Capturing Real-World Habitual Sleep Patterns With a Novel User-Centric Algorithm to Preprocess Fitbit Data in the All of Us Research Program: Retrospective Observational Longitudinal Study
Journal of Medical Internet Research · 2025
DOI: 10.2196/71718 ↗At a glance
Beobachtungsstudie in Journal of Medical Internet Research, 2025. Written by Hiral Master and 11 co-authors. Institution: Vanderbilt University Medical Center, Nashville, TN, United States. Major MEDLINE topics: Algorithms, Sleep, Wearable Electronic Devices. Cited 4 times so far (Crossref); 35 references. The full text is freely available in PubMed Central. Funded by: NIH HHS, NHLBI NIH HHS, FDA HHS.
Abstract (original language)
Background
Commercial wearables such as Fitbit quantify sleep metrics using fixed calendar times as default measurement periods, which may not adequately account for individual variations in sleep patterns. To address this limitation, experts in sleep medicine and wearable technology developed a user-centric algorithm designed to more accurately reflect actual sleep behaviors and improve the validity of wearable-derived sleep metrics.
Objective
This study aims to describe the development of a new user-centric algorithm, compare its performance with the default calendar-relative algorithm, and provide a practical guide for analyzing All of Us Fitbit sleep data on a cloud-based platform.
Methods
The default and user-centric algorithms were implemented to preprocess and compute sleep metrics related to schedule, duration, and disturbances using high-resolution Fitbit sleep data from 8563 participants (median age 58.1 years, 6002/8341, 71.96%, female) in the All of Us Research Program (version 7 Controlled Tier). Variations in typical sleep patterns were calculated by examining the differences in the mean number of primary sleep logs classified by each algorithm. Linear mixed-effects models were used to compare differences in sleep metrics across quartiles of variation in typical sleep patterns.
Results
Out of 8,452,630 total sleep logs collected over a median of 4.2 years of Fitbit monitoring, 401,777 (4.75%) nonprimary sleep logs identified by the default algorithm were reclassified as primary sleep by the user-centric algorithm. Variation in typical sleep patterns ranged from –0.08 to 1. Among participants with the greatest variation in typical sleep patterns, the user-centric algorithm identified significantly more total sleep time (by 17.6 minutes; P
Subjects
MeSH terms (MEDLINE)
Author keywords
Authors and institutions
- Vanderbilt University Medical Center, Nashville, TN, United States.
- Google, Mountain View, CA, United States.
- Brigham and Women's Hospital, Boston, MA, United States.
ORCID profiles: Hiral Master, Jeffrey Annis, Jack H Ching, Karla Gleichauf, Lide Han, Peyton Coleman, Kelsie M Full, Neil Zheng, Douglas Ruderfer, John Hernandez, Logan D Schneider, Evan L Brittain
Funding
- NIH HHS
- NHLBI NIH HHS
- FDA HHS
Cite
APA
Master, H., Annis, J., Ching, J. H., Gleichauf, K., Han, L., Coleman, P., Full, K. M., Zheng, N., Ruderfer, D., Hernandez, J., Schneider, L. D., & Brittain, E. L. (2025). Capturing Real-World Habitual Sleep Patterns With a Novel User-Centric Algorithm to Preprocess Fitbit Data in the All of Us Research Program: Retrospective Observational Longitudinal Study. Journal of Medical Internet Research. https://doi.org/10.2196/71718
Vancouver
Master H, Annis J, Ching JH, Gleichauf K, Han L, Coleman P, et al. Capturing Real-World Habitual Sleep Patterns With a Novel User-Centric Algorithm to Preprocess Fitbit Data in the All of Us Research Program: Retrospective Observational Longitudinal Study. Journal of Medical Internet Research. 2025. doi:10.2196/71718
BibTeX
@article{Master2025,
author = {Master, Hiral and Annis, Jeffrey and Ching, Jack H and Gleichauf, Karla and Han, Lide and Coleman, Peyton and Full, Kelsie M and Zheng, Neil and Ruderfer, Douglas and Hernandez, John and Schneider, Logan D and Brittain, Evan L},
title = {Capturing Real-World Habitual Sleep Patterns With a Novel User-Centric Algorithm to Preprocess Fitbit Data in the All of Us Research Program: Retrospective Observational Longitudinal Study},
journal = {Journal of Medical Internet Research},
year = {2025},
doi = {10.2196/71718}
}
EUVIMED