Modeling and analysis of independent mobility among older adults based on CatBoost-SHAP

Abstract

Ensuring independent mobility for older adults has become a public health and social concern in China owing to its rapidly aging population. To explore independent mobility trends among older adults and the impact of sociodemographic characteristics in recent years, this study used data from the Chinese Longitudinal Healthy Longevity Survey from 2012 to 2018, combined with binomial logit regression and CatBoost-Shapley additive explanation (SHAP) method to analyze the relationship between independent mobility and sociodemographic characteristics under bus- and walking-oriented environments. Study findings indicated that age and gender significantly affected the independent mobility of older adults. Policymaking should prioritize the needs of older adults, focusing on age and gender differences. Additionally, living expense adequacy significantly influenced independent mobility. Policies should substantially support economically disadvantaged older adults, ensuring their basic needs are met through subsidies and other measures. Moreover, the study found a notable impact of widowhood on independent mobility, suggesting enhanced social care and mental health support for widowed older adults, especially those who are long-lived. The outcomes of this study provided evidence for policymakers, which are beneficial for developing elderly-friendly travel policies to ensure and enhance the quality of life and independent mobility of older adults.

Keywords

independent mobility / cohort analysis / Shapley additive explanation (SHAP) / CatBoost model

References

[1] LIU Y Q, TAMURA R. Impact of Internet use on subjective well-being among future elderly in China: The mediation role of loneliness[C]// Proceedings of the 8th International Conference on Kansei Engineering and Emotion Research. Singapore, 2020: 329-339.

[2] XU P Y, ZHAO L D. Analysis of health insurance reform strategies from a risk-sharing perspective based on the Markov model[J]. Journal of Southeast University (English Edition), 2025, 41(1): 118-126.

[3] FENG X W, LIU L. A review on the characteristics and guidance strategies of bus travel for the elderly[J]. Journal of Transportation Engineering and Information, 2023, 21(1): 29-48. (in Chinese)

[4] XUE L, WANG X Y, SHAO J N, et al. Reconfiguration of structural hierarchy of brain in depression in the context of antidepressant effects[J]. Journal of Southeast University (Natural Science Edition), 2025, 55(2): 618-624. (in Chinese)

[5] CARAGATA G. Should I drive today? Development of a daily driving decisions model for older adults[J]. Transportation Research Part F: Traffic Psychology and Behaviour, 2021, 81: 158-172.

[6] BUTLER M, BROOKLAND R, SHOPE J T, et al. Medical fitness to drive assessment with older drivers: A qualitative study with general practitioners in New Zealand[J]. Journal of Transport & Health, 2020, 17: 100856.

[7] GORMLEY M, O’NEILL D. Driving as a travel option for older adults: Findings from the Irish longitudinal study on aging[J]. Frontiers in Psychology, 2019, 10: 1329.

[8] CHEN F, XU S, LI C X, et al. Comprehensive evaluation method for plateau driving fatigue based on psychophysiological indicators[J]. Journal of Southeast University (English Edition), 2024, 40(4): 355-362.

[9] SARKER R I, MAILER M, SIKDER S K. Walking to a public transport station: Empirical evidence on willingness and acceptance in Munich, Germany[J]. Smart and Sustainable Built Environment, 2019, 9(1): 38-53.

[10] DOU X C, JIAN M Y, GUO C, et al. Estimation of the aggregation degree of public transport use among elderly people based on urban built environment[J]. Journal of Transport Geography, 2023, 112: 103707.

[11] CHENG G, GUO L S. Bus transfer network construction and accessibility analysis based on GIS[J]. Journal of Jiangsu University (Natural Science Edition), 2024, 45(2): 191-197. (in Chinese)

[12] CONG L, ZHANG Y. Forecasting method of air conditioning load based on multi-objective regression[J]. Journal of Jiangsu University (Natural Science Edition), 2024, 45(4): 470-475. (in Chinese)

[13] PROKHORENKOVA L, GUSEV G, VOROBEV A, et al. CatBoost: Unbiased boosting with categorical features[C/OL]// Advances in Neural Information Processing Systems 30. Long Beach, CA, USA, 2017. https://proceedings.neurips.cc/paper/2018/hash/14491b756b3a51daac41c24863285549-Abstract.html.

[14] WANG J X, WIENS J, LUNDBERG S. Shapley flow: A graph-based approach to interpreting model predictions[C]// Proceedings of the 24th International Conference on Artificial Intelligence and Statistics. Vancouver, Canada, 2021: 721-729.

[15] KIM J, SCHMÖCKER J D, NAKAMURA T, et al. Integrated impacts of public transport travel and travel satisfaction on quality of life of older people[J]. Transportation Research Part A: Policy and Practice, 2020, 138: 15-27.

[16] CHENG L, WANG J E, PAEZ A. Mobility of older adults and the living environment: Introduction[J]. Journal of Transport Geography, 2023, 106: 103525.

[17] BARRETT A E, GUMBER C. Feeling older and driving less: The effect of age identity on older adults’ transition from driving[J]. Innovation in Aging, 2019, 3(1): igz004.

[18] BABULAL G M, VIVODA J, HARMON A, et al. Older adults’ expectations about mortality, driving life and years left without driving[J]. Journal of Gerontological Social Work, 2019, 62(8): 912-929.

[19] GOEL R, OYEBODE O, FOLEY L, et al. Gender differences in active travel in major cities across the world[J]. Transportation, 2023, 50(2): 733-749.

[20] KAMPHUIS C B, VAN LENTHE F J, GISKES K, et al. Socioeconomic differences in lack of recreational walking among older adults: The role of neighbourhood and individual factors[J]. The International Journal of Behavioral Nutrition and Physical Activity, 2009, 6: 1.

[21] SIREN A, HAUSTEIN S. Cohort analysis of older adults’ travel patterns in Denmark[R]. Kgs. Lyngby, Denmark: Department of Transport, 2012.

[22] DESCHAINTRES E, MORENCY C, TRÉPANIER M. Cross-analysis of the variability of travel behaviors using one-day trip diaries and longitudinal data[J]. Transportation Research Part A: Policy and Practice, 2022, 163: 228-246.

[23] NEWBOLD K B, SCOTT D M, SPINNEY J E L, et al. Travel behavior within Canada’s older population: A cohort analysis[J]. Journal of Transport Geography, 2005, 13(4): 340-351.

Funding

National Natural Science Foundation of China(52272367)

Natural Science Foundation of Jiangsu Province(BK20231324)