Systems and methods for analyzing blood glucose and changing human behavior

1 . A computer-implemented method for treating or preventing progression of prediabetes, diabetes, or metabolic syndrome in a subject, the method comprising:

providing a wearable device comprising at least one processor, memory, and one or more sensors configured to monitor physiological parameters of the subject;

receiving data for the subject including a condition or risk factors corresponding to prediabetes, diabetes, or metabolic syndrome and physiological data received from the one or more sensors of the wearable device;

monitoring, using the wearable device, a plurality of behavioral events associated with the subject and physiological parameters of the subject, each event being correlated to a timestamp within a time period;

identifying, using the received data input into generative artificial intelligence comprising one or more machine learning models, a pattern in the plurality of behavioral events that correlate with glucose dysregulation or elevated glycemic levels in the subject;

generating, using the generative artificial intelligence and based on the identified pattern and the received data, personalized content for the subject, wherein the personalized content includes tailored interventions to improve glycemic control of the subject;

generating one or more nudges for the subject based on the personalized content, wherein the one or more nudges comprise prompts or suggestions aimed at encouraging adherence to executing suggested behavior changes provided in the personalized content to improve glycemic control for the subject or improve long-term health outcomes for the subject;

automatically adjusting an operational parameter of the wearable device based on the identified pattern, the automatic adjustment comprising changing a monitoring frequency of the one or more sensors; and

causing presentation of an indication of the personalized content and the one or more nudges to the subject.

2 . The computer-implemented method of claim 1 , wherein:

at least one of the plurality of behavioral events comprises a last consumed meal;

the personalized content comprises feedback on the last consumed meal.

3 . The computer-implemented method of claim 2 , wherein the feedback comprises suggested timing for a next meal and educational content, the educational content comprising a meal plan for the subject that minimizes glucose spikes over a second time period.

4 . The computer-implemented method of claim 1 , wherein the personalized content comprises one or more of: dietary recommendations, exercise suggestions, and lifestyle modifications.

5 . The computer-implemented method of claim 1 , wherein the method further comprises:

monitoring a behavior or input responsive to the presentation of the one or more nudges;

iteratively repeating the monitoring of behavior exhibited by the subject;

in response to detecting additional behavioral events, identifying an additional pattern in the additional behavioral events;

updating the personalized content according to the additional behavioral events based on the identified additional pattern;

generating an updated nudge corresponding to the updated personalized content; and

causing presentation of the updated nudge and the updated personalized content to the subject.

6 . The computer-implemented method of claim 1 , wherein the monitoring of the plurality of behavioral events is performed at least in part by an artificial intelligence computer agent configured to use data generated by the monitoring and a plurality of template guides to generate the one or more nudges.

7 . The computer-implemented method of claim 1 , wherein the method further comprises:

adapting the personalized content based on contextual information associated with the subject, wherein the contextual information comprises at least one of: a current location, a time of day, one or more upcoming events, or one or more recent activities.

8 . The computer-implemented method of claim 1 , wherein the plurality of nudges are selected from nudge modes comprising a light mode, a regular mode, and a heavy mode.

9 . The computer-implemented method of claim 8 , wherein the heavy mode is activated during at least one of: periods following discontinuation of one or more medications or when the subject sets aggressive health goals.

10 . The computer-implemented method of claim 1 , wherein:

monitoring the plurality of behavioral events comprises monitoring or receiving blood glucose data for the subject;

identifying the pattern in the plurality of behavioral events comprises identifying a glucose time in range for the subject; and

selecting, based on the glucose time in range, one or more times in which to present the one or more nudges to the subject.

11 . The computer-implemented method of claim 1 , wherein the personalized content comprises a grocery shopping list curated according to the identified pattern, and the method further comprises automatically placing a plurality of items on the grocery shopping list in an online shopping cart or automatically placing an order of the plurality of items on the grocery shopping list.

12 . The computer-implemented method of claim 1 , wherein the personalized content comprises a plurality of restaurant menu suggestions selected according to the identified pattern, and food data corresponding to each of the plurality of restaurant menu suggestions, the food data indicating one or more of: calorie content, sugar content, carbohydrate content, and at least one reason for selecting the respective restaurant menu suggestions.

