• Multi-level determinants of ph...

Treffer: Multi-level determinants of physical activity and sports participation among adults during COVID-19 pandemic: an interpretable machine learning approach.

Title:
Multi-level determinants of physical activity and sports participation among adults during COVID-19 pandemic: an interpretable machine learning approach.
Authors:
Zhao K; School of Economics and Management, Chengdu Sport University, Chengdu, China., Chen Z; School of Physical Education and Health, Guangdong Polytechnic Normal University, Guangzhou, China., Huang Q; School of Intelligent Sports Engineering, Wuhan Sports University, Wuhan, China., Li S; School of Economics and Management, Wuhan Sports University, Wuhan, China., Tan G; School of Physical Education and Sports Science, South China Normal University, Guangzhou, China., Guo K; School of Economics and Management, Wuhan Sports University, Wuhan, China., Jiang L; School of Management, Beijing Sport University, Beijing, China.
Source:
Frontiers in psychology [Front Psychol] 2026 Jan 07; Vol. 16, pp. 1701201. Date of Electronic Publication: 2026 Jan 07 (Print Publication: 2025).
Publication Type:
Journal Article
Language:
English
Journal Info:
Publisher: Frontiers Research Foundation Country of Publication: Switzerland NLM ID: 101550902 Publication Model: eCollection Cited Medium: Print ISSN: 1664-1078 (Print) Linking ISSN: 16641078 NLM ISO Abbreviation: Front Psychol Subsets: PubMed not MEDLINE
Imprint Name(s):
Original Publication: Pully, Switzerland : Frontiers Research Foundation
References:
J Phys Act Health. 2012 Feb;9(2):163-72. (PMID: 22368216)
Int J Health Geogr. 2020 Jun 20;19(1):22. (PMID: 32563255)
SSM Popul Health. 2021 Nov 12;16:100964. (PMID: 34841038)
J Sport Health Sci. 2016 Sep;5(3):315-321. (PMID: 30356490)
J Occup Health. 2023 Jan;65(1):e12382. (PMID: 36627728)
Physiol Meas. 2014 Nov;35(11):2191-203. (PMID: 25340969)
Annu Rev Public Health. 2006;27:297-322. (PMID: 16533119)
BMC Public Health. 2015 Aug 20;15:806. (PMID: 26290046)
Front Psychol. 2020 Jun 30;11:1372. (PMID: 32695049)
Leis Stud. 2023 Aug 26;43(2):342-351. (PMID: 38562149)
J Sports Sci. 2022 Jan;40(1):116-124. (PMID: 34503395)
Psychol Sport Exerc. 2024 May;72:102609. (PMID: 38360078)
CMAJ. 2006 Mar 14;174(6):801-9. (PMID: 16534088)
Acta Psychol (Amst). 2024 Mar;243:104139. (PMID: 38237470)
Am J Prev Med. 2003 Jan;24(1):22-8. (PMID: 12554020)
Pan Afr Med J. 2017 Mar 01;26:110. (PMID: 28533833)
PLoS One. 2024 Jun 25;19(6):e0305820. (PMID: 38917146)
Cureus. 2023 Jan 7;15(1):e33475. (PMID: 36756008)
Obesity (Silver Spring). 2008 Feb;16(2):402-8. (PMID: 18239651)
Health Promot Pract. 2021 Sep;22(5):622-630. (PMID: 33955244)
Behav Sci (Basel). 2024 Sep 17;14(9):. (PMID: 39336046)
Syst Rev. 2023 Jun 21;12(1):102. (PMID: 37344901)
Lancet Glob Health. 2024 Aug;12(8):e1232-e1243. (PMID: 38942042)
J Act Sedentary Sleep Behav. 2022 Dec 2;1(1):9. (PMID: 40229978)
Front Public Health. 2025 Jun 05;13:1601577. (PMID: 40538690)
Risk Manag Healthc Policy. 2021 Nov 23;14:4697-4708. (PMID: 34866945)
Alzheimers Dement (N Y). 2021 May 13;7(1):e12169. (PMID: 34027023)
Res Q Exerc Sport. 2010 Mar;81(1):97-101. (PMID: 20387403)
Health Educ Q. 1988 Winter;15(4):351-77. (PMID: 3068205)
Prog Cardiovasc Dis. 2021 Jan-Feb;64:33-40. (PMID: 33428966)
J Mach Learn Res. 2019;20:. (PMID: 34335110)
Front Psychol. 2021 Mar 05;12:622929. (PMID: 33746840)
Sports Med. 2019 Oct;49(10):1585-1607. (PMID: 31267483)
PLoS One. 2021 May 17;16(5):e0250770. (PMID: 33999924)
J Sports Sci. 2024 Sep;42(17):1651-1663. (PMID: 39300762)
BMC Public Health. 2018 May 2;18(1):568. (PMID: 29716551)
J Environ Public Health. 2022 Aug 26;2022:4580589. (PMID: 36060889)
