances, the devices, systems, and techniques described herein can utilize data provided by an injection device to confirm a prediction of an insulin injection based on a user's recognition of one or more gestures. To illustrate by example, after a gesture for setting a dose and type on the injection device is recognized, a sensor can sense that a cartridge has been loaded into the injection device to prepare for administering an insulin injection, thereby confirming the gesture recognition. A user can provide input data (e.g., patient confirmation) to confirm the readiness of the insulin injection. The confirmation can be achieved through injection device data provided by other devices such as a device having a sensor for detecting an insulin dose in a syringe barrel. The sensor data can be used to predict that an insulin injection is ready and to predict that an insulin injection (e.g., recently) has occurred. A sensor for reading an insulin level in the injection device can measure a first insulin level and a second insulin level and determine that an intervening insulin injection has reduced the insulin level from the first level to the second level. One benefit of the confirmation is that user activity data supporting the prediction may be provided by unreliable external sensors and / or contain inaccurate or incorrect sensor data; indeed, the confirmation serves to mitigate the unreliability of external sensors and the inaccuracy or incorrectness of external sensor data. As another benefit of the confirmation, one or more processors can operate with an injection device that does not have any inertial measurement unit or other sensors. Indeed, confirmation through the injection device or injection device data allows one or more processors to rely on a wearable device to obtain user activity data without implementing internal sensors or relying on the sensors of the injection device.

[0027] Figure 1 is a block diagram showing an example system for delivering or guiding a therapeutic dose in accordance with one or more instances described in the present disclosure. Figure 1 Shows system 10A, which includes patient 12, insulin pump 14, tubing 16, infusion set 18, sensor 20 (which can be a glucose sensor), wearable device 22, patient device 24, and cloud 26. Cloud 26 represents a local area wide or global computing network that includes one or more processors 28A - 28N (“one or more processors 28”). In some instances, 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.

[0028] Patient 12 may have diabetes (e.g., type 1 diabetes or type 2 diabetes), and thus, the glucose level of patient 12 may be uncontrolled without the delivery of supplemental insulin. For example, patient 12 may not be able to produce enough insulin to control the glucose level, or due to insulin resistance that patient 12 may have developed, the amount of insulin produced by patient 12 may be insufficient.

[0029] To receive supplemental insulin, patient 12 may carry an insulin pump 14 coupled to a tube 16 for delivering insulin into patient 12. An infusion set 18 may be connected to the skin of patient 12 and include a cannula for delivering insulin into patient 12. A sensor 20 may also be coupled to patient 12 to measure the glucose level of patient 12. The insulin pump 14, the tube 16, the infusion set 18, and the sensor 20 may together form an insulin pump system. An example of an insulin pump system is the MINIMED TM 670G insulin pump system of Medtronic, Inc. However, other examples of insulin pump systems may be used, and the example techniques should not be considered limited to the MINIMED TM 670G insulin pump system. For example, the techniques described in this disclosure may be used for insulin pump systems that include wireless communication capabilities. However, the example techniques should not be considered limited to insulin pump systems with wireless communication capabilities, and other types of communication such as wired communication are also possible. In another example, the insulin pump 14, the tube 16, the infusion set 18, and / or the sensor 20 may be contained within the same housing.

[0030] The insulin pump 14 may be a relatively small device that patient 12 may place in different locations. For example, patient 12 may clip the insulin pump 14 to the waistband of the pants that patient 12 is wearing. In some examples, for discretion, patient 12 may place the insulin pump 14 in a pocket. Generally, the insulin pump 14 may be worn in different places, and patient 12 may place the insulin pump 14 in a certain location based on the particular clothing that patient 12 is wearing.

[0031] To deliver insulin, the insulin pump 14 includes one or more reservoirs (e.g., two reservoirs). The reservoir may 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 may be a battery-powered device powered by a replaceable and / or rechargeable battery.

[0032] The tube 16, sometimes referred to as a catheter, is connected at a first end to a reservoir in the insulin pump 14 and at a second end to the infusion set 18. The tube 16 may carry insulin from the reservoir of the insulin pump 14 to patient 12. The tube 16 may be flexible, allowing it to loop or bend to minimize concerns that the tube 16 will become detached from the insulin pump 14 or the infusion set 18 or that the tube 16 will break.

[0033] The infusion device 18 may include a thin cannula that the patient 12 inserts into the subcutaneous fat layer (e.g., subcutaneous connection). The infusion device 18 may rest near the patient 12's stomach. Insulin travels from the reservoir of the insulin pump 14 through the tubing 16, through the cannula in the infusion device 18, and into the patient 12's body. In some instances, the patient 12 may use an infusion device insertion device. The patient 12 may place the infusion device 18 into the infusion device insertion device, and upon pressing a button on the infusion device insertion device, the infusion device insertion device may insert the cannula of the infusion device 18 into the patient 12's fat layer, and with the cannula inserted into the patient 12's fat layer, the infusion device 18 may rest on top of the patient's skin.

[0034] The sensor 20 may include a cannula inserted subcutaneously in the patient 12, such as near the patient 12's stomach or in the patient 12's arm (e.g., subcutaneous connection). The sensor 20 may be configured to measure interstitial glucose levels, which are the glucose found in the fluid between the patient 12's cells. The sensor 20 may be configured to continuously or periodically sample the glucose level and the rate of change of the glucose level over time.

[0035] In one or more instances, the insulin pump 14 and the sensor 20, as well as Figure 1 the various components shown therein may together form a closed-loop therapy delivery system. For example, the patient 12 may set a target glucose level on the insulin pump 14, typically measured in milligrams per deciliter. The insulin pump 14 may receive the current glucose level from the sensor 20 and, in response, may increase or decrease the amount of insulin delivered to the patient 12. For example, if the current glucose level is higher than the target glucose level, the insulin pump 14 may increase the insulin. If the current glucose level is lower than the target glucose level, the insulin pump 14 may temporarily stop delivering insulin. The insulin pump 14 may be considered an example of an automated insulin delivery (AID) device. Other examples of AID devices are possible, and the techniques described in this disclosure may be applicable to other AID devices.

[0036] For example, the insulin pump 14 and the sensor 20 can be configured to operate together to mimic some of the ways in which a healthy pancreas functions. The insulin pump 14 can be configured to deliver basal insulin, which is a small amount of insulin that is continuously released throughout the day. Sometimes glucose levels can rise, such as due to eating or some other activity performed by the patient 12. The insulin pump 14 can be configured to deliver bolus insulin as needed in association with food intake or to correct an undesirably high glucose level in the bloodstream. In one or more instances, if the glucose level rises above a target level, the insulin pump 14 can increase the bolus insulin to address the rise in glucose level. The 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, the 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 lower the glucose level in response to a rise in glucose level due to eating or some other event.

[0037] Thus, 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., via a wireless link connection such as Bluetooth or BLE). The insulin pump 14 can compare the glucose level with a 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., how the glucose level is expected to be in the next 30 minutes), and the insulin pump 14 can adjust insulin delivery based on the predicted glucose level.

[0038] As described above, the patient 12 or a clinician can set a target glucose level on the insulin pump 14. The patient 12 or a clinician can set the target glucose level on the insulin pump 14 in a variety of ways. As an example, the patient 12 or a clinician can communicate with the insulin pump 14 using the patient device 24. Examples of the patient device 24 include mobile devices such as smartphones or tablet computers, laptop computers, etc. In some instances, the patient device 24 can be a special programmer or controller for the insulin pump 14. Although Figure 1 a single patient device 24 is shown, in some instances, there can be multiple patient devices. For example, the system 10A can include a mobile device and a controller, each of which is an instance of the patient device 24. For ease of description only, the example techniques are described with respect to the patient device 24, and it should be understood that the patient device 24 can be one or more patient devices.

[0039] The patient device 24 may also be configured to engage with the sensor 20. As an example, the patient device 24 may receive information from the sensor 20 via the insulin pump 14, where the insulin pump 14 relays information between the patient device 24 and the sensor 20. As another example, the patient device 24 may receive information (e.g., glucose level or rate of change of glucose level) directly from the sensor 20 (e.g., via a wireless link).

[0040] In one or more instances, the patient device 24 may display a user interface by which the patient 12 or a clinician may control the insulin pump 14. For example, the patient device 24 may display a screen that permits the patient 12 or a clinician to enter a target glucose level. As another example, the patient device 24 may display a screen that outputs current and / or past glucose levels. In some instances, the patient device 24 may output notifications to the patient 12, such as notifications of too high or too low glucose levels and notifications regarding any actions the patient 12 needs to take. For example, if the battery of the insulin pump 14 is low, the insulin pump 14 may output a low battery indication to the patient device 24, and the patient device 24 may in turn output a notification to the patient 12 to replace or charge the battery.

[0041] Controlling the insulin pump 14 via the patient device 24 is one example and should not be considered limiting. For example, the insulin pump 14 may include a user interface (e.g., buttons) that permits the patient 12 or a clinician to set various glucose levels of the insulin pump 14. Moreover, in some instances, the insulin pump 14 itself or as a supplement to the patient device 24 may 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 may output an audible or tactile output. As another example, if the battery is low, the insulin pump 14 may output a low battery indication on the display of the insulin pump 14.

[0042] The example manner in which the insulin pump 14 may deliver insulin to the patient 12 based on a current glucose level (e.g., measured by the sensor 20) was described above. In some cases, a therapeutic gain may be achieved by actively delivering insulin to the patient 12 rather than reacting when the glucose level becomes too high or too low.

[0043] Due to a specific user action, the glucose level of the patient 12 may increase. As an example, the glucose level of the patient 12 may rise due to the patient 12 engaging in activities such as eating or exercising. In some instances, if it can be determined that the patient 12 is engaging in an activity and insulin is delivered based on the determination that the patient 12 is engaging in the activity, a therapeutic gain may exist.

[0044] For example, patient 12 may forget to have insulin pump 14 deliver insulin after eating, resulting in insufficient insulin. Alternatively, patient 12 may have insulin pump 14 deliver insulin after eating but may forget that patient 12 previously had insulin pump 14 deliver insulin for the same meal event, resulting in an excessive insulin dose. Also, in an example where sensor 20 is used, insulin pump 14 may not take any action until the glucose level is greater than the target level. By actively determining that patient 12 is engaged in an activity, insulin pump 14 can deliver insulin in a manner such that the glucose level does not rise above the target level or rises only slightly above the target level (i.e., less than it would rise without active insulin delivery). In some cases, by actively determining that patient 12 is engaged in an activity and delivering insulin accordingly, the glucose level of patient 12 can rise more slowly.

[0045] Although the above describes actively determining that patient 12 is eating and delivering insulin accordingly, the example techniques are not limited thereto. The example techniques can be used to actively determine the activity that patient 12 is performing (e.g., eating, exercising, sleeping, driving, etc.). Insulin pump 14 can then deliver insulin based on the determination of the type of activity that patient 12 is performing.

[0046] As Figure 1 shown, patient 12 can wear wearable device 22. Examples of wearable device 22 include a smartwatch or a fitness tracker, either of which can be configured to be worn on the wrist or arm of the patient in some examples. In one or more examples, wearable device 22 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 22 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 frequency, amplitude, trajectory, position, speed, acceleration, and / or pattern of movement instantaneously or over time. The movement frequency of the patient's arm can refer to how many times patient 12 repeats a movement within a certain time (e.g., the frequency of moving back and forth between two positions). Wearable device 22 can be configured to determine one or more pose characteristics of patient 12, including values related to position and / or orientation.

