Publications

• Circadian Rhythm Analysis Using Wearable-Based Accelerometry as a Digital Biomarker of Aging and Healthspan, npj Digital Medicine
• Wearable‑based accelerometer activity profile as digital biomarker of inflammation, biological age, and mortality using hierarchical clustering analysis in NHANES 2011–2014, Scientific Reports
• Precise Segmentation of U.S. Adults from 24-Hour Wearable-based Physical Activity Profiles Using Machine Learning Clustering, IEEE ICHI 2023

The widespread adoption of personal digital devices, such as smartphones and wearables, offers an unprecedented potential for data collection to assess human health and disease states. Recent research has proposed that digital biomarkers for longevity could be used to identify individuals at higher risk for age-related diseases and to monitor the effectiveness of interventions aimed at promoting healthy aging. Currently, measures of health and longevity are based on factors such as inflammation, biological age, epigenetic clocks, and mortality. While these predictors can provide a better understanding of an individual’s life expectancy than chronological age, their potential for digitization has not been extensively studied.

To this end, leveraging advanced ML and statistical methods on wearable data, I have investigated wearable-derived circadian rest-activity rhythm for biological age prediction and data-driven population segmentation. I developed a novel digital biomarker to predict mortality, morbidity, and age-related functional performance from ~80,000 adults in the UK Biobank and US NHANES datasets.