The present disclosure relates to medicine administration and tracking and, more specifically, to medicine administration and tracking systems and methods including customized user alerts based on historical data.
Diabetes mellitus (“diabetes”) is a metabolic disease associated with high blood sugar due to insufficient production or use of insulin by the body. Diabetes affects hundreds of millions of people and is among the leading causes of death globally. Diabetes has been categorized into three types: type 1, type 2, and gestational diabetes. Type 1 diabetes is associated with the body's failure to produce sufficient levels of insulin for cells to uptake glucose. Type 2 diabetes is associated with insulin resistance, in which cells fail to use insulin properly. Gestational diabetes can occur during pregnancy when a pregnant woman develops a high blood glucose level. Gestational diabetes often resolves after pregnancy; however, in some cases, gestational diabetes develops into type 2 diabetes.
Various diseases and medical conditions, such as diabetes, require a user to self-administer doses of medicine. When administering a liquid medicine by injection, for example, the appropriate dose amount is set and then dispensed by the user, e.g., using a syringe, a medicine delivery pen, or a pump. Regardless of the particular device utilized for injecting the liquid medicine, it is important to accurately track the medicine dosed and to facilitate a user's compliance with a dosing regime, particularly for managing lifelong or chronic conditions like diabetes.
To the extent consistent, any of the aspects and features detailed herein can be utilized with any of the other aspects and features detailed herein in any suitable combination.
Provided in accordance with aspects of the present disclosure is a method for customizing user alerts in a medicine administration and tracking system. The method includes detecting an alertable condition for which a medicine administration and tracking system is configured to monitor, generating a custom alert for the alertable condition based at least in part on historical data indicating a responsiveness to previous alerts for the same alertable condition, delivering the generated custom alert to a user, determining the user's response to the generated custom alert, and updating the historical data to include the alertable condition, the generated custom alert, and the user's level of responsiveness to the generated custom alert.
In an aspect, generating the custom alert includes determining at least one of a type of device to which the alert is to be delivered or a manner in which the alert is to be delivered.
In an aspect, the generated custom alert is at least one of an audible alert and generating the custom alert includes determining a volume level of the audible alert, or a haptic alert and generating the custom alert includes determining an intensity or vibratory pattern of the haptic alert.
In an aspect, generating the custom alert includes delaying delivery of the alert to the user based on a time of day that the alertable condition is detected.
In an aspect, the method includes delaying delivery of the custom alert based on an activity of the user.
In an aspect, the generated custom alert includes a calculated insulin dose recommendation.
In an aspect, generating the custom alert includes determining for what alert configuration the user is most likely to respond.
In an aspect, the user is clustered into a cluster and generating the custom alert is based on a setting associated with the cluster.
In an aspect, determining the user's response to the generated custom alert includes determining that the user has not responded to the generated custom alert after expiration of a predetermined period of time. Additionally, or alternatively, the method may further include prompting the user for feedback on the failure to respond and updating the historical data of the user based on the feedback.
In another aspect of the disclosure, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium stores instructions, which when executed by a processor, cause the processor to detect an alertable condition for which a medicine administration and tracking system is configured to monitor, generate a custom alert for the alertable condition based at least in part on historical data indicating a responsiveness to previous alerts for the same alertable condition, deliver the generated custom alert to a user, determine the user's response to the generated custom alert, and update the historical data to include the alertable condition, the generated custom alert, and the user's level of responsiveness to the generated custom alert.
In an aspect, the instructions, when executed by the processor, cause the processor to generate the custom alert by determining at least one of a type of device to which the alert is to be delivered or a manner in which the alert is to be delivered.
In an aspect, the generated custom alert is at least one of an audible alert and the instructions, when executed by the processor, cause the processor to determine a volume level of the audible alert, or a haptic alert and the instructions, when executed by the processor, cause the processor to determine an intensity or vibratory pattern of the haptic alert.
In an aspect, the instructions, when executed by the processor, cause the processor to generate the custom alert by delaying delivery of the alert to the user based on a time of day that the alertable condition is detected.
In an aspect, the instructions, when executed by the processor, cause the processor to delay delivery of the alert based on an activity of the user.
In an aspect, the generated custom alert includes a calculated insulin dose recommendation.
In an aspect, the instructions, when executed by the processor, cause the processor to generate the custom alert by determining for what alert configuration the user is most likely to respond.