[0047] Patient 12 can wear wearable device 22 on his or her wrist. However, the example techniques are not limited thereto. Patient 12 can wear wearable device 22 on a finger, forearm, or bicep. Generally, patient 12 can wear wearable device 22 anywhere that can be used to determine a gesture indicating eating (such as a movement characteristic of the arm).

[0048] The way (i.e., movement characteristics) in which patient 12 is moving his or her arm can refer to the direction, angle, and orientation of patient 12's arm, including values related to the frequency, amplitude, trajectory, position, speed, acceleration, and / or pattern of the movement instantaneously or over time. As an example, if patient 12 is eating, patient 12's arm will be oriented in a specific way (e.g., the thumb facing patient 12's body), the angle of the movement of the arm will move at approximately 90 degrees (e.g., from the plate to the mouth), and the direction of the movement of the arm will be the path from the plate to the mouth. The forward / backward, up / down, pitch, roll, yaw measurements from wearable device 22 can indicate the way in which patient 12 is moving his or her arm. Also, patient 12 can have a certain frequency or pattern in which patient 12 moves his or her arm, which is more indicative of eating compared to other activities such as smoking or using an e-cigarette, where patient 12 can lift his or her arm to his or her mouth.

[0049] Although the above description describes wearable device 22 as being used to determine whether patient 12 is eating, wearable device 22 can be configured to detect the movement of patient 12's arm (e.g., one or more movement characteristics), and the movement characteristics can be used to determine the activity that patient 12 is performing. For example, the movement characteristics detected by wearable device 22 can indicate whether patient 12 is exercising, driving, sleeping, etc. As another example, wearable device 22 can indicate the posture of patient 12, which can be consistent with postures for exercising, driving, sleeping, etc. Another term for movement characteristics can be gesture movement. Thus, wearable device 22 can be configured to detect gesture movement (i.e., the movement characteristics of 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, injecting insulin, etc.).

[0050] In some instances, wearable device 22 can be configured to determine the specific activity that patient 12 is performing based on the detected gesture (e.g., the movement characteristics of patient 12's arm) and / or posture. For example, wearable device 22 can be configured to determine whether patient 12 is eating, exercising, driving, sleeping, etc. In some instances, wearable device 22 can output information indicating the movement characteristics of patient 12's arm and / or the posture of patient 12 to patient device 24, and patient device 24 can be configured to determine the activity that patient 12 is performing.

[0051] The wearable device 22 and / or the patient device 24 can be programmed with information that the wearable device 22 and / or the patient device 24 uses to determine a specific activity that patient 12 is performing. For example, patient 12 can perform various activities throughout the day, where the movement characteristics of patient 12's arm can be similar to the movement characteristics of patient 12's arm for a specific activity, but patient 12 is not performing the activity. As an example, patient 12 yawning and making his or her mouth into a cup shape may be similar to the movement of patient 12 eating. Patient 12 picking up something may be similar to the movement of patient 12 exercising. Also, in some instances, patient 12 may be performing a specific activity, but the wearable device 22 and / or the patient device 24 may fail to determine that patient 12 is performing a specific activity.

[0052] Accordingly, in one or more instances, the wearable device 22 and / or the patient device 24 can "learn" to determine whether patient 12 is performing a specific activity. However, the computing resources of the wearable device 22 and the patient device 24 may be insufficient to perform the learning required to determine whether patient 12 is performing a specific 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, the following is described with respect to one or more processors 28 in the cloud 26.

[0053] As Figure 1 shown, system 10A includes a cloud 26 that includes one or more processors 28. For example, cloud 26 includes a plurality of network devices (e.g., servers), and each of the plurality of devices includes one or more processors. One or more processors 28 can be the processors of the plurality of network devices and can be located within a single network device of the network devices or can be distributed across two or more of the network devices of the network devices. Cloud 26 represents a cloud infrastructure of one or more processors 28 that supports the running of application programs or operations requested by one or more users thereon. For example, cloud 26 provides cloud computing to store, manage, and process data on network devices using one or more processors 28 rather than through personal device 24 or wearable device 22. One or more processors 28 can share data or resources for performing computations and can be part of a compute server, a web server, a database server, etc. One or more processors 28 can be in network devices (e.g., servers) within a data center or can be distributed across multiple data centers. In some cases, the data centers can be in different geographical locations.

[0054] One or more processors 28 and other processing circuitry described herein can 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 circuitry, as well as any combination of such components. The functions attributed to one or more processors 28 and other processing circuitry described herein can be embodied as hardware, firmware, software, or any combination thereof.

[0055] One or more processors 28 can be implemented as fixed function circuitry, programmable circuitry, or a combination thereof. Fixed function circuitry refers to circuitry that provides a specific function and is pre-set in terms of the operations it can perform. Programmable circuitry refers to circuitry that can be programmed to perform various tasks and provides flexible functionality in terms of the operations it can perform. For example, programmable circuitry can execute software or firmware that causes the programmable circuitry to operate in a manner defined by instructions of the software or firmware. Fixed function circuitry can execute software instructions (e.g., to receive parameters or output parameters), but the type of operations performed by the fixed function circuitry is generally immutable. In some instances, one or more of the units can be different circuit blocks (fixed function or programmable), and in some instances, the one or more units can be integrated circuits. One or more processors 28 can include an arithmetic logic unit (ALU), elementary function unit (EFU), digital circuitry, analog circuitry, and / or programmable cores formed by programmable circuitry. In instances where software executed by programmable circuitry is used to perform the operations of one or more processors 28, the memory accessible to one or more processors 28 (e.g., on a server) can store the object code of the software that one or more processors 28 receive and execute.

[0056] In some instances, one or more processors 28 can be configured to determine a mode based on gesture movements (e.g., one or more movement characteristics determined by wearable device 22), and be configured to determine a specific activity that patient 12 is performing. One or more processors 28 can provide a real-time response cloud service that can determine, on a real-time response basis, the activity that patient 12 is performing, and in some instances, provide a recommended therapy (e.g., the amount of an insulin dose). Cloud 26 and patient device 24 can communicate via Wi-Fi or via a carrier network.

[0057] 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 indicative of movement characteristics of the arm of the patient 12 to the cloud 26 and may have other contextual information, such as location or time of day. 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.

[0058] An example manner is described in U.S. Patent Publication No. 2020 / 0135320A1, in which one or more processors 28 may be configured to determine that the patient 12 is performing an activity and to determine a treatment to be delivered. Generally, one or more processors 28 may first go through an initial "learning" phase, in which one or more processors 28 receive information to determine the behavior pattern of the patient 12. Some of this information may be provided by the patient 12. For example, the patient 12 may be prompted or he / she may himself / herself input into the patient device 24 information indicative of a particular activity that the patient 12 is performing, the duration of the activity, and other such information that one or more processors 28 may use to predict the behavior of the patient 12. After the initial learning phase, one or more processors 28 may still update the behavior pattern based on the most recently received information, but with less or no information from the patient 12.

[0059] During the initial learning phase, the patient 12 may provide information regarding the patient 12's dominant hand (e.g., right or left hand) and where the patient 12 wears the wearable device 22 (e.g., around the right or left wrist). The patient 12 may be instructed to wear the wearable device 22 on the wrist of the hand that the patient 12 uses to eat. The patient 12 may also provide information regarding the orientation of the wearable device 22 (e.g., the face of the wearable device 22 is on the top or bottom of the wrist).

[0060] During the initial learning phase, the patient 12 may actively or in response to a prompt / query (e.g., via the patient device 24) input information indicative of the patient 12's participation in an activity. During this time, the wearable device 22 may continuously determine one or more movement and / or posture characteristics (e.g., gestures) of the patient 12 and output such information to the patient device 24, which conveys the information to one or more processors 28. One or more processors 28 may store information of one or more movement characteristics of the movement of the arm of the patient 12 during the activity to later determine whether the patient 12 is participating in the activity (e.g., whether the information received regarding the manner and frequency of movement of the arm of the patient 12 is consistent with the stored information regarding the manner and frequency of movement of the arm of the patient 12 when it is known that the patient 12 is participating in the activity).

[0061] The above described the arm movement as a factor for determining whether patient 12 is participating in an activity. However, there may be various other factors that can be used alone or in combination with the arm movement to determine whether patient 12 is participating in an activity. As an example, patient 12 may participate in the activity at regular time intervals. As another example, patient 12 may participate in the activity at certain locations. During an initial learning phase, when patient 12 (e.g., via patient device 24) inputs that he or she is participating in the activity, patient device 24 may output information about the time of day and the location of patient 12. For example, patient device 24 may be equipped with a positioning device, such as a Global Positioning System (GPS) unit, and patient device 24 may output the location information determined by the GPS unit. There may be other ways to determine the location, such as based on Wi-Fi connection and / or access to 4G / 5G LTE, or some other form of access, such as tracking the device location of patient device 24 based on a telecommunications database. The time of day and the location are two examples of context information that can be used to determine whether patient 12 is participating in an activity.

[0062] However, there may be other examples of context information of patient 12, such as sleep patterns, body temperature, stress levels (e.g., based on pulse and respiration), heart rate, etc. Generally, there may be various biometric sensors (e.g., for measuring temperature, pulse / heart rate, respiration rate, etc.), and the various biometric sensors may be part of wearable device 22 or may be separate sensors. In some examples, the biometric sensors may be part of sensor 20.

[0063] The context information of patient 12 may include conditional information. For example, patient 12 may eat every 3 hours, but the exact time when patient 12 eats may vary. 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. Generally, any information that establishes a behavior pattern can be used to determine whether patient 12 is participating in a particular activity.

[0064] One or more processors 28 may utilize artificial intelligence such as machine learning or other data analysis techniques to determine whether patient 12 is engaging in an activity based on information determined and / or collected by wearable device 22 and patient device 24. As an example, during an initial learning phase, one or more processors 28 may utilize neural network techniques. For example, one or more processors 28 may receive training data from patient 12 for training a classifier module executed on one or more processors 28. As described above, when patient device 24 and / or wearable device 22 determine that patient 12 is engaging in an activity based on the way and frequency of movement of patient 12's arm (e.g., a gesture consistent with the movement of the arm during eating), one or more processors 28 may receive training data based on patient confirmation. One or more processors 28 may generate and store tagged data records that include features related to movement and other contextual features such as time of day or location. One or more processors 28 may train a classifier on a tagged data set that includes multiple tagged data records, and one or more processors 28 may use the trained classifier model to more accurately detect the start of a food intake event.

[0065] Other examples that may be used for neural networks include behavior patterns. For example, patient 12 may only eat a specific food after exercise and always eats the specific food after exercise. Patient 12 may eat at specific times and / or locations. Although described with respect to eating, there may be various conditions that together indicate the behavior pattern of patient 12 for different activities.

[0066] As another example, one or more processors 28 may utilize k-means clustering techniques to determine whether patient 12 is engaged in an activity. For example, during an initial learning phase, one or more processors 28 may receive different types of context information and form clusters, where each cluster represents a behavior of patient 12 (e.g., eating, sleeping, walking, exercising, etc.). For example, patient 12 may input information indicating that he or she is walking (e.g., inputting the information into patient device 24). One or more processors 28 may utilize all of the context information received while patient 12 is walking to form a first cluster associated with walking. Patient 12 may input information indicating that he or she is eating (e.g., inputting the information into patient device 24). One or more processors 28 may utilize all of the context information received while 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 may determine which cluster aligns with the context information and determine the activity that patient 12 is performing. As described in more detail, the type of activity and predictions 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.

