Engineering digital biomarkers of interstitial glucose from noninvasive smartwatches

TLDR

Prediabetes affects one in three people and progresses to type 2 diabetes in about 10 % of cases annually, yet no noninvasive, commercially available method exists for monitoring glycemic health. The study aims to develop practical, noninvasive strategies for monitoring and managing glycemic health in prediabetes. The authors design predictive variables from wearable smartwatch data using data‑driven and domain‑driven approaches to estimate interstitial glucose. Using 25,000 paired smartwatch and interstitial glucose measurements, the method achieved up to 84 % accuracy in detecting glucose deviations and 87 % accuracy in real‑time glucose prediction over 10 days.

Abstract

Abstract Prediabetes affects one in three people and has a 10% annual conversion rate to type 2 diabetes without lifestyle or medical interventions. Management of glycemic health is essential to prevent progression to type 2 diabetes. However, there is currently no commercially-available and noninvasive method for monitoring glycemic health to aid in self-management of prediabetes. There is a critical need for innovative, practical strategies to improve monitoring and management of glycemic health. In this study, using a dataset of 25,000 simultaneous interstitial glucose and noninvasive wearable smartwatch measurements, we demonstrated the feasibility of using noninvasive and widely accessible methods, including smartwatches and food logs recorded over 10 days, to continuously detect personalized glucose deviations and to predict the exact interstitial glucose value in real time with up to 84% and 87% accuracy, respectively. We also establish methods for designing variables using data-driven and domain-driven methods from noninvasive wearables toward interstitial glucose prediction.