In an aspect, the user is clustered into a cluster and the instructions, when executed by the processor, cause the processor to generate the custom alert based on a setting associated with the cluster.
In an aspect, the instructions, when executed by the processor, cause the processor to determine the user's response to the alert by determining that the user has not responded to the generated custom alert after expiration of a predetermined period of time.
In an aspect, the instructions, when executed by the processor, cause the processor to prompt the user for feedback on the failure to respond and update the historical data of the user based on the feedback.
Medicine injection pen 20, described in greater detail below, is a reusable injection pen configured to removably receive a medicine cartridge, e.g., a cartridge of insulin, for injecting a selected dose of insulin into a patient and recording information concerning the injected dose of insulin, e.g., a dose amount and/or timestamp data associated with the dose.
Computing device 30 is detailed and illustrated herein as a smartphone, although any other suitable computing device may be provided such as, for example, a tablet, a wearable computing device (e.g., a smart watch, smart glasses, etc.), a laptop and/or desktop computer, a smart television, a network-based server computer, etc.
Health management application 40 is paired with pen 20, which may be a prescription-only medical device, via computing device 30, although other suitable configurations are also contemplated. In aspects, the pairing of computing device 30 with pen 20 at least partially unlocks health management application 40 to enable the user to utilize some or all features of health management application 40, e.g., according to the user's prescription. Thus, the act of pairing can unlock and enable the functionality of health management application 40 and/or system 10 (including pen 20), while health management application 40 (and/or system 10) may provide only limited features in the absence of pairing with pen 20.
Health management application 40 of computing device 30, in aspects, can monitor and/or control functionalities of pen 20 and provide a dose calculator module and/or decision support module that can calculate and recommend a dose of medicine for the user to administer using pen 20. Health management application 40 provides a user interface, on the user interface of computing device 30, to allow a user to manage health-related data. For example, health management application 40 can be configured to control some functionalities of pen 20 and/or to provide an interactive user interface to allow a user to manage settings of pen 20 and/or settings for computing device 30 that can affect the functionality of system 10 (
In aspects, system 10 further includes a data processing system 50 in communication with pen 20 and/or computing device 30. Data processing system 50 can include one or more computing devices in a computer system and/or communication network accessible via the internet, e.g., including servers and/or databases in the cloud. System 10 can additionally or alternatively include sensor device 60 to monitor one or more health metrics and/or physiological parameters of the user. Examples of health metric and physiological parameter data monitored by sensor device 60 include analytes (e.g., glucose), heart rate, blood pressure, user movement, temperature, etc. Sensor device 60 may be a wearable sensor device such as a continuous glucose monitor (CGM) to obtain transcutaneous or blood glucose measurements that are processed to produce continuous glucose values. For example, the CGM can include a glucose processing module implemented on a stand-alone display device and/or implemented on computing device 30, which processes, stores, and displays the continuous glucose values for the user. Such continuous glucose values can be utilized by health management application 40, for example, for displaying health data, in dose calculation and/or decision support, etc. In aspects, data processing system 50 includes alert customization module 220 in addition to or as an alternative to alert customization module 220 residing on computing device 30.
With reference to
In aspects, in order to operate pen 20, the user first sets e.g., dials, a dose using a dose knob 26a of dose setting mechanism 25. For example, the dose may be adjusted up or down to achieve a desired dose amount prior to administration of the dose by rotating dose knob 26a in an appropriate direction. Once the appropriate dose has been set, the user applies a force against a dose dispensing button 26b of dose setting mechanism 25 to begin dispensing. More specifically, to begin dispensing, the user presses against the portion of dose dispensing button 26b that protrudes from body 22 of pen 20 to thereby drive a driving element 26c, e.g., a drive screw 26c, of dose dispensing mechanism 24 against an abutment of medicine cartridge 23 to dispense an amount of medicine from cartridge 23 through needle 29 into the user in accordance with the dose amount set by dose setting mechanism 25, e.g., dose knob 26a, during setting.
Operations monitoring mechanism 28 of pen 20 senses movement of a rotating and/or translating driving component (e.g., drive screw 26c) of dose dispensing mechanism 24. Operations monitoring mechanism 28 may include one or more switches, sensors, and/or encoders for this purpose. More specifically, any suitable switch(es), sensor(s), and/or encoder(s) may be utilized to sense rotary and/or linear movement. Non-limiting examples of such include rotary and linear encoders, Hall effect and other magnetic-based sensors, linearly variable displacement transducers, optical sensors, etc. With respect to an encoder, for example, the encoder can be configured to sense the rotation of drive screw 26c that, in turn, translates to dispense medicine; thus, by sensing rotation of drive screw 26c, the translational movement of drive screw 26c can be readily determined. Movement of the encoder may be detected as data processed by the processor of electronics unit 27 of pen 20, from which the amount of medicine dosed can be determined.