[0067] There may be various other ways in which one or more processors 28 can 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.

[0068] During the initial learning phase, patient 12 may also input information about the activity that patient 12 is performing. For example, in the case of eating, patient 12 may input information indicating what patient 12 is eating and / or how many carbohydrates are in the food that patient 12 is eating. As an example, at 9:00 every morning, patient 12 may input that he or she is eating a bagel or that patient 12 is consuming 48 grams of carbohydrates.

[0069] In some instances, one or more processors 28 may be configured to determine the amount of insulin to be delivered to patient 12 (e.g., the bolus insulin therapy dose). As an example, a memory accessible by one or more processors 28 may store patient parameters of patient 12 (e.g., weight, height, etc.). The memory may also store a lookup table that indicates the amount of bolus insulin to be delivered for different patient parameters and different types of food. One or more processors 28 may access the memory and may determine the amount of bolus insulin that patient 12 is to receive based on the type of food that patient 12 is eating and the patient parameters.

[0070] As another example, one or more processors 28 may be configured to utilize a “digital twin” of patient 12 to determine the amount of bolus insulin that patient 12 is to receive. The digital twin may be a digital replica or model of patient 12. The digital twin may be software that executes on one or more processors 28. The digital twin may receive information about what patient 12 ate as input. Because the digital twin is a digital replica of patient 12, the output from the digital twin may be information about what the glucose level of patient 12 may be after eating and a recommendation as to how much bolus insulin to deliver to patient 12 to control the rise in glucose level.

[0071] For example, the digital twin may indicate what the correct dose should have been for a past meal of patient 12. In one or more instances, patient 12 may input information indicating the food that patient 12 ate, and one or more processors 28 may receive information about the glucose level. Using the information indicating the food that patient 12 ate and the glucose level, one or more processors 28 may utilize the digital twin to determine what the insulin dose should have been (e.g., based on how the digital twin models how the food will affect the glucose level of the patient). Then, at a subsequent time when predicting patient 12 eating the same meal, one or more processors 28 may determine what the insulin dose should be based on the insulin dose that the digital twin had previously determined.

[0072] Thus, in one or more instances, one or more processors 28 may utilize information about movement characteristics of the arm, eating speed, food consumption, food content, etc., while also keeping track of postural characteristics and other situational information. Examples of situational information include location information, time of day, wake-up time, amount of time since the last meal, calendar events, information about the people that patient 12 may be meeting with, etc. One or more processors 28 may identify patterns and correlations between all these various factors to determine the activities that patient 12 is performing, such as eating, walking, sleeping, driving, etc.

[0073] After an initial learning phase, one or more processors 28 may automatically and with minimal input from patient 12 determine that patient 12 is performing a particular activity and, based on that determination, determine the amount of bolus insulin to be delivered. One or more processors 28 may output a recommendation for the amount of bolus insulin to be delivered to patient device 24. Patient device 24 may then in turn control insulin pump 14 to deliver the determined amount of insulin. As an example, patient device 24 may output the amount of bolus insulin to be delivered to insulin pump 14 with or without user confirmation. As another example, patient device 24 may output a target glucose level, and insulin pump 14 may deliver insulin to achieve the target glucose level. In some instances, one or more processors 28 may output information indicative of a target glucose level to patient device 24, and patient device 24 may output the information to insulin pump 14. All of these instances may be considered instances where one or more processors 28 determine the amount of insulin to be delivered to patient 12.

[0074] The above describes example ways of determining whether patient 12 is performing an activity, determining the amount of insulin to be delivered, and causing 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 that causes problems (e.g., patient 12 forgetting to record a meal, forgetting to take insulin, or taking insulin but forgetting that it has already been taken) is decreased.

[0075] While the example techniques above may be beneficial for patient 12 to receive insulin at the correct time, the present disclosure describes example techniques for further actively controlling the delivery of insulin to patient 12. For example, an instance where patient 12 wears insulin pump 14 was described above. However, sometimes patient 12 may not be able to wear insulin pump 14 and may need to manually inject insulin. There may also be times when patient 12 does not have an insulin dose in the reservoir for insulin pump 14. The techniques described above for determining the amount of insulin to be delivered and when to deliver insulin may also be useful in situations where insulin pump 14 is not available. For example, as described in more detail below with respect to Figure 2 and 3 In addition to insulin pump 14, patient 12 may utilize an injection device, such as an insulin pen, syringe, etc. When using an injection device, patient 12 may miss a dose or enter an incorrect amount of insulin even when notified to inject himself / herself.

[0076] The present disclosure describes examples of using activity data to determine gesture information indicative of a patient 12 (or possibly a caregiver) preparing to inject insulin or actually injecting insulin. Example techniques can determine whether the criteria for a proper insulin injection are met and can warn the patient 12 if the criteria are not met.

[0077] Specifically, the present disclosure describes example techniques for controlling the delivery of therapy to a diabetic patient, where the therapy involves timely injection of an effective amount of the correct type of insulin. To implement these techniques, one or more processors 28 can first predict that an insulin injection is about to occur in response to the recognition of one or more gestures indicative of an insulin injection, and then determine whether the predicted insulin injection is appropriate or inappropriate for the patient 12 by comparing the parameter data and other information of the insulin injection with established criteria for a proper insulin injection. The parameter data and other information can indicate the amount or type of insulin dose.

[0078] The established criteria can be communicated by a web server of a cloud service that controls the injection device 30, the patient device 24, or any other compatible device, and / or can be input by a healthcare professional using the injection device 30, the patient device 24, or any other compatible device. The established criteria can include recommendations and / or valid values / categorizations of various insulin injection parameters, the various insulin injection parameters including insulin dose, insulin type, and / or injection schedule (or alternatively, the time interval between injections). Examples of criteria for a proper insulin injection include one or more of the following: the number of clicks (or rotations of an insulin pen dial) for setting an insulin dose, the amount of time elapsed between insulin injections, whether the user has eaten between insulin injections, whether basal insulin is being injected into the patient based on the time of day or whether bolus insulin is being injected into the patient based on the time of day. Some techniques employ additional parameters and / or different parameters, including injection site / area, trajectory, etc. If the parameter data of the insulin injection do not meet the criteria for a proper insulin injection, one or more processors 28 can output an alert notifying the patient 12 that an inappropriate insulin injection is about to occur for display on an electronic display.

[0079] In some instances, one or more processors 28 may build a data model that is configured to distinguish user activities, such as a user activity of injecting insulin from a user activity of eating. During an initial learning phase, by training the data model with user activity data and infusion device data, one or more processors 28 may generate a data model for identifying any user activity mentioned in the present disclosure. In some instances, one or more processors 28 may employ the trained data model to predict whether patient 12 has eaten any food based on characteristics derived from movement characteristics, posture characteristics, and other contextual information that serves as features. In some instances, one or more processors 28 may employ the trained data model to determine whether to predict that patient 12 is using basal insulin or bolus insulin.

[0080] Figure 2 is a block diagram showing another example system for delivering or guiding a therapeutic dose in accordance with one or more instances described in the present disclosure. Figure 2 shows a system 10B similar to Figure 1 system 10A. However, in system 10B, patient 12 may not have an 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 possibly a caregiver of patient 12) may fill a syringe with insulin or set a dose in an insulin pen and inject himself or herself.

[0081] System 10B implementing the example techniques and devices described herein protects patient 12 from injecting himself or herself with insulin at an inappropriate time and / or in an inappropriate (e.g., ineffective) dose or type. To achieve such protection, one or more processors 28 may compare information indicating the current time or a set amount and / or type of a pending insulin injection with criteria for appropriate insulin injection, and if the comparison indicates that at least one criterion is not met, employ a technique to stop (or delay) the pending insulin injection and / or modify the set amount and / or type of insulin. As a result, one or more processors 28 prevent the injection of an incorrect amount and / or type of insulin to the patient and / or an injection at an incorrect time. The consequences of improper insulin injection can range from mild discomfort to a significant decline in the patient's health. For example, if not enough time has elapsed between a previous insulin injection and the current insulin injection, the patient may completely forget the previous insulin injection. If patient 12 has not eaten any food between injections, the patient may eventually experience low glucose levels.

[0082] In system 10B, one or more processors 28 capture sensor data (i.e., user activity data) provided by one or more inertial measurement units (e.g., in wearable device 22) that indicates various user activities. At least a portion of this user activity data captures characteristics of user movement and / or user posture while holding any injection device; examples of such characteristics include user hand movement, user hand posture (e.g., positioning / orientation), etc. The user can be patient 12, a caregiver of patient 12, or any other provider of insulin injections for patient 12. As described herein, the captured user activity data can include all user activities and is not specific to user activities involving an insulin pen or syringe or another manual injection device. At least for this reason, the user activity data can include gestures that may be misinterpreted as indicating an insulin injection. For example, refilling a syringe and preparing / administering an insulin injection with a syringe can involve the same or similar gestures, and any user activity indicating such a refilling event constitutes a marker that an insulin injection did not occur.

[0083] Additionally, the user activity data may contain inaccuracies, for example, due to limitations of one or more inertial measurement units. When the inertial measurement units in wearable device 22 generate sensor data (e.g., accelerometer data), the data is typically raw or unrefined. User activity data can be a higher-level abstraction of the sensor data generated by one or more sensors. While accelerometer data can describe two positions in three-dimensional space and the movement between those positions, the captured user activity data can describe the same movement in different spaces or a combination of two or more movements between positions in three-dimensional space. User activity data can describe a gesture or a portion of a gesture as a cohesive sequence of patient movement.

[0084] For any type of injection device, one or more processors 28 implementing the example techniques can build and train a data model until the data model can distinguish gestures indicating insulin injection from other patient gestures. By way of illustration, an example data model can use accelerometer data to define movement characteristics (e.g., vibration, acceleration, etc.), pose characteristics (e.g., positioning and orientation), and other characteristics of a pose that holds the injection device in a particular position and / or particular orientation to administer a diabetes treatment. The particular position and / or particular orientation can be pre-determined (e.g., by the device manufacturer) and / or learned over time. The particular position and / or particular orientation can be suggested by a patient caregiver and / or determined by a medical professional to be effective (e.g., most effective) for a diabetes treatment. Another detectable gesture includes setting an insulin dose for a manual injection device (e.g., by pumping insulin into a syringe barrel, turning a dial on an insulin pen, etc.). Other detectable user activity gestures corresponding to manual insulin injection include gestures that move the injection device closer to the patient's body, gestures that return the manual injection device to a safe position (e.g., in a medical waste disposal unit), gestures that remove air bubbles from a manual injection device (e.g., syringe barrel), gestures that refill the manual injection device with a subsequent insulin dose (e.g., refill event), etc.

[0085] A given data model for gesture detection can define one or more detectable insulin injection instances as any combination of the above gestures. Some gestures are ranked higher than others and are given precedence. Some gestures are contemporaneous and often occur when injecting insulin. Some gestures are related to a possible impact on the effectiveness of the diabetes treatment administered to patient 12, such as the gesture of removing air bubbles from a manual injection device as described above. Although some example techniques and systems employ multiple sensors 20, a composite pose for delivering an insulin dose via a manual injection device can be detected using data provided by a single sensor 20 known as an inertial measurement unit (e.g., an accelerometer and a gyroscope). Detecting gestures for completing an insulin injection as described herein benefits patient 12 and provides immediate results when any user activity occurs or is about to occur. Patient 12 does not undertake complex setup and / or operation tasks. In some instances, patient 12 does not perform any activity other than the corresponding user activity for injecting an insulin dose, and one or more processors 28 (and / or hardware / software components of patient device 24) predict that an insulin injection is about to occur.

