Preprint · CC-BY
via OpenAlex
Integrating supervised and unsupervised machine learning for behavior segmentation reveals latent frailty signatures and improves aging clocks in isogenic and outbred mice
Gautam S. Sabnis, Dustin Miao, Vivek Kumar
bioRxiv (Cold Spring Harbor Laboratory) · 2026
Abstract
Manual frailty index (FI) assessment in mice is a strong predictor of morbidity and mortality, and is frequently used in mechanistic and translational geroscience. However, it is labor-intensive, requires expert training, and is vulnerable to scorer variability. We previously developed a visual frailty index (vFI) that objectively predicts age and frailty using expert-defined, supervised behavioral features extracted from open-field videos. However, relying solely on human-defined features may miss subtle, latent behavioral signatures of aging. Here, we test whether unsupervised behavioral discovery using Keypoint-MoSeq (KPMS) could uncover these hidden signatures and improve the prediction of aging-related outcomes. Using a large dataset of isogenic C57BL/6J (B6J) and genetically diverse Diversity Outbred (DO) mice, we find that unsupervised features are highly predictive of chronological age, biological frailty, and the proportion of life lived. Notably, while supervised features overall outperformed unsupervised features in these tasks, combining both feature sets yielded the highest predictive accuracy across all outcomes. Despite these improvements, models trained on either feature set failed to generalize across strains, confirming that behavioral manifestations of aging are strongly population-specific. These findings demonstrate that supervised and unsupervised machine vision provide complementary information, establishing a highly sensitive, scalable, and non-invasive framework for objective and scalable geroscience in rodents.
◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:
Provenance
- Source
- OpenAlex
- DOI
- 10.64898/2026.03.23.713050
- Canonical
- link ↗
- Fetched
- 2026-11-05 MST
Cite this
APA
Sabnis, G.S., Miao, D., & Kumar, V. (2026). Integrating supervised and unsupervised machine learning for behavior segmentation reveals latent frailty signatures and improves aging clocks in isogenic and outbred mice. <em>bioRxiv (Cold Spring Harbor Laboratory)</em>. https://doi.org/10.64898/2026.03.23.713050
Vancouver
Sabnis GS, Miao D, Kumar V. Integrating supervised and unsupervised machine learning for behavior segmentation reveals latent frailty signatures and improves aging clocks in isogenic and outbred mice. bioRxiv (Cold Spring Harbor Laboratory). 2026. doi:10.64898/2026.03.23.713050.
BibTeX
@unpublished{gautam2026Integr,
title = {Integrating supervised and unsupervised machine learning for behavior segmentation reveals latent frailty signatures and improves aging clocks in isogenic and outbred mice},
author = {Gautam S. Sabnis and Dustin Miao and Vivek Kumar},
journal = {bioRxiv (Cold Spring Harbor Laboratory)},
year = {2026},
doi = {10.64898/2026.03.23.713050},
}
Research neighborhood
References, citing works, and semantically nearest findings. Click a node to open it.
Related findings
Environmental Epidemiology 2024
Open access · CC-BY
Associations between use of chemical hair products and epigenetic age: Findings from the Sister Study
Aging Clinical and Experimental Research 2024
Open access · CC-BY
Comparison of three frailty measures for predicting hospitalization and mortality in the Canadian Longitudinal Study on Aging
bioRxiv (Cold Spring Harbor Laboratory) 2025
Preprint · CC-BY
CpGeneAge: multi-omics aging clocks associated with Nf-κB signaling pathway in aging
Atria Research and Global Health Institute (ARGHI) 2026
Open access · US-GOV
Tirzepatide and Organ-Specific Biological Aging: A Parallel-Design Feasibility Study Using Proteomic Organ Clocks in a Preventive Brain Health Cohort
Frontiers in Aging 2024
Open access · CC-BY
Assessing the utility of epigenetic clocks for health prediction in South Korean
Nature Communications 2020
Open access · CC-BY