In aspects, the processor of electronics unit 27 of pen 20 can store the dose along with a timestamp for that dose and/or any other information associated with the dose. In aspects, the transceiver of electronics unit 27 enables pen 20 to transmit the dose and related information to computing device 30. In such aspects, once the dose is transmitted, the dose data and any related information associated with that particular transmitted dose is marked in the memory of electronics unit 27 of pen 20 as transmitted. If the dose is not yet transmitted to computing device 30 such as, for example, because no connection between the pen 20 and computing device 30 is available, then the dose and associated data can be saved and transmitted the next time a successful communication link between pen 20 and computing device 30 is established.
The timestamp may be the current time or a time from a count-up timer. When the dose and associated information is communicated to health management application 40 running on computing device 30, the timestamp and/or “time-since-dose” parameter (as determined by the count-up timer) is transmitted by pen 20 and received by computing device 30 for storage in memory 33 of data processing unit 31 of the computing device 30 (see
Dose dispensing mechanism 24 of pen 20 can include a manually powered mechanism (user powered and/or mechanically biased), a motorized mechanism, or an assisted mechanism (e.g., a mechanism that operates partly on manual power and partly on motorized power). Regardless of the particular configuration of the dose dispensing mechanism 24, as noted above, when a force (e.g., a manual force, electrically-powered motor force, or combinations thereof) is applied to drive screw 26c of dose dispensing mechanism 24, drive screw 26c in turn provides a force to urge medicine from medicine cartridge 23 to deliver the set or dialed dose. In aspects, dose dispensing mechanism 24 can be operated such that rotation and/or translation of the driving element, e.g., drive screw 26c, is facilitated by a variable tension spring or a variable speed motor to inject the dose over a specific time frame (e.g., 1 s, 5 s, etc.) to help reduce the pain of dosing and/or for other purposes.
Once computing device 30 receives the dose and related information (e.g., which can include time information, dose setting, and/or dose dispensing information, and other information about pen 20 and/or the environment and context as it relates to a dosing event), computing device 30 stores the dose related information in memory 33, e.g., which can be included among a list of doses or dosing events. In aspects, via the user interface associated with health management application 40, computing device 30 allows the user to browse a list of previous doses, to view an estimate of current medicine active in the patient's body (medicine on board, e.g., insulin on board) based on calculations performed by health management application 40, and/or to utilize a dose calculation module to assist the patient regarding dose setting information on the size of the next dose(s) to be delivered. For example, the patient may enter carbohydrates to be eaten and current blood sugar (which alternatively may be obtained directly from sensor device 60 (
Turning now to
Method 200 begins at step 201 where a condition for which an alert is to be generated is detected. The alertable condition may be, for example, that the user should take a dose of medicine (e.g., an injection of insulin); that the user is due, overdue, etc. to take a scheduled dose of medicine; that the user should adjust a dose amount; that the user needs to confirm or input data; etc. The alertable condition may be detected based on a number of factors including, for example, a glucose concentration value (manually entered by the user or provided by a CGM) or Insulin-on-Board. The alertable condition may also be detected based on other data or input received or processed such as data received by computing device 30 including the tracked location of the user; physical activity of the user including step count, movement distance and/or intensity, estimated calories burned, and/or activity duration; and/or interaction pattern of the user with computing device 30. It is noted that the alertable condition need not be detected based on physiological factors but, rather, may additionally or alternatively be based on other factors such as time of day, time since last dose, etc.