[0086] Before a patient 12 or a caregiver of patient 12 injects insulin, it may be beneficial to ensure that the appropriate amount and / or correct type of insulin is being injected. One or more processors 28 may generate information indicative of the amount of insulin and / or the type of insulin dose in an insulin injection that the patient 12 or the caregiver of patient 12 is most likely preparing, based on corresponding gestures. The one or more processors may compare the information indicative of the amount or type of insulin dose to criteria for an appropriate insulin injection. As described herein, the criteria for an appropriate insulin injection may specify recommendations for a patient's diabetes therapy, including a recommended insulin dose, insulin type, dosing regimen, whether sufficient time has elapsed between insulin injections, whether food has been consumed between insulin injections, whether the patient is using basal insulin or bolus insulin based on the time of day, etc. The criteria may further specify which insulin pen settings are to be activated to meet the above recommendations. If the criteria are not met, the one or more processors may output an alert so that the patient 12 or the caregiver of patient 12 does not inject the patient 12, or more generally, perform some modification to correct an impropriety associated with the insulin injection or improve the efficacy of the insulin injection.

[0087] To generate information indicative of the amount of insulin and / or the type of insulin dose in the insulin injection described above, one or more processors 28 may utilize a data model to detect corresponding gestures. An example corresponding gesture for setting the insulin dose and / or type may involve the number of clicks or amount of rotation on a dial of an insulin pen. Another example corresponding gesture for setting the insulin dose and / or type is loading a cartridge into an insulin pen or similar injection device. The one or more processors 28 improve the efficiency of detecting these gestures through device confirmation and / or patient confirmation. Another example corresponding gesture for setting the insulin dose and / or type in a syringe is aspirating insulin into a syringe barrel by drawing. Other contextual cues may (partially) identify the insulin type, such as the time of day and / or location. For example, long-acting insulin may typically be delivered first in the morning or before going to bed at night, while rapid-acting insulin may typically be delivered before a meal. Time and location cues may distinguish the respective time periods when long-acting insulin or rapid-acting insulin is more likely and appropriate.

[0088] Training and / or applying a data model to convert user activity data into detectable gestures consumes processing power and other resources. Although one or more processors 28 may utilize a trained data model to distinguish insulin injection from other user activities described in user activity data, structural and functional limitations may prevent the data model from rendering accurate predictions even through training. Other limitations associated with the inertial measurement unit in the wearable device 22 may further reduce the utility of user activity data. Although an example wearable device 22 (e.g., a smartwatch) that houses one or more inertial measurement units may capture user activity data indicative of wrist and hand movement, for various reasons, these movements may not accurately reflect the movement of a manual injection device. A patient may move, position, and / or orient a manual injection device without even creating a substantial amount of user activity data. The wearable device 22 may be on a hand different from the hand holding the manual injection device. As another limitation, a caregiver may administer an injection, resulting in no meaningful user activity data. There is no mechanism in the data captured by the wearable device to unambiguously identify that a patient or caregiver is using a manual injection device or any other injection device.

[0089] To minimize the above inaccuracies in the user activity data or data model provided by the wearable device 22 and / or to minimize the resource requirements for detection as much as possible, one or more processors 28 may use various data sets describing the utilization of a manual injection device, an injection device 30, or any other insulin delivery device by a patient or caregiver to confirm a detected gesture (e.g., confidence level). These data sets may be referred to herein as injection device data, and examples thereof include user input data provided through an input mechanism and / or sensor data provided by the patient device 24, a network device of a cloud service, the insulin delivery device itself, and / or an external device of the patient 12. In fact, the confirmation of any detected gesture alleviates the above limitations of the wearable device 22.

[0090] When a detected gesture may identify (e.g., predict) an insulin injection, in response to a possible identification (e.g., prediction) of an insulin injection, some example devices, systems, and techniques of the present disclosure further benefit the patient 12 through example injection device data indicating at least device confirmation or patient confirmation. In patient confirmation, an inquiry as to whether an insulin injection is about to occur or is occurring is presented to the patient 12, and through user input, the patient 12 confirms or denies a pending or recently occurred insulin injection through any injection device embodiment including any manual injection device. In device confirmation, one or more processors 28 utilize accurate data describing the injection device (e.g., user operation) of the manual injection device including Figure 3 to confirm or reject the prediction.

[0091] ForFigure 2 For a manual injection device, one or more processors 28 may be configured to confirm or reject a prediction of an insulin injection based on injection device data. Since a manual injection device may not be equipped with any sensing technology to assist in confirming or rejecting such predictions, one or more processors 28 utilize another source to access the injection device data. For some manual injection devices, one or more processors 28 may query the injection device data from the patient device 24 or another device (e.g., a smart cap attached to an insulin pen, a smart phone, etc.). For example, a smart phone may include sensing technology (e.g., optical or electro-optical sensors, a combination of an optical sensor and an LED, an accelerometer, an ambient light sensor, a magnetometer, a gyroscope, a camera, etc.) for recording example injection device data of a most recently occurred manual injection.

[0092] One or more processors 28 may establish various criteria (e.g., standards, thresholds, conditions, etc.) to confirm an insulin injection prediction based on user activity data provided by the wearable device 22. Using a set of example criteria to confirm (or reject) any given prediction, one or more processors 28 may utilize the injection device data (a more accurate source of information) as evidence to corroborate an initial gesture detection based on the user activity data provided by the wearable device 22. Synthesizing the injection device data with the user activity data provides a complete picture of the patient's activity when using any injection device. A set of example criteria may only require the above vibration data, while another set of example criteria may require two vibration data. Additionally (or alternatively), one or more processors 28 may compare the user activity data with the injection device data for various markers where an insulin injection did not occur, and if sufficient markers are identified in the comparison, reject the contrary prediction. It should be noted that, as described herein, machine learning concepts are incorporated into gesture detection; at least for this reason, the devices, systems, and techniques of the present disclosure may utilize established learning mechanisms to more accurately predict the time when an insulin injection is about to occur or is occurring, regardless of whether one or more processors 28 confirm or reject a prediction of a manual insulin injection. Some example learning mechanisms adjust the data model by, for example, adjusting the insulin injection definition with different gestures, adjusting the feature values or defining different features for the gesture, adjusting the prediction process of the data model (e.g., mathematical functions, probability distributions, etc.), adjusting the metrics of the data model or the method for measuring user activity based on the data provided by the wearable device 22 (e.g., accelerometer data), and / or adjusting the data model in another way.

[0093] Figure 3 is a block diagram showing another example system for delivering or guiding a therapeutic dose according to one or more instances described in the present disclosure. Figure 3 shows similar toFigure 1 System 10A and Figure 2 System 10C of System 10B. 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 possibly a caregiver of patient 12) may use injection device 30 to inject himself or herself.

[0094] Injection device 30 may be different from a syringe because injection device 30 may be a device capable of communicating with patient device 24 and / or other devices in System 10C. Moreover, injection device 30 may include a reservoir and may be able to dispense as much insulin for delivery based on information indicating how much therapy dose is to be delivered. For example, injection device 30 may automatically set the amount of insulin based on information received from patient device 24. In some instances, injection device 30 may be similar to insulin pump 14 but not worn by patient 12. An example of injection device 30 is an insulin pen, which is sometimes also referred to as a smart insulin pen. Another example of injection device 30 may be an insulin pen with a smart cap, where the smart cap may be used to set a specific insulin dose.

[0095] The above examples describe insulin pump 14, a syringe, and 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 insulin pump 14, a syringe, and injection device 30. As described, a syringe may be a device for injecting insulin but not necessarily capable of communicating or dispensing a specific amount of insulin. However, injection device 30 may be a device for injecting insulin and may be capable of communicating with other devices (e.g., via Bluetooth, BLE, and / or Wi-Fi) or may be capable of dispensing a specific amount of insulin. Injection device 30 may be a powered (e.g., battery-powered) device, and a syringe may be a device that does not require power.

[0096] To provide gesture-based diabetes therapy control using an insulin delivery device (e.g., insulin pump 14, a syringe, and / or injection device 30), example techniques and systems implement a data model that defines certain user activities as gestures; examples of defined gestures include gesture groups (e.g., sequences) that, when combined, form an example insulin injection of an insulin delivery device. One or more processors 28 of patient device 24 may detect data indicative of an insulin injection by comparing the movement and / or pose of a user (e.g., a patient) of the defined insulin injection gesture in an example data model implementation with the movement of the patient and / or the patient pose corresponding to the gesture when patient 12 holds the insulin delivery device.

[0097] To detect gestures when a patient 12 controls an injection device 30, some example devices, systems, and techniques in this disclosure implement the same or similar data models for detecting gestures when a patient 12 controls a manual injection device. One reason is that user activity data generated to record the gestures of a user (e.g., patient 12 or a caregiver of patient 12) while holding a manual injection device may be similar to user activity data generated to record the gestures of a user (e.g., patient 12 or a caregiver of patient 12) while holding injection device 30. Even if the user activity data is somewhat different (e.g., in a different format), substantially the same sensors are used to record the movement characteristics and / or posture characteristics of the patient's arm and hand while utilizing (e.g., holding and operating) injection device 30. Although there may be differences in how patient 12 performs gestures in injection device 30 to set the insulin dose and / or type as opposed to a syringe, these differences represent movement characteristics that can be written as definitions for specific gestures for injection device 30. For example, instead of loading a syringe barrel with insulin, patient 12 operates dials and other control devices on injection device 30 to set the next insulin dose and / or type. At least for these reasons, one or more processors 28 of patient device 24 can apply substantially the same data model to detect a posture (e.g., gesture) indicating insulin injection with injection device 30 in user activity data generated from data provided by one or more (external) sensors in an external device such as wearable device 22.

[0098] Because the wearable device 22 operates as a source of user activity data for both the manual injection device and the injection device 30 for the same external device, there may be the same limitations in predicting insulin injections performed by the injection device 30. To mitigate and / or eliminate some or all of these limitations, one or more processors 28 of the patient device 24 may execute a mechanism configured to confirm or reject a prediction that an insulin injection is about to occur or is occurring. In some instances, one or more processors 28 of the patient device 24 provide device confirmation and / or patient confirmation. In one instance, one or more processors 28 of the patient device 24 may communicate a request to confirm or reject a prediction of an insulin injection to the injection device 30 by way of device confirmation and / or patient confirmation. In turn, the injection device 30 communicates a response indicating confirmation or rejection based on internal injection device data and / or input data from the patient 12. If the injection device 30 has been set up to inject the patient 12 or has injected the patient 12 and has recorded the injection, the injection device 30 responds to the request with an affirmative device confirmation. On the other hand, if the injection device 30 has not been set up to inject the patient 12 or has not recently injected the patient 12, the injection device 30 responds to the request with a negative device rejection. The injection device 30 may output an inquiry to the patient 12 as to whether the patient 12 is about to inject insulin, and based on input data provided by the patient and indicating the patient 12's response, the injection device 30 may respond to the patient device 24 with an affirmative patient confirmation or a negative patient rejection (e.g., a negative). In an example device confirmation, one or more processors 28 of the patient device 24 communicate a query for medical record data to a communication component of the injection device 30, the medical record data including record data of any recent insulin injections. If the timestamp of the most recent insulin injection matches the timestamp of the prediction that an insulin injection is about to occur, one or more processors 28 of the patient device 24 may determine that the injection device 30 is confirming the prediction of the occurrence of an insulin injection. In another instance of device confirmation, one or more processors 28 of the patient device 24 may access an application programming interface provided by the injection device 30 and call an interface function configured to provide confirmation or rejection of a prediction of an insulin injection.