Int J Environ Res Public Health. 2020 Jul 16;17(14):. (PMID: 32708630)
BMC Public Health. 2024 Jul 17;24(1):1923. (PMID: 39020343)
J Korean Med Sci. 2021 Jan 18;36(3):e19. (PMID: 33463093)
Int J Prev Med. 2023 Feb 18;14:15. (PMID: 37033280)
Arch Public Health. 2025 Jun 10;83(1):147. (PMID: 40495242)
Bioinformatics. 2012 Jan 1;28(1):112-8. (PMID: 22039212)
Int Rev Educ. 2020;66(4):575-602. (PMID: 32836371)
Int J Behav Nutr Phys Act. 2014 Mar 11;11(1):37. (PMID: 24618001)
Front Physiol. 2021 Sep 22;12:682233. (PMID: 34630133)
Lancet Diabetes Endocrinol. 2016 Jun;4(6):487-97. (PMID: 27133172)
Front Public Health. 2024 Oct 21;12:1414837. (PMID: 39498106)
BMC Med Res Methodol. 2018 Dec 22;18(1):176. (PMID: 30577770)
Int J Obes Relat Metab Disord. 1999 Apr;23 Suppl 3:S55-63. (PMID: 10368004)
BMC Sports Sci Med Rehabil. 2022 Mar 21;14(1):42. (PMID: 35313960)
BMC Med Inform Decis Mak. 2019 Aug 22;19(1):169. (PMID: 31438926)
Entropy (Basel). 2023 May 08;25(5):. (PMID: 37238520)
BMC Public Health. 2025 Oct 1;25(1):3281. (PMID: 41034910)
Int J Sports Physiol Perform. 2020 Jun 21;15(7):917-919. (PMID: 32570215)
Ann Behav Med. 2003 Dec;26(3):172-81. (PMID: 14644693)
Risk Manag Healthc Policy. 2021 Jun 03;14:2319-2331. (PMID: 34113188)
Risk Manag Healthc Policy. 2020 Sep 03;13:1419-1430. (PMID: 32943959)
J Transl Med. 2020 Jun 8;18(1):229. (PMID: 32513197)
Int J Environ Res Public Health. 2022 Feb 16;19(4):. (PMID: 35206434)
J Med Internet Res. 2021 Feb 3;23(2):e23701. (PMID: 33347421)
J Am Med Dir Assoc. 2019 Aug;20(8):1032-1036. (PMID: 30792108)
Public Health. 2022 Jun;207:7-13. (PMID: 35452934)
Circulation. 2013 Nov 12;128(20):2259-79. (PMID: 24126387)
Br J Sports Med. 2020 Dec;54(24):1451-1462. (PMID: 33239350)
Scand J Med Sci Sports. 2018 Aug;28(8):1908-1915. (PMID: 29697863)
Public Health Rep. 1985 Mar-Apr;100(2):126-31. (PMID: 3920711)
Br J Sports Med. 2013 Jan;47(1):44-8. (PMID: 22522584)
Int J Behav Nutr Phys Act. 2019 Dec 9;16(1):124. (PMID: 31815626)
Int J Environ Res Public Health. 2021 Apr 09;18(8):. (PMID: 33918760)
J Sports Sci. 2018 Aug;36(15):1784-1791. (PMID: 29272203)
J Phys Act Health. 2021 Apr 21;18(6):737-747. (PMID: 33883289)
Food Nutr Bull. 2004 Sep;25(3):292-302. (PMID: 15460274)
Front Public Health. 2024 Jan 08;11:1309824. (PMID: 38259776)
Front Public Health. 2023 Jan 04;10:1069219. (PMID: 36684986)
J Sports Sci. 2022 Feb;40(3):310-322. (PMID: 34720042)
Aust N Z J Public Health. 2017 Jun;41(3):248-255. (PMID: 28110514)
Percept Mot Skills. 2024 Apr;131(2):537-550. (PMID: 38252595)
Environ Sci Technol. 2021 Oct 5;55(19):12741-12754. (PMID: 34403250)
Br J Sports Med. 2022 May;56(10):568-576. (PMID: 35140062)
Int J Behav Nutr Phys Act. 2013 Aug 15;10:98. (PMID: 23945179)
Br J Sports Med. 2014 Feb;48(3):220-5. (PMID: 24002240)
Front Psychol. 2024 Dec 06;15:1471658. (PMID: 39712543)
Acta Paediatr. 2020 Oct;109(10):2147-2148. (PMID: 32557827)
Front Sports Act Living. 2021 Dec 08;3:682287. (PMID: 34957395)
JAMA Netw Open. 2020 Jan 3;3(1):e1918962. (PMID: 31922560)
Eur J Sport Sci. 2022 Apr;22(4):511-520. (PMID: 33568023)
Sci Rep. 2023 Sep 20;13(1):15628. (PMID: 37730690)
Sports (Basel). 2019 May 23;7(5):. (PMID: 31126126)
PLoS One. 2020 Sep 25;15(9):e0239378. (PMID: 32976547)
Malays J Nutr. 2011 Apr;17(1):67-75. (PMID: 22135866)
Res Q Exerc Sport. 2024 Dec;95(4):873-885. (PMID: 38875156)
Contributed Indexing:
Keywords: COVID-19; adults; influencing factors; interpretable machine learning; physical activity; socio-ecological model; sports participation
Entry Date(s):
Date Created: 20260123 Date Completed: 20260123 Latest Revision: 20260125
Update Code:
20260125
PubMed Central ID:
PMC12819603
DOI:
10.3389/fpsyg.2025.1701201
PMID:
41574062
Database:
MEDLINE

