Motif clustering and digital biomarker extraction for free-living physical activity analysis

Abstract Background Analyzing free-living physical activity (PA) data presents challenges due to variability in daily routines and the lack of activity labels. Traditional approaches often rely on summary statistics, which may not capture the nuances of individual activity patterns. To address these...

Full description

Saved in:
Bibliographic Details
Main Authors: Ya-Ting Liang, Charlotte Wang
Format: Article
Language:English
Published: BMC 2025-01-01
Series:BioData Mining
Subjects:
Online Access:https://doi.org/10.1186/s13040-025-00424-1
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849726171992817664
author Ya-Ting Liang
Charlotte Wang
author_facet Ya-Ting Liang
Charlotte Wang
author_sort Ya-Ting Liang
collection DOAJ
description Abstract Background Analyzing free-living physical activity (PA) data presents challenges due to variability in daily routines and the lack of activity labels. Traditional approaches often rely on summary statistics, which may not capture the nuances of individual activity patterns. To address these limitations and advance our understanding of the relationship between PA patterns and health outcomes, we propose a novel motif clustering algorithm that identifies and characterizes specific PA patterns. Methods This paper proposes an elastic distance-based motif clustering algorithm for identifying specific PA patterns (motifs) in free-living PA data. The algorithm segments long-term PA curves into short-term segments and utilizes elastic shape analysis to measure the similarity between activity segments. This enables the discovery of recurring motifs through pattern clustering. Then, functional principal component analysis (FPCA) is then used to extract digital biomarkers from each motif. These digital biomarkers can subsequently be used to explore the relationship between PA and health outcomes of interest. Results We demonstrate the efficacy of our method through three real-world applications. Results show that digital biomarkers derived from these motifs effectively capture the association between PA patterns and disease outcomes, improving the accuracy of patient classification. Conclusions This study introduced a novel approach to analyzing free-living PA data by identifying and characterizing specific activity patterns (motifs). The derived digital biomarkers provide a more nuanced understanding of PA and its impact on health, with potential applications in personalized health assessment and disease detection, offering a promising future for healthcare.
format Article
id doaj-art-7792a8c9f8f34a6fa71921dafedb4d26
institution DOAJ
issn 1756-0381
language English
publishDate 2025-01-01
publisher BMC
record_format Article
series BioData Mining
spelling doaj-art-7792a8c9f8f34a6fa71921dafedb4d262025-08-20T03:10:17ZengBMCBioData Mining1756-03812025-01-0118111610.1186/s13040-025-00424-1Motif clustering and digital biomarker extraction for free-living physical activity analysisYa-Ting Liang0Charlotte Wang1Institute of Epidemiology and Preventive Medicine, College of Public Health, National Taiwan UniversityInstitute of Health Data Analytics and Statistics, College of Public Health, National Taiwan UniversityAbstract Background Analyzing free-living physical activity (PA) data presents challenges due to variability in daily routines and the lack of activity labels. Traditional approaches often rely on summary statistics, which may not capture the nuances of individual activity patterns. To address these limitations and advance our understanding of the relationship between PA patterns and health outcomes, we propose a novel motif clustering algorithm that identifies and characterizes specific PA patterns. Methods This paper proposes an elastic distance-based motif clustering algorithm for identifying specific PA patterns (motifs) in free-living PA data. The algorithm segments long-term PA curves into short-term segments and utilizes elastic shape analysis to measure the similarity between activity segments. This enables the discovery of recurring motifs through pattern clustering. Then, functional principal component analysis (FPCA) is then used to extract digital biomarkers from each motif. These digital biomarkers can subsequently be used to explore the relationship between PA and health outcomes of interest. Results We demonstrate the efficacy of our method through three real-world applications. Results show that digital biomarkers derived from these motifs effectively capture the association between PA patterns and disease outcomes, improving the accuracy of patient classification. Conclusions This study introduced a novel approach to analyzing free-living PA data by identifying and characterizing specific activity patterns (motifs). The derived digital biomarkers provide a more nuanced understanding of PA and its impact on health, with potential applications in personalized health assessment and disease detection, offering a promising future for healthcare.https://doi.org/10.1186/s13040-025-00424-1Digital biomarkerActivity patternFunctional data analysisFeature extractionClusteringAssociation
spellingShingle Ya-Ting Liang
Charlotte Wang
Motif clustering and digital biomarker extraction for free-living physical activity analysis
BioData Mining
Digital biomarker
Activity pattern
Functional data analysis
Feature extraction
Clustering
Association
title Motif clustering and digital biomarker extraction for free-living physical activity analysis
title_full Motif clustering and digital biomarker extraction for free-living physical activity analysis
title_fullStr Motif clustering and digital biomarker extraction for free-living physical activity analysis
title_full_unstemmed Motif clustering and digital biomarker extraction for free-living physical activity analysis
title_short Motif clustering and digital biomarker extraction for free-living physical activity analysis
title_sort motif clustering and digital biomarker extraction for free living physical activity analysis
topic Digital biomarker
Activity pattern
Functional data analysis
Feature extraction
Clustering
Association
url https://doi.org/10.1186/s13040-025-00424-1
work_keys_str_mv AT yatingliang motifclusteringanddigitalbiomarkerextractionforfreelivingphysicalactivityanalysis
AT charlottewang motifclusteringanddigitalbiomarkerextractionforfreelivingphysicalactivityanalysis