[0099] The above examples describe the insulin pump 14, syringe, and injection device 30 as example ways of delivering insulin. In the present disclosure, the term "insulin delivery device" can generally refer to a device for delivering insulin. Examples of insulin delivery devices include the insulin pump 14, syringe, and injection device 30. As described, a syringe can be a device for injecting insulin but not necessarily capable of communicating or delivering a specific amount of insulin. However, the injection device 30 can be a device for injecting insulin and can be capable of communicating with other devices or can be capable of delivering a specific amount of insulin. The injection device 30 can be a powered (e.g., battery-powered) device, and the syringe can be a device that does not require power.

[0100] Figure 4 is a block diagram showing an example of a patient device in accordance with one or more examples described in the present disclosure. Although the patient device 24 can generally be described as a handheld computing device, the patient device 24 can be, for example, a laptop computer, cellular phone, or workstation. In some examples, the patient device 24 can be a mobile device such as a smartphone or tablet computer. In such examples, the patient device 24 can 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 can be a dedicated controller for communicating with the insulin pump 14, injection device 30, or smart cap for a manual injection device.

[0101] Although examples are described with one patient device 24, in some examples, the patient device 24 can be a combination of different devices (e.g., a mobile device and a controller). For example, the mobile device can provide access to one or more processors 28 of the cloud 26 via Wi-Fi or a carrier network, and the controller can provide access to the insulin pump 14. In such examples, the mobile device and the controller can communicate with each other via Bluetooth or BLE. Various combinations of the mobile device and the controller that together form the patient device 24 are possible, and the example techniques should not be considered limited to any one particular configuration.

[0102] As Figure 4 shown, the patient device 24 can include processing circuitry 32, memory 34, a user interface 36, telemetry circuitry 38, and a power supply 39. The memory 34 can store program instructions that, when executed by the processing circuitry 32, cause the processing circuitry 32 to provide the functions attributed to the patient device 24 throughout the present disclosure.

[0103] In some instances, the memory 34 of the patient device 24 may store multiple parameters, such as the amount of insulin to be delivered, the target glucose level, the delivery time, and the like. The processing circuitry 32 (e.g., via the telemetry circuitry 38) may output the parameters stored in the memory 34 to the insulin pump 14 or the injection device 30 to deliver insulin to the patient 12. In some instances, the processing circuitry 32 may execute a notification application stored in the memory 34, and the notification application outputs notifications to the patient 12 via the user interface 36, such as notifications of taking insulin, the amount of insulin, and the time of taking insulin.

[0104] The memory 34 may comprise any volatile, non-volatile, fixed, removable, magnetic, optical, or dielectric medium, such as RAM, ROM, hard disk, removable disk media, NVRAM, EEPROM, flash memory, and the like. The processing circuitry 32 may take the form of one or more microprocessors, DSPs, ASICs, FPGAs, programmable logic circuitry, etc., and the functions attributed to the processing circuitry 32 herein may be embodied as hardware, firmware, software, or any combination thereof.

[0105] The user interface 36 may include buttons or a keyboard, lights, 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 this disclosure, the processing circuitry 32 may present and receive therapy-related information via the user interface 36. For example, the processing circuitry 32 may receive patient input via the user interface 36. The patient input may be entered, for example, by pressing buttons or a keyboard, entering text, or selecting an icon from the touch screen. The patient input may be information indicating the food the patient 12 has eaten, such as whether the patient 12 has used insulin (e.g., via a syringe or the injection device 30) for an initial learning phase, and other such information.

[0106] The telemetry circuitry 38 includes any suitable hardware, firmware, software, or any combination thereof for communicating with another device such as the cloud 26, insulin pump 14, or injection device 30 (if applicable), wearable device 22, and sensor 20. The telemetry circuitry 38 can receive communications with the help of an antenna, which can be internal and / or external to the patient device 24. The telemetry circuitry 38 can also be configured to communicate with another computing device via wireless communication technology or directly 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 the IEEE 802.11, Bluetooth, or BLE specification sets, infrared communication such as according to the IrDA standard, or other standard or proprietary telemetry protocols. The telemetry circuitry 38 can also provide a connection to a carrier network to access the cloud 26. In this way, other devices can be enabled to communicate with the patient device 24.

[0107] The power source 39 delivers operating power to the components of the patient device 24. In some instances, the power source 39 can include a battery, such as a rechargeable or non-rechargeable battery. A non-rechargeable battery can be selected to last for several years, while a rechargeable battery can be inductively charged from an external device, for example, daily or weekly. Recharging of the rechargeable battery can be accomplished by using an alternating current (AC) outlet or by a proximal inductive interaction between an external charger and an inductive charging coil within the patient device 24.

[0108] Before a patient 12 or a caregiver of patient 12 injects insulin, it may be beneficial to ensure that the appropriate amount and / or correct type of insulin is injected. As described herein, there are many opportunities for users of insulin delivery devices to administer inappropriate insulin injections. One or more processors of processing circuitry 32 or one or more processors 28 can access user activity data generated by one or more inertial measurement units and then generate, based on the user activity data, information indicative of the amount of insulin and / or the type of insulin dose in the insulin injection that patient 12 or a caregiver of patient 12 is most likely preparing based on a corresponding gesture. One or more processors of processing circuitry 32 (or one or more processors 28) can identify the corresponding gesture based on movement characteristics, posture characteristics, and other instances in the user activity data. Processing circuitry 32 (or one or more processors 28) can compare the information indicative of the amount or type of insulin dose with criteria for an appropriate insulin injection. As described herein, the criteria for an appropriate insulin injection can specify recommendations for a patient's diabetes therapy, including a recommended insulin dose, insulin type, dosing regimen, whether sufficient time has elapsed between insulin injections, whether food has been consumed between insulin injections, whether the patient is using basal insulin or bolus insulin based on the time of day, etc. The criteria can further specify which insulin pen settings are to be activated to meet the above recommendations. The criteria can be determined by the patient, caregiver, or any healthcare professional in authority via patient device 24 or cloud 26. The purpose of comparing information regarding the time, amount, and / or type of a pending insulin injection setting with criteria for an appropriate insulin injection is to prevent the patient from being injected with an incorrect amount and / or type of insulin and / or at an incorrect time. The consequences of improper insulin injection can range from mild discomfort to a significant decline in the patient's health. For example, if sufficient time has not elapsed between a previous insulin injection and the current insulin injection, the patient may completely forget the previous insulin injection. If patient 12 has not consumed any food between injections, the patient may ultimately experience low glucose levels.

[0109] If the criteria are not met, processing circuitry 32 can output an alert so that patient 12 or a caregiver of patient 12 does not inject patient 12, or more generally, perform some modification to correct the impropriety associated with the insulin injection or improve the efficacy of the insulin injection. In some instances, one or more processors 28 transmit instructions to patient device 28 that cause patient device 28 to output an alert.

[0110] Figure 5is a block diagram showing an example of a wearable device in accordance with one or more examples described in the present disclosure. As shown, the wearable device 22 includes processing circuitry 40, a memory 42, a user interface 44, telemetry circuitry 46, a power source 48, and an inertial measurement unit 50. The processing circuitry 40, the memory 42, the user interface 44, the telemetry circuitry 46, and the power source 48 may be similar to, respectively, Figure 3 the processing circuitry 32, the memory 34, the user interface 36, the telemetry circuitry 38, and the power source 39 of

[0111] The inertial measurement unit 50 may include a gyroscope and / or various components for determining the pitch-roll-yaw and x-y-z coordinates of the wearable device 22. In some examples, the inertial measurement unit 50 may be considered 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 circuitry 40 may be configured to determine one or more movement characteristics based on values from the inertial measurement unit 50. For example, the processing circuitry 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 those related to frequency, amplitude, trajectory, orientation, velocity, acceleration, and / or movement pattern. The processing circuitry 40 may determine the orientation of the patient 12's arm based on values from the inertial measurement unit 50, such as whether the back of the hand or the front of the hand is facing the patient 12 or whether the side of the hand is facing the patient 12 such that the thumb is facing the patient 12 and the index finger side is visible.

[0112] As an example, when the patient 12 is holding chopsticks to eat, the patient 12 may orient his or her wrist in a particular way, which may be different if the patient 12 is holding a sandwich. For different types of food, the frequency at which the patient 12 moves his or her arm from the position where he or she picks up the food to the position where he or she puts the food in his or her mouth may be different. For example, the frequency and movement pattern of eating with a fork may be different from that of eating with a spoon or a fork and knife, which may be different from eating with the hand (such as a sandwich or pizza). For all these different food items, the movement characteristics may be different, and the output values from the inertial measurement unit may also be different for the 50. However, for all movement characteristics, one or more processors (including the processing circuitry 40 in some examples) may be configured to determine that the patient 12 is eating.

[0113] One or more inertial measurement units 50 may output such information (e.g., pitch-roll-yaw and x-y-z 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 feeding event is occurring).

[0114] To enable detection of gestures corresponding to insulin injection for patient 12, inertial measurement unit 50 may generate various data indicative of the activity of patient 12 (e.g., pitch-roll-yaw and xyz coordinates) for output, the activity including the patient's utilization of injection device 30, a manual injection device, or any other device configured to deliver a diabetes therapy. Data generated by inertial measurement unit 50 (e.g., accelerometer data) may be processed into user activity data indicative of patient movement and / or patient posture corresponding to the patient's utilization of injection device 30. By comparing the user activity data to a data model configured to define gestures corresponding to insulin injection, one or more processors 28 of patient device 24 may detect one or more of these gestures and, in response to the detection, determine whether an insulin injection is predicted to occur.

[0115] If patient 12 is using a manual injection device, additional sensors may provide manual injection data to confirm the prediction. If patient 12 is using injection device 30, instead of having to use additional sensors and other hardware / software components to obtain manual injection device data, one or more processors 28 establish a communication channel with injection device 30 and receive (e.g., by request) data describing the operational details of one or more historical insulin injections. In this way, the prediction that an insulin injection is about to occur or is occurring may be confirmed or rejected based on the injection device data of the manual injection device or injection device 30.

[0116] While the example techniques above may benefit Patient 12 in receiving insulin at the right time, the present disclosure describes example techniques for further actively controlling the delivery of insulin to Patient 12. Specifically, the present disclosure describes example techniques for controlling the delivery of a therapy to a diabetic patient, where the therapy involves timely injection of an effective amount of the right type of insulin. To implement these techniques, one or more processors 28 may determine whether an upcoming insulin injection is appropriate or inappropriate for Patient 12 by comparing various injection parameters to established criteria. As described above, the established criteria may include recommendations and / or valid values / categorizations of injection parameters, which include insulin dose, insulin type, and / or injection schedule / time (or alternatively, the time interval between injections). Some techniques employ additional parameters and / or different parameters, including injection site / area, trajectory, etc.

