Preprint · OA
via OpenAlex
A novel health risk model based on intraday physical activity time series collected by smartphones
Evgeny Getmantsev, Boris Zhurov, Timothy V. Pyrkov, Peter O. Fedichev
arXiv (Cornell University) · 2018 · ▲ 4 citations
Abstract
We compiled a demo application and collected a motion database of more than 10,000 smartphone users to produce a health risk model trained on physical activity streams. We turned to adversarial domain adaptation and employed the UK Biobank dataset of motion data, augmented by a rich set of clinical information as the source domain to train the model using a deep residual convolutional neuron network (ResNet). The model risk score is a biomarker of ageing, since it was predictive of lifespan and healthspan(definition) (as defined by the onset of specified diseases), and was elevated in groups associated with life-shortening lifestyles, such as smoking. We ascertained the target domain performance in a smaller cohort of the mobile application that included users who were willing to share answers to a short questionnaire related to their disease and smoking status. We thus conclude that the proposed pipeline combining deep convolutional and Domain Adversarial neuron networks (DANN) is a powerful tool for disease risk and lifestyle-associated hazard assessment from mobile motion sensors that are transferable across devices and populations.
◌ CITATION ONLY
Full text is not openly licensed for redistribution here. Read it at the source:
Provenance
- Source
- OpenAlex
- DOI
- 10.48550/arxiv.1812.02522
- Canonical
- link ↗
- Fetched
- 2026-11-08 MST
Cite this
APA
Getmantsev, E., Zhurov, B., Pyrkov, T.V., & Fedichev, P.O. (2018). A novel health risk model based on intraday physical activity time series collected by smartphones. <em>arXiv (Cornell University)</em>. https://doi.org/10.48550/arxiv.1812.02522
Vancouver
Getmantsev E, Zhurov B, Pyrkov TV, Fedichev PO. A novel health risk model based on intraday physical activity time series collected by smartphones. arXiv (Cornell University). 2018. doi:10.48550/arxiv.1812.02522.
BibTeX
@unpublished{evgeny2018Anovel,
title = {A novel health risk model based on intraday physical activity time series collected by smartphones},
author = {Evgeny Getmantsev and Boris Zhurov and Timothy V. Pyrkov and Peter O. Fedichev},
journal = {arXiv (Cornell University)},
year = {2018},
doi = {10.48550/arxiv.1812.02522},
}
Research neighborhood
References, citing works, and semantically nearest findings. Click a node to open it.
Related findings
arXiv (Cornell University) 2025
Preprint · OA
Profiling Frailty: A parsimonious Frailty Index from health administrative data based on POSET theory
57GGardner 2022
Open access · US-GOV
Development of Physical Activity Features for Ear-worn Devices
BMC Geriatrics 2022
Open access · CC-BY
Low physical activity is the strongest factor associated with frailty phenotype and frailty index: data from baseline phase of Birjand Longitudinal Aging Study (BLAS)
Molecular Psychiatry 2017
Open access · CC-BY
Brain age predicts mortality
European Journal of Preventive Cardiology 2025
Open access · CC-BY
Physical activity and mortality: towards healthspan-oriented metrics and outcomes. A Scientific Statement from the European Association of Preventive Cardiology (EAPC) of the ESC
Fondazione IRCCS Ca' Granda, Ospedale Maggiore Policlinico 2024
Open access · US-GOV