Health Tech
Study Shows Smartwatch Data Can Help Detect Early Diabetes Risk
Wearable data combined with biomarkers may enable scalable early detection of insulin resistance
A recent study has introduced a scalable and accessible approach to analysing data from wearable devices such as smartwatches to identify early signs of diabetes.
Researchers from Google Research in the United States analysed data from 1,165 participants, using smartwatch-derived signals along with demographic details and routine blood biomarkers, including fasting glucose and lipid profiles, to predict insulin resistance.
The study, published in Nature, highlights that individuals with insulin resistance are at a higher risk of developing diabetes, cardiovascular disease, hyperlipidaemia, and hypertension.
Findings from the research suggest that relying solely on fasting glucose levels is insufficient for accurately estimating insulin resistance, underlining the importance of incorporating lifestyle-related data into risk assessment.
"In this study, we present a method for predicting IR (insulin resistance) using signals derived from a consumer smartwatch, demographics and routinely measured blood biomarkers. This method has the potential to be scaled to millions of people, and to enable widespread identification of IR," the authors wrote.
"We assembled a large cohort (n=1,165) with a combined set of data from wearable devices, together with demographics and blood biomarkers, and a ground-truth measure of IR," they said.
As part of the research, the team also developed a large language model called ‘IR agent’, which integrates assessment results with lifestyle and biomarker data to provide a comprehensive view of metabolic health and diabetes risk, along with personalised recommendations.
"This work establishes a scalable, accessible framework for early detection of metabolic risk, which could enable timely lifestyle interventions to prevent progression to type-2 diabetes," the authors said.
Researchers from Google Research in the United States analysed data from 1,165 participants, using smartwatch-derived signals along with demographic details and routine blood biomarkers, including fasting glucose and lipid profiles, to predict insulin resistance.
The study, published in Nature, highlights that individuals with insulin resistance are at a higher risk of developing diabetes, cardiovascular disease, hyperlipidaemia, and hypertension.
Findings from the research suggest that relying solely on fasting glucose levels is insufficient for accurately estimating insulin resistance, underlining the importance of incorporating lifestyle-related data into risk assessment.
"In this study, we present a method for predicting IR (insulin resistance) using signals derived from a consumer smartwatch, demographics and routinely measured blood biomarkers. This method has the potential to be scaled to millions of people, and to enable widespread identification of IR," the authors wrote.
"We assembled a large cohort (n=1,165) with a combined set of data from wearable devices, together with demographics and blood biomarkers, and a ground-truth measure of IR," they said.
As part of the research, the team also developed a large language model called ‘IR agent’, which integrates assessment results with lifestyle and biomarker data to provide a comprehensive view of metabolic health and diabetes risk, along with personalised recommendations.
"This work establishes a scalable, accessible framework for early detection of metabolic risk, which could enable timely lifestyle interventions to prevent progression to type-2 diabetes," the authors said.
Diabetes Risk DetectionDigital Health InnovationGoogle Research