[0117] Once confirmed and deemed appropriate, the recorded data of the insulin injection is stored, and the recorded time may include the injection time. Ensuring timely insulin injection prevents low glucose levels from occurring in Patient 12's blood. The same data model is continuously applied to user activity data over time, and when a subsequent insulin injection is detected, the detected time is compared to the recorded time of the previous injection. If the time difference is below the recommended time interval between appropriate insulin injections (i.e., too early), the patient device 24 outputs an alert warning Patient 12 in text and / or audio output. For example, if Patient 12 is preparing an insulin injection but the amount of time elapsed since the previous insulin injection is insufficient, Patient 12 may have forgotten the previous insulin injection, and if Patient 12 is not prevented from receiving the dose too early, an excess of insulin may accumulate in Patient 12's bloodstream, causing the cells in Patient 12's body to absorb too much glucose from the blood and / or Patient 12's liver and release less glucose (i.e., hypoglycemia). These two effects are typical consequences of inappropriate insulin injection.

[0118] Depending on the situation, a meal event may or may not result in a low glucose level in the blood of patient 12. If no meal is detected between insulin injections, even if the subsequent insulin injection is timely, patient 12 may eventually develop a low glucose level. This correlation holds in some cases where patient 12 does not even receive a subsequent insulin injection. Continuously applying the above data model to the user activity data streamed from the wearable device 22 can further ensure that patient 12 eats before a subsequent insulin injection. If one or more processors 28 (and / or one or more processors of the patient device 24) detect a meal event and a subsequent insulin injection at appropriate corresponding times based on the user activity data provided by the wearable device 22, one or more processors 28 can generate recorded data confirming the diabetes therapy and then store the recorded data as part of the medical history (i.e., medical record) of patient 12. On the other hand, if, after monitoring the user activity data provided by the wearable device 22, one or more processors 28 (and / or one or more processors of the patient device 24) fail to detect a meal event before detecting a subsequent insulin injection, the patient device 24 can output an alert notifying patient 12 (or the caregiver of patient 12) of the potential misconduct in the injection. In some instances, the patient device 24 outputs data requesting that patient 12 not perform the subsequent insulin injection at this time and / or eat before the injection. The patient device 24 can output data indicating an inquiry to patient 12 to answer whether patient 12 has eaten between injections.

[0119] An example reason for injecting rapid-acting insulin (the first type of insulin) may be to compensate for carbohydrates or correct hyperglycemia. When correcting hyperglycemia, the subsequent insulin dose can address the insulin-on-board from the previous injection. If a dose is given when patient 12 has normal blood glucose and one or more processors 28 fail to detect a meal within a certain time period (e.g., 15 minutes), one or more processors 28 can output an alert to remind patient 12 to eat something to address the insulin dose. If a dose is given to correct hyperglycemia and the dose is given after a recent similar dose, one or more processors 28 can output an alert notifying patient 12 (and / or the caregiver of patient 12) that hyperglycemia may be overcompensated. The alert can further suggest that the caregiver needs to monitor the blood glucose of patient 12 and / or patient 12 may need to eat something to prevent hypoglycemia.

[0120] The dose of long-acting insulin (the second type of insulin) is typically delivered once a day; however, Patient 12 may receive two long-acting doses within a short period of time or at different times of the day (e.g., a first dose in the morning and a second dose in the evening). In some instances, one or more processors 28 may output an alert warning Patient 12 and having sufficient time to prevent the dose before a second subsequent dose is given. In other instances, if one or more processors 28 detect an appropriate injection followed by an injection of subsequent long-acting insulin, one or more processors 28 may output an alert notifying Patient 12 to monitor their blood glucose within the next 12 - 24 hours to prevent possible hypoglycemia.

[0121] In fact, while these alerts can prevent Patient 12 from being affected by the consequences of injecting insulin without proper intervention of a meal event, some instances enable one or more processors 28 (and / or one or more processors of Patient Device 24) to have more control over Patient 12's injection. For example, if the injection device 30 is communicatively coupled to one or more processors 28 (and / or one or more processors of Patient Device 24), one or more processors 28 (and / or one or more processors of Patient Device 24) may transmit instructions to the injection device 30 to stop (or delay) a subsequent insulin injection if a meal event has not been detected first. If no meal event is detected and Patient 12 is preparing a subsequent insulin injection, one or more processors 28 (and / or one or more processors of Patient Device 24) may issue a command to lock the injection device 30 in a non-operational state. This may be automatically performed in response to detecting a subsequent insulin injection without a meal event. In other instances, after determining that Patient 12 is likely not to have eaten anything before attempting a subsequent insulin injection, the injection device 30 may automatically terminate Patient 12's operation.

[0122] Figure 6 is a flowchart showing an example operating method according to one or more instances described in the present disclosure. Figure 6 is described in terms of one or more processors. 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.

[0123] One or more processors may identify at least one gesture (60) indicative of preparing an insulin injection using an injection device based on user activity data. Identification of the at least one gesture implies that an insulin injection has recently occurred, is about to occur, or is occurring. 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 data indicative of user activity, including data indicative of gestures made by patient 12 or a caregiver of patient 12 when preparing an insulin injection using an injection device (e.g., injection device 30). Example insulin injections may consist of one or more gestures, where each gesture is defined according to a data model configured to distinguish insulin injections from other user activities (e.g., user activities or caregiver activities). Generally, the present disclosure contemplates that user activity includes any activity of a user of an injection device. In one instance, the data model includes a definition of each of a plurality of gestures (e.g., user activity gestures), and a definition of each (detectable) example of an insulin injection made by patient 12 as a combination of gestures. The data model may define an example insulin injection as including only one gesture.

[0124] Based on the at least one identified gesture, one or more processors may generate information (62) indicative of at least one of an amount or type of insulin dose in an insulin injection made by the injection device. For example, an inertial measurement unit 50 within wearable device 22 provides vibration data to one or more processors 28 associated with movement of a dial and other instruments used to set the dose and / or type. The one or more processors may compare the generated information to criteria for a proper insulin injection (64). Criteria for a proper insulin injection include any combination of the following: the number of clicks used to set the amount of the insulin dose, the amount of time elapsed between insulin injections, whether the user ate between insulin injections, whether basal insulin is being injected into the patient based on the time of day or whether bolus insulin is being injected into the patient based on the time of day. In some instances, the one or more processors determine whether the user ate based on user input and / or based on gesture data (e.g., as described above). The purpose of comparing information about the time, amount, and / or type set for a pending insulin injection to the criteria is to prevent the patient from being injected with an incorrect amount and / or type of insulin and / or at an incorrect time. The consequences of improper insulin injection can range from mild discomfort to a significant decline in the patient's health. For example, if not enough time has elapsed between a previous insulin injection and the current insulin injection, the patient may completely forget the previous insulin injection. If patient 12 has not eaten any food between injections, the patient may eventually experience low glucose levels.

[0125] One or more processors may be based on information (66) that indicates whether a criterion is met by a comparison output. In response to determining that the criterion for appropriate insulin injection is not met, one or more processors may output an alert that includes at least one of text, graphics, sound, or video, the alert being operable to notify the user that the insulin injection is inappropriate. The present disclosure contemplates a variety of situations where the criterion for appropriate insulin injection is not met: Patient 12 receives an insulin injection in the following situations: 1) not enough time has passed since the previous injection; 2) there is not enough food in the body; 3) there is no effective insulin dose (e.g., amount); and / or 4) the type of insulin in the dose is incorrect, etc. By way of example, injecting rapid-acting insulin (one type of insulin) can compensate for carbohydrates and / or correct hyperglycemia, but when the insulin dose of rapid-acting insulin is undercompensated (e.g., too low an amount) or overcompensated (e.g., too high an amount), one or more processors may output an alert notifying the user of undercompensation or overcompensation, respectively. For example, if one or more processors fail to detect a meal within a certain period of time (e.g., fifteen minutes), one or more processors may output an alert to remind Patient 12 to eat, e.g., to address overcompensation of insulin. An alternative alert may suggest a subsequent insulin injection to correct undercompensation. The alert may be transmitted to a caregiver's device, e.g., prompting the caregiver to monitor Patient 12's blood glucose, carbohydrates, and / or food intake.

[0126] In some instances, in response to a confirmation of an insulin injection based on injection device data (e.g., device confirmation), one or more processors may generate at least one of the following: (1) data recording the insulin injection for storage in the patient's medical data; (2) data indicating the insulin injection identification for display on an electronic display; or (3) data indicating an inappropriate insulin injection compared to the criterion for appropriate insulin injection for display on an electronic display. The injection device data may be received and transmitted from a device communicatively coupled to the injection device (e.g., a smart cap for any insulin pen), a device having a sensor (e.g., an optical sensor) for sensing the injection device (e.g., a syringe) (e.g., a smart phone), or the injection device itself.

[0127] One or more processors may process input data from Patient 12 indicating patient confirmation or patient negation. In some instances, Patient 12 transmits the input data in response to a query submitted via a communication channel with the patient device. Patient 12 may receive the query as content presented on an electronic display of a smart device or on the injection device. In response to the patient rejecting an insulin injection, one or more processors may perform learning techniques to adjust the data model. In some instances, the learning techniques adjust the data model to more accurately predict an insulin injection based on Patient 12's gestures during operation of the injection device.

[0128] In some instances, one or more processors may determine the time of a subsequent insulin injection, determine whether the user is attempting to inject insulin using an injection device based on movement detected by the wearable device prior to the time of the subsequent insulin injection, and output data presenting an alert to the user that the user has injected insulin based on the determination that the patient has attempted to inject insulin using the injection device prior to the time of the subsequent insulin injection.

[0129] Figure 7A and 7B is a flowchart showing another example method of operation in accordance with one or more examples described in the present disclosure. Similar to Figure 6 , Figure 7A and 7B is described in terms of one or more processors. The one or more processors may be one or more of 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.

[0130] As Figure 7A shown, one or more processors may predict (e.g., determine) whether an insulin injection is about to occur or is occurring, for example, by identifying one or more gestures indicating preparation for an insulin injection using an injection device based on user activity data. For example, one or more processors may determine whether an insulin injection is about to occur or is occurring based on a data model of patient 12, where the data model is configured to distinguish insulin injections from other user activities (e.g., patient activities and / or caregiver activities). An example insulin injection may consist of multiple gestures, where each gesture is defined according to a data model configured to distinguish insulin injections from other user activities. In one instance, the data model includes a definition of each of the multiple gestures (e.g., user activity gestures), and a definition of each (detectable) example of an insulin injection performed by patient 12 as a combination of gestures. The data model may define an example insulin injection as including only one gesture. If one or more processors determine that an insulin injection will not occur (i.e., does not occur), then the user activity may not change, and patient 12 may continue with other non-insulin injection gestures. As Figure 7A shown, although gestures are made immediately before and during delivery of insulin to patient 12 (e.g., basal insulin (e.g., baseline therapy)), one or more processors may continuously examine the user activity data to identify defined gestures corresponding to an example insulin injection and determine (e.g., predict) that an insulin injection is about to occur or is occurring.

[0131] AsFigure 7A Further shown, one or more processors may detect (e.g., determine) whether insulin injection gesture components such as gestures for setting a dose are about to occur or are occurring (70). For example, one or more processors may determine whether any gesture including the above insulin injection gesture components is about to occur or is occurring based on user activity data indicating one or more movement characteristics, posture characteristics (e.g., position and / or orientation), and other characteristics detected by the wearable device 22. These characteristics and other context information may be processed based on sensor data generated by the wearable device 22. If one or more processors detect that a gesture for setting a dose is about to occur or is occurring (yes branch of 70), then one or more processors may determine the diabetes therapy dose and / or type (74). For example, one or more processors may determine the amount and / or type of insulin dose based on data from an inertial measurement unit (e.g., vibration data). If either the insulin dose or the dose type deviates from a standard indicating an appropriate amount, dose type, or time to deliver the insulin dose, then this determination is postponed until after prediction and at least until after device or patient confirmation. This postponement conserves resources and provides sufficient time to warn the patient 12 and / or correct the insulin injection. If one or more processors do not detect a gesture for setting a dose (no branch of 70), then one or more processors may determine that the insulin injection is not ready or will not occur.

