Browse Prior Art Database

Predictive Alert Notification and Behavior Recommendation to Keep Blood Glucose Under Control Disclosure Number: IPCOM000254582D
Publication Date: 2018-Jul-12
Document File: 3 page(s) / 323K

Publishing Venue

The Prior Art Database

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 53% of the total text.


Predictive Alert Notification and Behavior Recommendation to Keep Blood Glucose Under Control Diabetes is a chronic condition in which the body’s ability to produce and/or use insulin is impaired. Insulin is an essential hormone in the body to regulate the amount of sugar in the blood. An impairment in either the production or use of insulin in the body causes an elevated level of blood glucose in the body, which can eventually cause damage to other organ systems in the body such as the cardiovascular system, digestive system, etc. The goal of diabetes management is to optimize the blood sugar levels by regulating the things that increase or decrease the blood sugar (e.g., food, exercise, medications, sleep, stress, etc.). One of the biggest challenges in managing a diabetic’s blood sugar level is predicting the factors that will increase or decrease the blood sugar, especially to a level that can be injurious to the patient such as causing hypoglycemic (low blood sugar) or hyperglycemic (high blood sugar) events. Current diabetic patients do not have these alerts. Most patients just take insulin based on consumed food, and are not aware that the same insulin could act differently with activity after food consumption. Diabetic patients also face the challenge of having to go to different doctors for consultations: a dietitian, nutritionist, endocrinologist, primary care physician, etc. The novel solution is a system that uses predictive analytics on collected historical and current data to determine and alert the patient to an impending hypo- or hyperglycemic event, and then make a recommendation for appropriate actions to mitigate the event. The system uses patient similarity analytics along with insights gained from historical data to create predictive models for detecting impending adverse events. The core novelty is a system and method for continuous monitoring and generation of alerts of impending hypoglycemic events. At a high level, the novel system:

1. Collects data to monitor the patient’s glucose level A. Historical B. User profile/medical history C. Recent (e.g., from wearable devices that track food intake, nutritional

value, and exercise) 2. Performs predictive analytics for the patient’s glucose level based on:

A. Insulin levels B. Continuous Glucose Monitor (CGM) C. Food content D. Calorie consumption E. Recent movement/exercise

3. Compares data from Step 1 to similar patients' data


4. Reviews patient profile and historical data for the nutritional value or levels of carbohydrates, sugar, etc. in ready-made food

5. Reviews the same data (as in Step 3) for a similar patient 6. Predicts the likely changes to (BG) levels based on Steps 1-5 7. Alerts the patient to take appropriate action to ensure proper levels of insulin and

blood glucose (BG). Recommendati...