Docket #: S21-137
Metabolic Subphenotype Predictor – software for continuous glucose monitoring
Stanford researchers at the Snyder Lab have developed a novel software application, called the Metabolic Subphenotype Predictor, which predicts if a patient is insulin resistant through continuous glucose monitoring.
Current methods of identifying pre-diabetes are blood tests that predict insulin resistance, but do not identify other metabolic subphenotypes. Additionally, these tests are not readily available to the general public. This method defines the dominant metabolic phenotype using the shape of a glucose curve after administering an oral glucose tolerance test. This invention makes testing for diabetes more accessible and cost effective, while providing personalized medical treatment and targeted lifestyle interventions.
Stage of Development
Research -
in vivo
Related Technology
Stanford Docket S18-198-Continuous glucose monitoring classification algorithm to identify glucotypes at diabetes risk
Applications
- Companion software for continuous glucose monitoring devices
Advantages
- Novel software application that is not available anywhere else
- Accessible diagnosis for rural and underserved areas
- Personalization of medical treatment and targeted lifestyle interventions based on the identification of the dominant metabolic phenotype
Related Links
Patents
- Published Application: 20220406400
Similar Technologies
-
A Prognostic Algorithm for Cancer Outcomes Using Machine Learning Analysis of Connective Tissue Networks and Cell Interactions S21-354A Prognostic Algorithm for Cancer Outcomes Using Machine Learning Analysis of Connective Tissue Networks and Cell Interactions
-
24-hour Ambulatory Monitoring Based Autonomic and Gastric Myoelectric Evaluation S22-14524-hour Ambulatory Monitoring Based Autonomic and Gastric Myoelectric Evaluation
-
A Machine Learning Algorithm for Analysis of Connective Tissue Networks in Scarring and Chronic Fibroses S19-317A Machine Learning Algorithm for Analysis of Connective Tissue Networks in Scarring and Chronic Fibroses