[0132] One or more processors may detect (e.g., determine) whether a gesture that moves the injection device closer to the patient 12's body (another insulin injection gesture component) is about to occur or is occurring (76). Similar to other gestures, a gesture that moves the injection device closer to the patient 12's body may be detected if user activity data including patient movement characteristics and / or patient posture characteristics matches the data model definition of the gesture. If one or more processors fail to detect a gesture that moves the injection device closer to the patient 12's body in the user activity data (or other context data) (no branch of 76), then one or more processors may wait for an alternative gesture or predict no injection after an appropriate waiting time (78). If one or more processors detect that a gesture that moves the injection device closer to the patient 12's body is about to occur or is occurring (yes branch of 76), then one or more processors may continue to detect (e.g., determine) whether a gesture that holds the injection device in a particular position / orientation (another gesture corresponding to insulin injection) is about to occur or is occurring (80).

[0133] If one or more processors do not detect the above-described gesture of holding the injection device in the user activity data (or other context data) (the no branch of 80), then the one or more processors may monitor the user activity data for alternative gestures corresponding to an insulin injection during a waiting period (82). In some instances, the waiting period may not exceed the amount of time consumed to administer an insulin injection.

[0134] If one or more processors do detect a gesture of holding the injection device in a particular position / orientation (the yes branch of 80), then the one or more processors monitor the user activity data for additional gestures and / or non-occurrence markers during a waiting period (84). The one or more processors may recognize the above-described posture corresponding to an insulin injection, but there may be indicator indicators and there may be user activity data indicating patient movement and / or a patient posture that contradicts the prediction of an insulin injection. For example, if there is no insulin in the injection device, the above-described gesture cannot correspond to an actual injection. If certain additional gestures are detected (e.g., a gesture to clear air bubbles in the insulin), where these gestures also correspond to an insulin injection, then the detection refutes any recognition of a non-occurrence marker.

[0135] The one or more processors may determine whether a predicted insulin injection is about to occur or is occurring based on the detection of the above-described gesture as a component of a composite insulin injection gesture and any non-occurrence markers of the insulin injection gesture (86). If the one or more processors predict the occurrence of an insulin injection (the yes branch of 86), then the one or more processors proceed to Figure 7B If the one or more processors are unable to predict the occurrence of an insulin injection (the no branch of 86), then the one or more processors detect a refill event or another user activity gesture that replaces the insulin injection (88). For example, if a sufficient number of non-occurrence markers are identified based on the user activity data, the one or more processors may determine that the above-described detection of the components of an insulin injection posture is a false positive. One example of a sufficient number of non-occurrence markers is a refill event, where the injection device 30 is refilled with another insulin cartridge. Another example of a sufficient number of non-occurrence markers is recent activity of the patient 12 without an injection device.

[0136] If the injection device 30 is not available, the patient 12 may use a syringe to deliver a partial therapy dose. For example, the one or more processors may output information about the insulin dose and / or type to the patient device 24, and the patient 12 may then use the syringe to deliver a partial therapy dose based on the information output by the patient device 24 through the user interface 36.

[0137] Proceed to Figure 7B, after one or more processors predict a pending diabetes treatment in the form of an insulin injection, the one or more processors may confirm a prediction (86) that an insulin injection is about to occur or is occurring.

[0138] For example, one or more processors may predict (e.g., determine) whether an insulin injection is about to occur or is occurring based on one or more movement characteristics, posture characteristics (e.g., location and / or orientation), and other characteristics detected by the wearable device 22. These characteristics and other context information may be acquired / captured (and then processed) into user activity data and compared to a data model that defines each posture corresponding to an example insulin injection.

[0139] Referring Figure 7A , if one or more processors predict that an insulin injection is about to occur or is occurring, the one or more processors execute a mechanism (90) for confirming or rejecting the prediction based on injection device data. If the prediction of an insulin injection occurring cannot be confirmed and / or rejected (no branch of 90), the one or more processors may execute a machine learning mechanism to adjust the data model to more accurately predict no injection (i.e., not occurring) for the captured user activity data and general insulin injections (92). Additionally, the one or more processors may continue to monitor the insulin injection in the user activity data.

[0140] If the prediction of an insulin injection occurring is confirmed (yes branch of 90), the one or more processors may determine whether the criteria for a proper insulin injection are met (94). For example, the one or more processors may apply each criterion to the parameters of the predicted insulin injection to determine satisfaction or dissatisfaction. Such parameters include insulin dose, insulin type, injection time, etc. Thus, the criteria include the correct (e.g., recommended and / or effective) version of the same parameters, and if the number of criteria met is insufficient, the one or more processors may identify that an inappropriate insulin injection is about to occur or is occurring. These parameters may be determined based on the user activity data and insulin injection data used for the prediction. The criteria may be predetermined or learned over time.

[0141] If the criteria are met (yes branch of 94), the one or more processors may store a record of the pending insulin injection in the medical record data (96). Before storing the medical record data, the one or more processors may wait until the device or patient confirms.

[0142] If the criteria are not met (the no branch of 94), one or more processors may determine whether to modify a pending improper insulin injection (98). In some instances, if one or more processors determine to modify a pending improper insulin injection (the yes branch of 98), one or more processors may output various information to the patient device 24 and / or the injection device 30 on an electronic display of the patient device 24; an example of the output information includes information (e.g., content) describing the modification to correct the impropriety and / or improve the efficacy in the pending insulin injection (100). In some instances, the electronic display may be included in the user interface 36 of the patient device 24. One or more processors may output the correct insulin dose and / or insulin dose type on the electronic display to attempt to modify the pending improper insulin dose and / or type, respectively. In some instances, one or more processors (e.g., in the patient device 24 or in a web server in the cloud 26) may output data that guides the injection device 30 to automatically correct the insulin dose and / or insulin dose type or prevent an insulin injection from occurring. One or more processors may output a recommended and / or effective orientation / location to hold the injection device 30 or a manual injection device prior to administering insulin.

[0143] As another example, one or more processors may output information for a patient 12 or a caregiver of the patient 12 to follow, where the output information may include a set of instructions for properly administering a diabetes therapy to the patient. The set of instructions may indicate the correct insulin type, the appropriate dose of the correct insulin type, a safe injection area for receiving the appropriate dose of the correct insulin type, a recommended trajectory when moving the injection device to inject the appropriate dose of the correct insulin, an orientation or location to hold the injection device prior to reaching the safe injection area (e.g., site) following the recommended trajectory, an injection time (or time window) and / or an interval between insulin injections. One or more processors may output data including a graphical representation of an appropriate insulin injection on the electronic display of the user interface 36. In some instances, one or more processors of the patient device 24 transmit data indicative of the content presenting the set of instructions and / or the graphical representation to a device maintained by the patient's caregiver. To assist the caregiver in administering the diabetes therapy, the graphical representation and / or the set of instructions may be displayed as an output on an electronic display of the device maintained by the caregiver.

[0144] If one or more processors determine not to modify an inappropriate insulin injection (the no branch of 98), then the one or more processors output an alert (102) that the insulin injection is inappropriate. In response to determining that an insulin injection does not meet the criteria for an appropriate insulin injection, the one or more processors may output any combination of text, graphics, sound, video, and / or other content types in the alert on the electronic display of the patient device 24, the alert being operable to notify the patient 12 that the insulin injection is inappropriate. For example, if the one or more processors determine that it is more beneficial to prevent or delay an inappropriate insulin injection than to modify the injection, then the one or more processors may output such an alert to notify the patient 12 that the insulin injection is inappropriate. For example, if the current time does not conform to the injection schedule recommended for the patient 12, the injection is untimely and will be blocked or delayed by the alert. The alert may include text as well as a sound warning. As another example, if sufficient time has not elapsed between previous injections, a subsequent injection is inappropriate and will be blocked or delayed by the alert. In another example, a network device on the patient device 24 or the cloud 26 may transmit an instruction to direct the injection device 30 to stop a pending inappropriate insulin injection.

[0145] As described above, there may be various sensors for measuring different context information. Some example ways in which sensor information can be utilized are provided below. For example, based on movement characteristics, one or more processors 28 may determine the amount and time of insulin delivery. In some instances, one or more processors 28 may not issue a prompt to the patient 12 based on sensor data, such as a low battery or other types of alerts, such as whether glucose is slightly out of range, such as not issuing a prompt when the patient 12 is driving or sleeping. The sensor may indicate a change in temperature, and one or more processors 28 may set a target glucose level based on the temperature. The sensor may indicate that the patient 12 is exercising, and one or more processors 28 may set a target glucose level based on whether the patient 12 is exercising and whether the patient 12 is performing aerobic or anaerobic exercise.

[0146] In some instances, the time at which the patient device 24 and / or the wearable device 22 outputs information (e.g., broadcasts) to one or more processors 28 may be based on the context information of the patient 12, such as biometrics, location, and time of day. In some instances, the patient device 24 and / or the wearable device 22 may output information in a power-saving manner (e.g., broadcasts during sleep may be reduced).

[0147] There may be other ways to utilize the location information of the patient 12 to help control glucose levels. As an example, the patient device 24 may output information about foods or food companies that provide products to help treat diabetes based on the location of the patient 12 being at a grocery store.

[0148] Various examples that can be utilized together or in combination are described below.

[0149] Example 1: A system for controlling the delivery of diabetes therapy, the system comprising: a wearable device configured to generate user activity data associated with a user's arm; and one or more processors configured to: identify, based on the user activity data, at least one gesture indicative of preparing an insulin injection using an injection device; generate, based on the at least one identified gesture, information indicative of at least one of the amount or type of insulin dose in the insulin injection performed by the injection device; compare the generated information with a standard for a proper insulin injection; and, based on the comparison, output information indicative of whether the standard is met.

[0150] Example 2. The system according to Example 1, wherein, in order to identify the at least one gesture, the one or more processors are configured to identify at least one of the following, based on the user activity data: (1) a first gesture for setting at least one of the amount or type of the dose in the insulin injection; (2) a second gesture for moving the injection device closer to the patient's body; or (3) a third gesture for holding the injection device in a specific position or orientation.

[0151] Example 3. The system according to Examples 1 to 2, wherein the standard for a proper insulin injection comprises one or more of the following: the number of clicks for setting the amount of the insulin dose, the amount of time elapsed between insulin injections, whether the user eats between insulin injections, whether basal insulin is injected into the patient based on the time of day or whether bolus insulin is injected into the patient based on the time of day.

[0152] Example 4: The system according to Examples 1 to 3, wherein, in order to output information indicative of whether the standard is met, the one or more processors are configured to:

[0153] In response to determining that the standard for a proper insulin injection is not met, output an alert comprising at least one of text, graphics, sound, or video, the alert being operable to notify the user that the insulin injection is inappropriate.

[0154] Example 5: The system according to Examples 1 to 4, wherein the wearable device comprises:

[0155] One or more inertial measurement units for generating at least a portion of the user activity data.

[0156] Example 6: The system according to Examples 1 to 5, wherein the one or more processors are configured to: receive confirmation of the insulin injection from at least one of the injection device, a device communicatively coupled to the injection device, or a device having a sensor for sensing the injection device.