13 . The computer-implemented method of claim 1 , wherein the computer-implemented method is performed by an artificial intelligence health coach configured to share data with a buddy computing device according to permissions associated with the subject, the shared data comprising one or more of: a blood glucose estimation, identified behavioral patterns, a status update corresponding to the subject, and a summary corresponding to the subject.

14 . The computer-implemented method of claim 1 , further comprising:

defining a reward milestone associated with a health goal for the subject;

monitoring progress toward the reward milestone;

enrolling a buddy device associated with a trusted contact of the subject to receive status information according to permission settings provided by the subject;

providing an update to the buddy device, the update comprising updates on behavior, food intake, exercise, or physiological changes corresponding to the subject;

receiving feedback from the buddy device about the subject;

in response to determining achievement of the reward milestone, generating reward content comprising a gamified experience using the generative artificial intelligence, wherein the gamified experience is tailored to the subject based on the identified pattern, the feedback from the buddy device, and personal preferences associated with the subject; and

causing presentation of the gamified experience to the subject as a reward for achieving the reward milestone.

15 . The computer-implemented method of claim 1 , further comprising:

defining a health goal for the subject, wherein the health goal includes a target number of meal events satisfying health criteria over a defined time period;

monitoring meal-related behavioral events including:

events indicating selection of home cooked meals, and

events indicating selection of healthy options when dining at restaurant venues;

determining meal-related behavioral events that satisfy the health criteria;

calculating progress toward the health goal based on the monitoring;

generating, using the generative artificial intelligence and based on the calculated progress, adaptive recommendations for improving adherence to the health goal, wherein the adaptive recommendations are personalized based on correlations between the monitored meal-related behavioral events and the calculated progress; and

causing presentation of progress information indicating the progress relative to the target number.

16 . The computer-implemented method of claim 1 , monitoring adherence of the subject to the one or more nudges over a subsequent time period; and

analyzing correlations between the monitored adherence and changes in glycemic control for the subject to assess therapeutic effectiveness of the interventions.

17 . The computer-implemented method of claim 1 , wherein adjusting the operational parameter comprises one or more of:

decreasing the monitoring frequency of the one or more sensors when determining, for the subject, a sustained adherence to the personalized content; and

triggering monitoring of one or more physiological parameters by the wearable device for a subsequent time period based on the identified pattern.

18 . A system for treating or preventing progression of prediabetes, diabetes, or metabolic syndrome in a user, the system comprising:

a wearable device configured to be worn on a body site of the user, the wearable device comprising:

at least one processor; and

one or more sensors configured to monitor physiological parameters of the user;

memory storing instructions that, when executed by the at least one processor, cause the system to execute operations comprising:

receiving data for the user including a condition or risk factors corresponding to prediabetes, diabetes, or metabolic syndrome and

receiving blood glucose data from the wearable device;

monitoring, using the one or more sensors, a plurality of behavioral events associated with the user and physiological responses of the user corresponding to the behavioral events, each event being correlated to a timestamp within a time period;

identifying, using the blood glucose data as input to a generative artificial intelligence system comprising one or more machine learning models trained on behavioral and physiological data, a pattern in the plurality of behavioral events, wherein the one or more machine learning models are configured to:

analyze temporal correlations between behavioral events and physiological responses of the user, and

detect recurring behavioral sequences that correlate with changes in the blood glucose data;

generating, based on the identified pattern, the received blood glucose data, and the received data for the user, personalized content for the user using the generative artificial intelligence system, wherein the personalized content includes tailored behavioral interventions specific to the user and configured to modify dietary behavior, exercise behavior, or lifestyle behavior to improve glucose regulation and prevent progression of the prediabetes, diabetes, or metabolic syndrome;

generating one or more nudges for the user based on the personalized content, wherein the one or more nudges comprise prompts or suggestions aimed at encouraging adherence to executing suggested behavior changes provided in the personalized content;

automatically adjusting an operational parameter of the wearable device based on the identified pattern or the blood glucose data, wherein adjusting the operational parameter of the wearable device comprises changing a monitoring frequency or changing a frequency of receiving data from the wearable device; and

causing presentation of the personalized content and the one or more nudges to the user.

19 . The system of claim 18 , wherein:

at least one of the plurality of behavioral events comprises a last consumed meal; and

the personalized content comprises feedback on the last consumed meal.