Weitere Informationen

Background: Both physical activity (PA) and sports participation (SP) are considered important for the promotion of health among adults in the post-disease outbreak period. In the context of the COVID-19 pandemic, the study applied the Socio-ecological Model, with a total of 45 factors on four levels: individual characteristics, individual behaviors, interpersonal relationships, and community environment. The aim was to apply interpretable machine learning algorithms in the examination of common and distinct determinants of PA and SP with the purpose of deriving specific insights relevant to public health policy.
Methods: To examine the comparable but different patterns of behavior regarding PA and SP, this research used the Chinese General Social Survey of 2021 with a sample of N = 2,717 participants. Eight machine learning models were designed with the aid of Python coding, including the following models: Logistic Regression, Support Vector Machine, Decision Tree, Random Forest (RF), Adaptive Boosting, Gradient Boosting Decision Tree, eXtreme Gradient Boosting Model (XGBoost), and Light Gradient Boosting. As part of evaluating these models' performance, Accuracy, Area Under the Curve (AUC), and the F1-score results were used after executing the grid search on the models' respective variables. The Permutation Feature Importance method was used to quantify factor importance and identify key factors, and Partial Dependence Plots were generated to interpret the direction of these influences.
Results: Results showed that the best algorithm for predicting PA was the RF with an AUC of 0.613 and that it selected 10 key factors. Additionally, the best algorithm that predicted SP was XGBoost with an AUC of 0.772, and it selected 12 key factors. Common influencing factors during the COVID-19 pandemic include suitability for exercise and recreational lifestyle, with BMI category also playing a significant role. Distinctive factors of PA were primarily related to the community environment (e.g., fresh food outlets and neighborhood care), reflecting its dependence on environmental contexts. In contrast, distinctive factors of SP were more concentrated at the individual characteristics (e.g., education level and socioeconomic status) and behaviors level (e.g., learning and health examination), highlighting the role of personal initiative and the accumulation of socio-cultural and economic capital.
Conclusion: The Socio-ecological Model effectively delineated commonalities as well as differences in determinants of PA and SP across adults during the COVID-19 pandemic. Interpretable machine learning aided in identifying and ranking multi-level determinants, offering a nuanced insight into the relative importance across levels of ecology. These findings provide data-driven insights for future disease outbreaks, facilitating the targeted allocation of intervention resources to key influencing domains.
(Copyright © 2026 Zhao, Chen, Huang, Li, Tan, Guo and Jiang.)

The author(s) declared that this work was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.