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-10748658-B2
Publication Date
2020-08-18
Expiration Date
Abstract
Methods and devices include database management and graphical user interfaces for measurements collected by analyzing blood.
Core Innovation
The invention relates to a computer-implemented method for managing blood glucose levels of a user in which patient data are electronically received in a server before generation of a treatment plan. The received data include 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. The received data are stored in a database connected to one or more processors, and metadata are extracted from the stored data.
The method applies one or more machine learning algorithms to the received data to generate a goal and a treatment plan. The goal includes reduction in the A1C value of the user at an end of a treatment period compared to an A1C value at a beginning of the treatment period. The treatment plan is based on the length of time diagnosed and the types and dosages of medications consumed, and includes instructions for tasks performed by the user during a first subset of the treatment period.
The method iteratively revises the treatment plan by electronically receiving, during the first subset, data relating to the treatment plan, including medication types, timing, and dosages, carbohydrate amounts, sleep amount, exercise performed, and blood glucose levels. Machine learning algorithms determine medication compliance, diet compliance, and exercise compliance by comparing received values to prescribed values, analyze the medication, carbohydrate, sleep, and exercise information together with blood glucose levels to identify patterns, and revise the treatment plan for a subsequent subset based on the determined compliances and identified patterns.
The invention further integrates GPS-based restaurant recommendations and route generation, questionnaire-driven determination of a tendency to follow regimens, and trigger-event notification. Based on received GPS data and time proximity to scheduled meals, restaurants in proximity that are cataloged in a database are identified, recommended meals are output based on carbohydrate content, and a walking route is generated to a selected catalogued restaurant. A questionnaire is administered and user answers are used to determine a tendency to follow medication, diet, and exercise regimens, and a trigger event that occurs before an adverse effect on blood glucose levels is determined based on the identified patterns and used for notification when a subsequent instance is detected.
Claims Coverage
The independent claim coverage includes seven inventive features spanning goal generation with A1C reduction, task-based treatment-plan generation, ML-driven compliance and pattern analysis, iterative treatment-plan revision, GPS-based carbohydrate-matched restaurant recommendations with walking-route generation, questionnaire-based regimen-following tendency, and trigger-event notification related to adverse blood glucose effects.
A1C reduction goal generation from received diagnosis, medication, and A1C values
Electronically receiving in a server, before generation of a treatment plan, data including a length of time diagnosed with a blood glucose condition, types and dosages of medications consumed, and A1C values; extracting metadata; and applying one or more machine learning algorithms to generate a goal including reduction in the A1C value at an end of a treatment period compared to a beginning A1C value, and a treatment plan based on the length of time diagnosed and the types and dosages of medications.
Task-based initial treatment plan for a first subset with prescribed measurement, medication, carbohydrates, and exercise
Generating a treatment plan that includes instructions for tasks to be performed by the user during a first subset of the treatment period, where tasks include prescribed blood glucose measurement pairs before and after meals, prescribed timing and dosage of medication, a prescribed amount of carbohydrates, or prescribed exercise.
Iterative plan revision by machine-learning compliance determination and pattern identification across treatment subsets
Electronically receiving data relating to the treatment plan during the first subset, including medication types, timing, dosages, carbohydrate amounts, sleep amount, exercise performed, and blood glucose levels; determining medication compliance, diet compliance, and exercise compliance by comparing received values to prescribed values; analyzing the medication, carbohydrate, sleep, and exercise information together with blood glucose levels to identify patterns; and revising the treatment plan for a subsequent subset based on the determined compliances and identified patterns.
GPS-based proximity restaurant identification and carbohydrate-content meal recommendations
Receiving GPS data from the electronic device of the user; identifying restaurants in proximity based on the GPS data and time proximity to scheduled meals, where the restaurant database includes meals offered and carbohydrate content of each meal; and outputting identified restaurants and recommended meals based on carbohydrate content.
Walking-route generation to a selected catalogued restaurant
Receiving a selection of a catalogued restaurant from the user and generating a walking route for the user to travel from the current location to the selected restaurant.
Questionnaire-based determination of a tendency to follow medication, diet, and exercise regimens
Administering a questionnaire to the user via a software application downloaded to the electronic device; electronically receiving user answers; determining based on the user answers a tendency of the user to follow a medication regimen, a diet regimen, and an exercise regimen; and generating the treatment plan also based on the determined tendency.
Trigger-event detection preceding adverse blood glucose effects with user notification
Determining based on the identified patterns a trigger event that occurs before an adverse effect on blood glucose levels; sending a notification to the user upon detecting a subsequent instance of the trigger event; and identifying the trigger event and the adverse effect on blood glucose levels, where the trigger event is a day of the week or an amount of exercise performed that exceeds a threshold and the adverse effect includes hyperglycemia.
Overall, the independent claim coverage is directed to an ML-based, A1C-reduction goal and treatment-plan generator that collects adherence and glucose-related data to determine compliance and identify patterns, revises the treatment plan across subsets, and includes GPS-based carbohydrate-matched restaurant recommendations with walking-route generation, questionnaire-driven regimen-following tendency, and trigger-event notifications associated with adverse effects including hyperglycemia.
Stated Advantages
Reduction in A1C value of the user at an end of a treatment period compared to a beginning A1C value.
Iterative updating of the treatment plan based on medication, diet, and exercise compliance and identified patterns between behaviors and blood glucose levels.
Recommendations of meals at nearby restaurants based on carbohydrate content.
User notifications when a detected trigger event occurs that precedes an adverse effect on blood glucose levels, including hyperglycemia.
Documented Applications
Managing blood glucose levels of a user using a computer-implemented method that generates and revises a treatment plan based on machine learning and adherence data.
Carbohydrate-matched meal recommendations at nearby restaurants using GPS proximity and restaurant database carbohydrate content.
Walking route generation from a current location to a selected restaurant.
Using a questionnaire to estimate a tendency to follow a medication regimen, diet regimen, and exercise regimen for use in generating the treatment plan.
Detecting trigger events that occur before adverse glucose effects and sending notifications to the user, where hyperglycemia is an adverse effect.
Interested in licensing this patent?