Identifying cluster profiles based on barriers and facilitators to physical activity during COVID-19 confinement: A cross-sectional study using machine learning analysis
PLOS One · 27.07.2026 · 21 (7) · e0354036
DOI: 10.1371/journal.pone.0354036 ↗Kurz gefasst
Querschnittstudie in der Zeitschrift PLOS One, online erschienen am 27.07.2026. Verfasst von Fernanda Castro Monteiro und 10 weiteren Autor:innen. Beteiligte Einrichtung: Psychiatry Institute, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil. Hauptthemen laut MEDLINE: COVID-19, Machine Learning, Exercise. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: CNPQ, Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro.
Abstract (Originalsprache)
Social restrictions, such as confinement periods, tend to reduce physical activity (PA) levels. However, sociodemographic factors may influence specific barriers and facilitators to PA during such periods. This study aimed to identify cluster profiles of individuals based on barriers and facilitators to physical activity (PA) during COVID-19 confinement. Brazilian adults participated in a cross-sectional online survey. The questionnaire collected demographic data, PA levels, sedentary behavior (SB), and perceived barriers and facilitators for PA. During data preprocessing, correlated barriers and facilitators related to a similar topic were aggregated. Using machine learning analysis, the K-modes evaluated by the Silhouette Score were used for barriers and the ROCK evaluated by the Silhouette Score was used for facilitators. The barriers model produced well-defined profiles, whereas the facilitators model did not. The facilitator model generated clusters with multiple negative silhouette coefficients and exhibited a significantly less cohesive cluster structure. Therefore, only the barriers-based model was used for further analysis. The best model generated eight clusters, each named according to the most frequent barriers in the group, such as “Inactive depressive women”, “Active depressive women” and “Super active”. The depressive clusters presented more barriers to PA, three barriers each one. Significant differences in PA and SB were observed across clusters. This work highlights the novelty of using unsupervised machine learning to uncover latent subgroups based on multiple concurrent barriers. In conclusion, tailored home-based and outdoor strategies should be developed, particularly targeting individuals with depressive symptoms and those facing significant time constraints.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Psychiatry Institute, Federal University of Rio de Janeiro, Rio de Janeiro, Brazil.
- Institute of Health Sciences, Universidad de O'Higgins, Rancagua, Chile.
- National Institute of Technology, Rio de Janeiro, Brazil.
- Rio de Janeiro State University, Rio de Janeiro, Brazil.
- Federal University of Santa Maria, Santa Maria, Brazil.
- Faculty of Health Sciences, Universidad Autónoma de Chile, Providência, Chile.
ORCID-Profile: Henrique Nunes Pereira Oliva, Lara Carneiro
Förderung
- CNPQ
- Fundação Carlos Chagas Filho de Amparo à Pesquisa do Estado do Rio de Janeiro
Zitieren
APA
Castro Monteiro, F., Luiza C Wuillaume, M., Linhares Veloso Filho, C., Figueiredo, K., Barreto Schuch, F., Nunes de Carvalho, A., Sousa Matias, T., Nunes Pereira Oliva, H., Sobral Monteiro-Junior, R., Carneiro, L., & Camaz Deslandes, A. (2026). Identifying cluster profiles based on barriers and facilitators to physical activity during COVID-19 confinement: A cross-sectional study using machine learning analysis. PLOS One, 21(7), e0354036. https://doi.org/10.1371/journal.pone.0354036
Vancouver
Castro Monteiro F, Luiza C Wuillaume M, Linhares Veloso Filho C, Figueiredo K, Barreto Schuch F, Nunes de Carvalho A, et al. Identifying cluster profiles based on barriers and facilitators to physical activity during COVID-19 confinement: A cross-sectional study using machine learning analysis. PLOS One. 2026;21(7):e0354036. doi:10.1371/journal.pone.0354036
BibTeX
@article{CastroMonteiro2026,
author = {Castro Monteiro, Fernanda and Luiza C Wuillaume, Maria and Linhares Veloso Filho, Carlos and Figueiredo, Karla and Barreto Schuch, Felipe and Nunes de Carvalho, Andrea and Sousa Matias, Thiago and Nunes Pereira Oliva, Henrique and Sobral Monteiro-Junior, Renato and Carneiro, Lara and Camaz Deslandes, Andrea},
title = {Identifying cluster profiles based on barriers and facilitators to physical activity during COVID-19 confinement: A cross-sectional study using machine learning analysis},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0354036},
doi = {10.1371/journal.pone.0354036}
}
EUVIMED