20 . The system of claim 18 , wherein the operations further comprise:

determining a nudge mode selected from a light mode, a regular mode, and a heavy mode, the selection being based on a historical adherence to previously generated nudges or recommendations using a predictive machine learning model; and

generating the one or more nudges according to the determined nudge mode.

21 . The system of claim 20 , wherein the heavy mode is activated during at least one of: periods following discontinuation of one or more medications or when the user sets aggressive health goals.

22 . The system of claim 18 , wherein the personalized content comprises a plurality of restaurant menu suggestions selected according to the identified pattern, and food data corresponding to each of the plurality of restaurant menu suggestions, the food data indicating one or more of: calorie content, sugar content, carbohydrate content, and at least one reason for selecting the respective restaurant menu suggestions.

23 . The system of claim 18 , wherein the operations are performed by an artificial intelligence health coach configured to share data with a buddy computing device according to permissions associated with the user, the shared data comprising one or more of: blood glucose estimations, identified patterns, a status update corresponding to the user, and a summary corresponding to the user.

24 . The system of claim 18 , wherein the personalized content comprises a grocery shopping list curated according to the identified pattern, and the operations further comprise automatically placing a plurality of items on the grocery shopping list in an online shopping cart or automatically placing an order of the plurality of items on the grocery shopping list.

25 . A non-transitory computer-readable medium for managing behavior of a subject, the computer-readable medium storing instructions that when executed by at least one processor, cause the at least one processor to perform operations for treating or preventing progression of prediabetes, diabetes, or metabolic syndrome in a subject, the operations comprising:

providing a wearable device comprising at least one processor, memory, and one or more sensors configured to monitor physiological parameters of the subject;

receiving data for the subject including a condition or risk factors corresponding to prediabetes, diabetes, or metabolic syndrome and physiological data received from the one or more sensors of the wearable device;

monitoring, using the wearable device, a plurality of behavioral events associated with the subject and physiological parameters of the subject, each event being correlated to a timestamp within a time period;

identifying, using the received data input being provided to a generative artificial intelligence a pattern in the plurality of behavioral events that correlates with glucose dysregulation or elevated glycemic levels in the subject;

generating, using the generative artificial intelligence and based on the identified pattern and the received data, personalized content for the subject, wherein the personalized content includes tailored interventions to improve glycemic control of the subject;

generating one or more nudges for the subject based on the personalized content, wherein the one or more nudges comprise prompts or suggestions aimed at encouraging adherence to executing suggested behavior changes provided in the personalized content; and

causing presentation of the personalized content and the one or more nudges to the subject,

wherein the one or more nudges are configured to coach the subject to modify the behavior of the subject over an upcoming time period.

26 . The non-transitory computer-readable medium of claim 25 , wherein:

at least one of the plurality of behavioral events comprises a last consumed meal; and

the personalized content comprises feedback on the last consumed meal.

27 . The non-transitory computer-readable medium of claim 25 , wherein the operations further comprise:

monitoring a behavior or input responsive to the presentation of the one or more nudges;

iteratively repeating the monitoring of the behavior or input exhibited by the subject;

in response to detecting additional behavioral events, identifying an additional pattern in the additional behavioral events;

updating the personalized content according to the additional behavioral events based on the identified additional pattern;

generating an updated nudge corresponding to the updated personalized content; and

causing presentation of the updated nudge and the updated personalized content to the subject.

28 . The non-transitory computer-readable medium of claim 25 , wherein the personalized content comprises presentation of one or more venues and a grocery shopping list curated according to the identified pattern, a budget, a location of the subject, and a determination of an availability of a plurality of items on the grocery shopping list, and the operations further comprising automatically placing the plurality of items on the grocery shopping list in an online shopping cart or automatically placing an order of the plurality of items on the grocery shopping list.

29 . The non-transitory computer-readable medium of claim 25 , wherein the personalized content comprises a plurality of restaurant menu suggestions selected according to the identified pattern, and food data corresponding to each of the plurality of restaurant menu suggestions, the food data indicating one or more of: calorie content, sugar content, carbohydrate content, and at least one reason for selecting the respective restaurant menu suggestions.

30 . The non-transitory computer-readable medium of claim 25 , wherein the operations are performed by an artificial intelligence health coach configured to share data with a buddy computing device according to permissions associated with the subject, the shared data comprising one or more of: blood glucose estimations, identified patterns, a status update corresponding to the subject, and a summary corresponding to the subject.