Researchers from the Weizmann Institute of Science in Rehovot, Tel Aviv-based startup Pheno.AI and chip giant NVIDIA have developed GluFormer, an AI model that can predict an individual’s future glucose levels and other health metrics based on past glucose monitoring data.
The model was trained on 14 days of glucose monitoring data from over 10,000 non-diabetic study participants, with data collected every 15 minutes through a wearable monitoring device. The data was collected as part of the Human Phenotype Project, an initiative by Pheno.AI, a startup that aims to improve human health through data collection and analysis.
GluFormer can currently predict the response of glucose levels to a person’s actions. For example, if they eat a particular meal under certain conditions, the model can say how each an individual person will respond.
The model can predict the level of glucose in the blood four years ahead and compare the results with or without a certain treatment in order to adapt the future treatment plan and help patients adhere to it. For pharmaceutical companies, the system can help predict the results of clinical trials.
Other values that the model should be able to predict are: fatty tissue around the liver and pancreas, blood pressure and sleep apnea, through continuous monitoring of changes in the patient’s sugar levels and other medical tests.
The research is being led by Prof. Eran Segal of the Weizmann Institute’s Department of Computer Science and Applied math, Prof. Gal Chechik, senior director of AI research at Nvidia, Pheno.ai data researcher Gal Sapir, and lead researcher, Guy Lutsker, a Nvidia researcher and Ph.D. student at the Weizmann Institute.
Published by Globes, Israel business news – en.globes.co.il – on November 26, 2024.
© Copyright of Globes Publisher Itonut (1983) Ltd., 2024.
