Daily Physical Activity Patterns Enhance Mortality Prediction in NHANES 2011–2014: A Comparative Study Across Classical, Machine Learning, and Deep Learning Models Using Accelerometer Data
Ghosh, Srimanta Cho, Sunwoo Emma Yue, Yuanzhen Matabuena, Marcos Saha, Enakshi Ghosal, Rahul
Ghosh, Srimanta
Cho, Sunwoo Emma
Yue, Yuanzhen
Matabuena, Marcos
Saha, Enakshi
Ghosal, Rahul
Supervisor
Department
Epidemiology
Embargo End Date
Type
Journal article
Date
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
Background : Physical activity (PA) is a crucial modifiable risk factor for mortality among older adults. While most studies use total PA volume as a summary metric, continuously monitored accelerometer data can capture more detailed daily PA patterns. This study compares the ability of classical, machine learning, and deep learning survival models to predict mortality using temporal-pattern-based PA features. Methods : We analyzed data from 3,032 individuals aged ≥50 years from the 2011 to 2014 cohort of the National Health and Nutrition Examination Survey (NHANES), linked with mortality data in the National Death Index. Minute-level accelerometer data were transformed into functional principal components to capture the temporal dynamics of daily activity. We evaluated four survival models: Cox Proportional Hazards, Random Survival Forest, Gradient Boosted Survival Model, and DeepSurv for mortality prediction using Harrell’s C-index and time-dependent area under curve (AUC) over 100 random train-test splits. Results : Based on the Cox Proportional Hazards model, a higher daily PA during the daytime was found to be associated with a reduced hazard of all-cause mortality, while a higher PA during night, indicating disrupted sleep, was found to be associated with a higher hazard of all-cause mortality. The Random Survival Forest model exhibited the highest predictive performance, with a mean C-index of 0.80 and a mean time-dependent AUC of 0.91. This was superior to DeepSurv (C-index: 0.78, AUC: 0.85), Gradient Boosted Survival Model (C-index: 0.78, AUC: 0.83), and the traditional Cox Proportional Hazards model (C-index: 0.77, AUC: 0.82). Notably, machine learning models Random Survival Forest and Gradient Boosted Survival Model demonstrated significant gains when using functional principal components-based features compared to simpler mean activity-based models. Conclusions : Functional features derived from daily activity patterns provide richer interpretation of time-of-day patterns than traditional summary statistics. When combined with flexible machine learning models, they can uncover the complex, nonlinear relationships between PA and survival, improving mortality prediction for older adults.
Citation
S. Ghosh, S.E. Cho, Y. Yue, M. Matabuena, E. Saha, R. Ghosal, "Daily Physical Activity Patterns Enhance Mortality Prediction in NHANES 2011–2014: A Comparative Study Across Classical, Machine Learning, and Deep Learning Models Using Accelerometer Data," Journal for the Measurement of Physical Behaviour, vol. 9, no. 1, 2026, https://doi.org/10.1123/jmpb.2025-0052.
Source
Journal for the Measurement of Physical Behaviour
Conference
Keywords
32 Biomedical and Clinical Sciences, 3202 Clinical Sciences, 40 Engineering, 4009 Electronics, Sensors and Digital Hardware, 3 Good Health and Well Being
Subjects
Source
Publisher
Human Kinetics