[0157] Example 7: The system according to Examples 1 to 6, further comprising a patient device, wherein the patient device includes the one or more processors.

[0158] Example 8: The system according to Examples 1 to 7, wherein the one or more processors are further configured to: determine the time of a subsequent insulin injection; determine whether the user attempts to use the injection device to inject insulin based on movement detected by the wearable device before the time of the subsequent insulin injection; and output data presenting an alert to the user that the user has injected insulin based on the determination that the patient attempts to use the injection device to inject insulin before the time of the subsequent insulin injection.

[0159] Example 9: The system according to Examples 1 to 8, wherein the one or more processors are further configured to: output data indicating a modification to correct an inadequacy associated with the insulin injection or increase the efficacy of the insulin injection based on the comparison indicating non - satisfaction of the criteria.

[0160] Example 10: The system according to Examples 1 to 9, wherein the one or more processors are further configured to: output data guiding the injection device to automatically modify the insulin injection or prevent the insulin injection based on the comparison indicating non - satisfaction of the criteria.

[0161] Example 11: The system according to Examples 1 to 10, wherein the one or more processors are further configured to: generate data presenting a set of instructions for the proper administration of the therapy to the patient, the set of instructions indicating the correct insulin type, the appropriate dose of the correct insulin type, a safe injection area for receiving the appropriate dose of the correct insulin type, a recommended trajectory when moving the injection device to inject the appropriate dose of the correct insulin type, maintaining the orientation or position of the injection device before reaching the safe injection area following the recommended trajectory, and the time interval between insulin injections.

[0162] Example 12: The system according to Examples 1 to 11, wherein the one or more processors are further configured to: transmit the data presenting the set of instructions to a device maintained by a caregiver for the patient, wherein the set of instructions is displayed as an output on an electronic display of the device maintained by the caregiver.

[0163] Example 13: A method includes: identifying, by one or more processors, at least one gesture indicating preparation of an insulin injection using an injection device based on user activity data, wherein a wearable device is configured to generate the user activity data associated with the user's arm; generating, by the one or more processors, based on the at least one identified gesture, information indicating at least one of an amount or a type of an insulin dose in the insulin injection performed by the injection device; comparing, by the one or more processors, the generated information with a standard for a proper insulin injection; and outputting, by the one or more processors, based on the comparison, information indicating whether the standard is met.

[0164] Example 14: The method according to Example 13, wherein identifying the at least one gesture further includes: identifying, based on the user activity data, at least one of the following: (1) a first gesture for setting at least one of the amount or the type of the dose in the insulin injection; (2) a second gesture for moving the injection device closer to the patient's body; or (3) a third gesture for holding the injection device in a particular position or orientation.

[0165] Example 15: The method according to Examples 13 to 14, wherein the standard for the proper insulin injection includes one or more of the following: the number of clicks for setting the insulin dose, the amount of time elapsed between insulin injections, whether the user eats between insulin injections, whether basal insulin is injected into the patient based on the time of day or whether bolus insulin is injected into the patient based on the time of day.

[0166] Example 16: The method according to Examples 13 to 15, wherein outputting the information indicating whether the standard is met further includes: in response to determining that the standard for the proper insulin injection is not met, outputting an alert including at least one of text, a graphic, a sound, or a video for notifying the user that the insulin injection is not appropriate.

[0167] Example 17: The method according to Examples 13 to 16, further includes: receiving, from at least one of the injection device, a device communicatively coupled to the injection device, or a device having a sensor for sensing the injection device, a confirmation of the insulin injection.

[0168] Example 18: The method according to Examples 13 to 17 further includes: determining a time for a subsequent insulin injection; determining whether the user attempts to inject insulin using the injection device based on movement detected by the wearable device before the time of the subsequent insulin injection; and outputting data for presenting an alert to the user that the user has injected insulin based on the determination that the patient attempts to inject insulin using the injection device before the time of the subsequent insulin injection.

[0169] Example 19: The method according to Examples 13 to 18 further includes: outputting information indicating a modification to correct an inadequacy associated with the insulin injection or increase the efficacy of the insulin injection based on the comparison indicating non - satisfaction of the criteria.

[0170] Example 20: A computer - readable storage medium having instructions stored thereon that, when executed, cause one or more processors to: identify at least one gesture indicating preparation of an insulin injection using an injection device based on user activity data, wherein a wearable device is configured to generate the user activity data associated with the user's arm; generate information indicating at least one of an amount or a type of an insulin dose in the insulin injection performed by the injection device based on the at least one identified gesture; compare the generated information with criteria for a proper insulin injection; and output information indicating whether the criteria are satisfied based on the comparison.

[0171] 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, as well as 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" generally may refer to any of the foregoing logic circuitry alone or in combination with other logic circuitry or any other equivalent circuitry.

[0172] In one or more examples, the functions described in this disclosure may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a computer - readable medium and executed by a hardware - based processing unit. The computer - readable medium may include a computer - readable storage medium that forms a tangible non - transitory 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 circuitry. Thus, as used herein, the term "processor" may refer to any of the foregoing structures or any other structure suitable for implementing the techniques described herein.

[0173] Additionally, in some aspects, the functions described herein can be set 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. Instead, the functions associated with one or more modules or units can be performed by separate hardware or software components or integrated in common or separate hardware or software components. Similarly, the techniques can be implemented entirely in one or more circuits or logic elements. The techniques of the present disclosure can be implemented in a variety of devices or apparatuses, including one or more processors 28 of cloud 26, one or more processors of patient device 24, one or more processors of wearable device 22, one or more processors of insulin pump 14, or some combination thereof. The one or more processors can be one or more integrated circuits (ICs) and / or discrete circuitry residing at various locations within the example systems described in the present disclosure.

[0174] One or more processors or processing circuitry for example for the example techniques described in the present disclosure can be implemented as fixed function circuitry, programmable circuitry, or a combination thereof. Fixed function circuitry refers to circuitry that provides a specific function and is pre-set in terms of the operations that can be performed. Programmable circuitry refers to circuitry that can be programmed to perform various tasks and provides flexible functionality in terms of the operations that can be performed. For example, programmable circuitry can execute software or firmware that causes the programmable circuitry to operate in a manner defined by the instructions of the software or firmware. Fixed function circuitry can execute software instructions (e.g., to receive parameters or output parameters), but the type of operations performed by the fixed function circuitry is generally immutable. In some instances, one or more of the units can be different circuit blocks (fixed function or programmable), and in some instances, the one or more units can be integrated circuits. The processor or processing circuitry can include an arithmetic logic unit (ALU), elementary function unit (EFU), digital circuitry, analog circuitry, and / or programmable cores formed by programmable circuitry. In instances where software executed by programmable circuitry is used to perform the operations of the processor or processing circuitry, the memory accessible by the processor or processing circuitry can store the object code of the software that the processor or processing circuitry receives and executes.

[0175] Various aspects of the present disclosure have been described. These and other aspects are within the scope of the following claims.

Claims

1. A system for controlling the delivery of a diabetes therapy, the system comprising: A wearable device configured to generate user activity data associated with a user's arm; And One or more processors configured to: Identify at least one gesture indicative of preparing an insulin injection using an injection device based on the user activity data; Generate information indicative of at least one of the amount or type of insulin dose in the insulin injection performed by the injection device based on the at least one identified gesture; Compare the generated information with a standard for a proper insulin injection; and Based on the comparison, output information indicating whether the standard is met.

2. The system according to claim 1, wherein, in order to identify the at least one gesture, the one or more processors are configured to: Identify at least one of the following based on the user activity data: (1) a first gesture for setting at least one of the amount or type of the dose in the insulin injection; (2) a second gesture for moving the injection device closer to the patient's body; or (3) a third gesture for holding the injection device in a specific position or orientation.

3. The system according to any one of claims 1 to 2, wherein the standard for a proper insulin injection comprises one or more of the following: the number of clicks for setting the amount of the insulin dose, the amount of time elapsed between insulin injections, whether the user eats between insulin injections, whether basal insulin is injected into the patient based on the time of day or whether bolus insulin is injected into the patient based on the time of day.

4. The system according to any one of claims 1 to 2, wherein, in order to output information indicating whether the standard is met, the one or more processors are configured to: In response to determining that the standard for a proper insulin injection is not met, output an alert comprising at least one of text, graphics, sound, or video, the alert being operable to notify the user that the insulin injection is inappropriate.

5. The system according to any one of claims 1 to 2, wherein the wearable device comprises: One or more inertial measurement units for generating at least a portion of the user activity data.

6. The system according to any one of claims 1 to 2, wherein the one or more processors are configured to: Receive confirmation of the insulin injection from at least one of the injection device, a device communicatively coupled to the injection device, or a device having a sensor for sensing the injection device.

7. The system according to any one of claims 1 to 2, further comprising a patient device, wherein the patient device comprises the one or more processors.

8. The system according to any one of claims 1 to 2, wherein the one or more processors are further configured to: Determine the time of a subsequent insulin injection; Determine whether the user attempts to inject insulin using the injection device based on movement detected by the wearable device before the time of the subsequent insulin injection; and Based on the determination that the patient attempts to inject insulin using the injection device before the time of the subsequent insulin injection, output data for presenting an alert to the user that the user has injected insulin.

9. The system according to any one of claims 1 to 2, wherein the one or more processors are further configured to: Output data indicating a modification to correct an inadequacy associated with the insulin injection or increase the efficacy of the insulin injection based on the comparison indicating non - satisfaction of the criteria.

10. The system according to any one of claims 1 to 2, wherein the one or more processors are further configured to: Based on the comparison indicating non - satisfaction of the criteria, output data for guiding the injection device to automatically modify the insulin injection or prevent the insulin injection.

11. The system according to any one of claims 1 to 2, wherein the one or more processors are further configured to: Generate data presenting a set of instructions for appropriately administering the therapy to the patient, the set of instructions indicating the correct insulin type, an appropriate dose of the correct insulin type, a safe injection area for receiving the appropriate dose of the correct insulin type, a recommended trajectory when moving the injection device to inject the appropriate dose of the correct insulin type, maintaining the orientation or position of the injection device before reaching the safe injection area following the recommended trajectory, and the time interval between insulin injections.

12. The system according to claim 11, wherein the one or more processors are further configured to: Transmit the data presenting the set of instructions to a device for the patient maintained by a caregiver, wherein the set of instructions is displayed as an output on an electronic display of the device maintained by the caregiver.

13. A method, comprising: Identify, by one or more processors, at least one gesture indicating preparation for an insulin injection using an injection device based on user activity data, wherein a wearable device is configured to generate the user activity data associated with the user's arm; Generate, by the one or more processors, based on the at least one identified gesture, information indicating at least one of an amount or a type of an insulin dose in the insulin injection performed by the injection device; Compare, by the one or more processors, the generated information with criteria for an appropriate insulin injection; And Output, by the one or more processors, information indicating whether the criteria are satisfied based on the comparison.

14. The method according to claim 13, further comprising: Determine the time of a subsequent insulin injection; Determine whether the user attempts to inject insulin using the injection device based on movement detected by the wearable device before the time of the subsequent insulin injection; and Output data for presenting to the user an alert that the user has injected insulin, based on the determination that the patient attempted to inject insulin using the injection device before the time of the subsequent insulin injection.

15. A computer-readable storage medium having instructions stored thereon that, when executed, cause one or more processors to perform the operations of the one or more processors of any one of claims 1, 3 to 4, 6, and 8 to 12.

Images