In a groundbreaking development, Google Research has unveiled a new framework capable of utilizing wearable devices such as smartwatches to detect early signs of diabetes. This study, conducted with 1,165 participants, employed data from smartwatches along with demographic and routine blood biomarker information to predict insulin resistance, a key indicator of diabetes.
According to the study published in the prestigious journal Nature, simply measuring fasting glucose is not enough to estimate insulin resistance accurately. The researchers highlighted that integrating lifestyle factors and biomarkers gives a holistic view of an individual’s metabolic health, potentially leading to preventive interventions against diabetes.
The research team also created an ‘IR agent’ language model, providing personalized health recommendations. Notably, continuous data collection by smartwatches captures variances in daily activities, heart function, and sleep, all contributing to accurate metabolic health assessments, making this method accessible to millions globally.
(With inputs from agencies.)