ADAMMA - Core for AI & Digital Biomarker Research

Digital Biomarker of Aging

Long-term lifestyle behaviors like physical activity, circadian rhythms, and sleep are closely linked to health outcomes, chronic disease incidence, and biological aging. Scalable digital devices, such as smartwatches and smartphones, facilitate continuous data collection to quantify these behaviors and explore their relationship to aging. Our research focuses on developing digital biomarkers of aging by applying advanced statistical methods, machine learning, and data science to wearable-derived accelerometer data. This work has led to publications in Scientific Reports and npj Digital Medicine, as well as presentations at IEEE ICHI 2023 and IEEE EMBC 2024. Additionally, we are developing an open-source package to enable researchers to apply our biological age algorithm using their own wearable or smartwatch data.

Publications

Circadian rhythm analysis using wearable-based accelerometry as a digital biomarker of aging and healthspan
Circadian rhythm analysis using wearable-based accelerometry as a digital biomarker of aging and healthspan
Jinjoo Shim, Elgar Fleisch, Filipe Barata
npj Digital Medicine  ·  04 Jun 2024  ·  doi:10.1038/s41746-024-01111-x
Precise Segmentation of U.S. Adults from 24-Hour Wearable-based Physical Activity Profiles Using Machine Learning Clustering
Precise Segmentation of U.S. Adults from 24-Hour Wearable-based Physical Activity Profiles Using Machine Learning Clustering
Jinjoo Shim, Elgar Fleisch, Filipe Barata
2023 IEEE 11th International Conference on Healthcare Informatics (ICHI)  ·  26 Jun 2023  ·  doi:10.1109/ichi57859.2023.00083
XGBAge: Prediction and Identification of Factors Influencing Biological Age Using Wearable Accelerometer Data
XGBAge: Prediction and Identification of Factors Influencing Biological Age Using Wearable Accelerometer Data
Jinjoo Shim, Elgar Fleisch, Filipe Barata
2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  ·  15 Jul 2024  ·  doi:10.1109/embc53108.2024.10781878