After an alertable condition is detected in step 201, method 200 proceeds to step 203. In step 203, a customized alert for the alertable condition is generated for the user. The customized alert may be based at least in part on historical data of the user's responsiveness to past alerts. In particular, system 10 stores historical data corresponding to the user's historical responsiveness to different types of alerts, for different alertable conditions, delivered at different times and days, and/or under different circumstances. The customization of the alert may include any of the factors described below with respect to alert customization module 220 (
In step 205, the generated custom alert is delivered to the user (and/or other recipient(s) as determined in alert customization step 203). In step 207, a user's responsiveness to the generated custom alert is determined. A user's responsiveness to the generated custom alert may include, but is not limited to, a determination as to whether the generated custom alert was viewed and/or acknowledged, whether any action was taken in response to receipt of the generated custom alert, the result of the action taken, a comparison of the action taken to an action recommended in the alert, etc. If a user response is not received after a preconfigured period of time (or even in the event a response has been received or action taken), a prompt may be delivered to solicit a response of the user or to obtain feedback from the user pertaining to the reasons for the lack of acknowledgement of the delivered alert or other feedback regarding the alert, to be used for further alert customization for that user and/or other users. The preconfigured period of time may be customized for the particular user based on historical data of the user. In step 209, the historical data of the user is updated based on the determined response of the generated custom alert, the condition for which the result was triggered, user information, and/or the received feedback.
Referring to
With particular reference to
With particular reference to
Referring back to
The alert customization module 220 is configured to compare metrics of exercise (e.g., steps), and if sufficient activity or exercise is detected, generate an output indicative of a warning to be provided to the user that their present dose setting (e.g., previous dose calculation) may suggest too many carbs due to their recent exercise. The alert customization module 220 is configured to use hypoglycemia as a metric or gain to the learning algorithm, e.g., to make user specific. For example, the alert customization module 220 can be configured to make variables more conservative until acceptable levels of hypoglycemia are reached.
In some implementations, the alert customization module 220 can produce an output indicative of recommending exercise, e.g., in lieu of insulin to lower a glucose level, based on the historical data for this user indicating that this user or the cluster of users is more receptive to exercise recommendations over administering a dose. For example, known exercise routines such as a 5 minute walk or 15 minutes of cardio may be calibrated for that particular user, based on past experience of how much such activities lower glucose for this particular user or other users within the clustered group. The example algorithm can base the calculated exercise recommendation on one or more of several factors, including insulin on board (JOB), food recently eaten, time of day, other recent exercise, and other parameters used by a calculation algorithm. The alert customization module 220 can track activity by monitoring accelerometer data, e.g., from the pen 20 itself, and/or from the computing device 30, and/or based on data from other wearable devices (such as activity monitors, for example) to adjust dose calculations/recommendations.
In some implementations, for example, the alert customization module 220 is configured to stagger partial-doses based on certain, user specific circumstances. In an illustrative example, the alert customization module 220 is configured stagger partial-doses based on foods with known slow glycemic response for this user of other users in the cluster. For example, pizza may prompt for a partial correction dose immediately and the rest of the dose an hour later to try to maintain a flat glucose response. This partial correction may be based on the user's own history with this or similar foods, and/or aggregated data from a larger population of users who have all had experience with this type of food. The alert customization module 220 can provide a dose reminder automatically set for (in this example) an hour later. In some implementations, for example, the alert customization module 220 is configured to also adjust a second dose based on glucose level, or prompt for a glucose measurement before recommending the second dose.
The various aspects and features disclosed herein may be combined in different combinations than the combinations specifically presented in the description and accompanying drawings. It should also be understood that, depending on the example, certain acts or events of any of the processes or methods described herein may be performed in a different sequence, may be added, merged, or left out altogether (e.g., all described acts or events may not be necessary to carry out the techniques). In addition, while certain aspects of this disclosure are described as being performed by a single module or unit for purposes of clarity, it should be understood that the techniques of this disclosure may be performed by a combination of units or modules associated with, for example, a medical device.
In one or more examples, the described functional and/or operational aspects 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. Computer-readable media may include non-transitory computer-readable media, which corresponds to a tangible medium such as data storage media (e.g., RAM, ROM, EEPROM, flash memory, or any other medium that can be used to store desired program code in the form of instructions or data structures and that can be accessed by a computer).
Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable logic arrays (FPGAs), or other equivalent integrated or discrete logic circuitry. Accordingly, the term “processor” or “processing unit” as used herein may refer to any of the foregoing structure or any other physical structure suitable for implementation of the described techniques. Also, the techniques could be fully implemented in one or more circuits or logic elements.
While several aspects of the present disclosure have been detailed above and are shown in the drawings, it is not intended that the disclosure be limited thereto, as it is intended that the disclosure be as broad in scope as the art will allow and that the specification be read likewise. Therefore, the above description and accompanying drawings should not be construed as limiting, but merely as exemplifications of particular aspects. Those skilled in the art will envision other modifications within the scope and spirit of the claims appended hereto.