Database management and graphical user interfaces for measurements collected by analyzing blood
Inventors
McRAITH, Kevin • KESANI, Hari • Iyer, Anand • SUSAI, Gabriel • SHOMALI, Mansur • RAO, Prasad Matti
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10978207-B2
Publication Date
2021-04-13
Expiration Date
Abstract
Methods and devices include database management and graphical user interfaces for measurements collected by analyzing blood.
Core Innovation
The invention provides a computer-implemented health management system for managing blood glucose levels of a user by electronically receiving, in a server, data including a length of time that the user has been diagnosed with a blood glucose condition, types and dosages of medications consumed by the user, and A1C values of the user. The system stores the received data in a database connected to the processors, extracts metadata from the stored data, and inputs the metadata into one or more machine learning algorithms to generate a goal for the user and a treatment plan before generation of the treatment plan.
The generated goal includes a reduction in the A1C value of the user at an end of a treatment period as compared to an A1C value at a beginning of the treatment period. The generated treatment plan includes instructions for tasks to be performed by the user during a first subset of the treatment period, including prescribed blood glucose measurement pairs to be measured before and after meals, prescribed timing and dosage of medication, a prescribed amount of carbohydrates to be consumed, and/or prescribed exercise to be performed.
The treatment plan is generated using machine learning algorithms including one or more of artificial neural networks, Bayesian statistics, case-based reason, decision trees, inductive logic processing, Gaussian process regression, Gene expression programming, Logistic model trees, stochastic modeling, or statistical modeling, and is based on length of diagnosis and medication types and dosages, and at least cohort data for a cohort associated with the user. The system outputs the generated treatment plan to the user via an electronic device, electronically receives data relating to the treatment plan during the first subset of the treatment period, and revises the treatment plan for a subsequent subset based on determined medication compliance, determined diet compliance, determined exercise compliance, and identified patterns.
In addition, the invention uses GPS data from the electronic device to identify restaurants in proximity to the user, where the restaurant database includes meals offered and a carbohydrate content of each meal, outputs a list of identified restaurants with recommended meals based on carbohydrate content, receives a selection of a catalogued restaurant, and generates a walking route for the user to travel along from a current location to the selected restaurant. The invention also determines a trigger event that occurs before an adverse effect on blood glucose levels, including hyperglycemia, where the trigger event is a day of the week and/or an amount of exercise performed that exceeds a threshold, and sends a notification to the user upon detecting a subsequent instance of the trigger event including an identification of the trigger event and the adverse effect.
Claims Coverage
The independent claims identified in the provided content are clm-00001, clm-00010, and clm-00018. Across these independent claims, the inventive coverage includes machine-learning goal generation, iterative treatment-plan generation with compliance and pattern-based revision across treatment subsets, GPS-based restaurant identification and recommended meals with carbohydrate content, and trigger-event detection with notifications tied to adverse effects including hyperglycemia.
Cohort-informed goal generation for A1C reduction
A method that electronically receives diagnosis duration, medication types and dosages, and A1C values, extracts metadata, inputs the metadata into one or more machine learning algorithms to generate a goal including a reduction in the A1C value at an end of a treatment period compared to a beginning A1C value, wherein the goal is generated based at least on cohort data for a cohort associated with the user.
Machine learning treatment plan with prescribed user tasks across treatment subsets
A method that generates a treatment plan to achieve the A1C-reduction goal, the treatment plan including instructions for tasks to be performed by the user during a first subset of a treatment period, wherein the tasks include one or more of prescribed blood glucose measurement pairs to be measured before and after meals, prescribed timing and dosage of medication to be consumed, a prescribed amount of carbohydrates to be consumed, or prescribed exercise to be performed; electronically receiving treatment-plan-related data during the first subset, revising the treatment plan for a subsequent subset based on determined medication compliance, determined diet compliance, determined exercise compliance, and identified patterns, and outputting a revised treatment plan including changed tasks compared to the first subset.
Gps-based nearby restaurant meal recommendation using carbohydrate content
A method that receives GPS data from the electronic device, identifies restaurants in proximity based on the received GPS data, where the restaurant database includes meals offered and carbohydrate content of each meal, outputs a list of identified restaurants with recommended meals based on carbohydrate content, receives a selection of a catalogued restaurant, and generates a walking route for the user from a current location to the selected restaurant.
Regimen-tendency determination
A method that determines a tendency of the user to follow at least one of a medication regimen, a diet regimen, and an exercise regimen, wherein generating the treatment plan also is based on the determined tendency.
Trigger-event detection before adverse effect and notification of hyperglycemia
A method that determines, based on identified patterns, a trigger event that occurs before an adverse effect on blood glucose levels, wherein the adverse effect includes hyperglycemia, and where the trigger event is a day of the week and/or an amount of exercise performed that exceeds a threshold, and that sends a notification to the user via the electronic device upon detecting a subsequent instance of the trigger event, wherein the notification includes an identification of the trigger event and an identification of the adverse effect on blood glucose levels that occurs after the trigger event.
The independent claim set in the provided content centers on using machine learning algorithms to generate and revise treatment plans with A1C reduction as a goal across treatment subsets, incorporating compliance and pattern identification for plan revision. Additional independent coverage includes GPS-based restaurant identification and meal recommendations using carbohydrate content, regimen-tendency determination, and trigger-event detection before adverse blood glucose effects with user notifications tied to hyperglycemia and triggers such as day of the week and/or exercise exceeding a threshold.
Stated Advantages
Documented Applications
No documented applications found
Interested in licensing this patent?