Objective  Explore the influencing factors of depression in elderly people with activities of daily living (ADL) disorders, and construct a depression risk prediction model for elderly people with ADL disorders in China based on machine learning (ML) algorithms.

Methods  Based on the fifth round of data from the China Health and Retirement Longitudinal Study (CHARLS) project, the Boruta algorithm and Lasso regression algorithm were used to screen depression risk factors in elderly people with ADL disorders. The 9 ML methods of random forest, light gradient boosting machine, extreme gradient boosting, Logistic regression, K-nearest neighbor, support vector machine, artificial neural network, decision tree, and Elastic Net regression algorithm were used to construct a depression risk prediction model, and SHAP algorithm was used to explain the final model.

Results  A total of 3,167 elderly individuals with ADL disorders were included, with a depression detection rate of 60.69%. The random forest model has the best predictive performance, with AUCs of 0.804 [95%CI (0.788, 0.820)] and 0.779 [95%CI (0.752, 0.806)] on the training and testing sets, respectively. The SHAP algorithm results showed that the impact of life satisfaction, pain and discomfort, self-rated health status, satisfaction with child relationships, gender, whether any falls have occurred since 2018, the number of outpatient visits to medical institutions in a month, age, education level, and whether the internet has been used in the past month on the depression risk prediction model for elderly people with ADL disorders decreased in order. The calibration curve indicates that the predicted performance of the model is basically consistent with the actual results, and the decision curve shows that the model has good clinical applicability.

Conclusion  Early age, female, low educational level, declining self-evaluation of health status, low life satisfaction, low child relationship satisfaction, increased number of outpatient clinics in medical institutions, falls, physical pain, and inability to use the internet significantly increased the risk of depression among the elderly with ADL disorders. Among the depression risk prediction models constructed based on ML algorithm, the random forest model achieved the optimal prediction performance.

1.齐土格, 王志会, 王丽敏, 等. 中国城乡老年人群两年内日常生活活动能力受损发生情况及影响因素[J]. 中华流行病学杂志, 2019, 40(3): 272-276. [Qi SG, Wang ZH, Wang LM, et al. Incidence of activities of daily living disability and related factors in community-dwelling older adults in China[J]. Chinese Journal of Epidemiology, 2019, 40(3): 272-276.]

2.Liu H, Ma Y, Lin L, et al. Association between activities of daily living and depressive symptoms among older adults in China: Evidence from the CHARLS[J]. Front Public Health, 2023, 11: 1249208.

3.Xie T, Liu D, Guo J, et al. The longitudinal effect of sensory loss on depression among Chinese older adults[J]. J Affect Disord, 2021, 283: 216-222.

4.李艳萍, 王媛, 纪之琳, 等. 中国≥45岁中老年人多重慢性病模式与日常和工具性日常生活活动能力残疾的关联性 [J]. 中华疾病控制杂志, 2024, 28(1): 26-31. [Li YP, Wang  Y, Ji ZL, et al. The association between multiple chronic disease patterns and disability in daily and instrumental activities of daily living among middle-aged and elderly people aged 45 and above in China[J]. Chinese Journal of Disease Control and Prevention, 2024, 28(1): 26-31.]

5.周恒益, 李静, 戴丹华, 等. 社区老年人日常生活活动能力与心理健康的关系及睡眠质量的中介作用[J]. 复旦学报(医学版), 2024, 51(2): 143-150. [Zhou HY, Li J, Dai DH, et al. The relationship between daily living activity ability and mental health of elderly people in the community, and the mediating role of sleep quality[J]. Journal of Fudan University (Medical Edition), 2024, 51(2): 143-150.]

6.Lestari SK, Ng N, Kowal P, et al. Diversity in the factors associated with ADL-related disability among older people in six middle-income countries: a cross-country comparison[J]. Int J Environ Res Public Health, 2019, 16(8): 1341.

7.He M, Ma J, Ren Z, et al. Association between activities of daily living disability and depression symptoms of middle-aged and older Chinese adults and their spouses: a community based study[J]. J Affect Disord, 2019, 242: 135-142.

8.刘叶, 高广峰, 周亦凡, 等. 老年人群中视听障碍对主观幸福感的影响: 抑郁倾向的中介作用[J]. 复旦学报(医学版), 2024, 51(4): 558-565. [Liu Y, Gao GF, Zhou YF, et al. The impact of visual and auditory impairments on subjective well-being in the elderly population: the mediating role of depressive tendencies[J]. Journal of Fudan University (Medical Edition), 2024, 51(4): 558-565.]

9.Li H, Wang A, Gao Q, et al. Prevalence of somatic-mental multimorbidity and its prospective association with disability among older adults in China[J]. Aging (Albany NY), 2020, 12(8): 7218-7231.

10.Carmona-Torres JM, Rodríguez-Borrego MA, Laredo-Aguilera JA, et al. Disability for basic and instrumental activities of daily living in older individuals[J]. PLoS One, 2019, 14(7): e0220157.

11.Wang S, Yu M, Huang W, et al. Longitudinal association between ADL disability and depression in middle-aged and elderly: national cohort study[J]. J Nutr Health Aging, 2025, 29(2): 100450.

12.李巧凤, 晏毅龙, 何悦菡, 等. 中国不同抑郁程度中老年人群慢性病共病患病情况网络分析[J]. 中国公共卫生, 2024, 40(8): 948-953. [Li QF, Yan YL, He YH, et al. Network analysis of chronic comorbidities among middle-aged and elderly people with different degrees of depression in China[J]. Chinese Public Health, 2024, 40(8): 948-953.]

13.崔宇琛, 张晗, 胡志强, 等. 基于机器学习的青年人群颞下颌关节紊乱病风险预测模型的构建[J]. 口腔医学研究, 2024, 40(10): 867-872. [Cui YC, Zhang H, Hu ZQ, et al. Construction of a machine learning based model for predicting the risk of temporomandibular joint disorders in young people[J]. Oral Medicine Research, 2024, 40(10): 867-872.]

14.陈贺, 王黎君, 郎英旭, 等. 1990—2021年中国及分省儿童和青少年慢性病疾病负担分析[J]. 中国慢性病预防与控制, 2024, 32(12): 884-892. [Chen H, Wang LJ, Lang YX, et al. Analysis of chronic disease burden in children and adolescents in China and provinces from 1990 to 2021[J]. Chinese Journal of Chronic Disease Prevention and Control, 2024, 32(12): 884-892.]

15.李敏超, 宋丽君, 陆国飞, 等. 我国≥60岁老年人抑郁流行现状及影响因素分析[J]. 华南预防医学, 2024, 50(12): 1130-1135. [Li MC, Song LJ, Lu GF, et al. Analysis of the current situation and influencing factors of depression among elderly people aged 60 and above in China[J]. South China Preventive Medicine, 2024, 50(12): 1130-1135.]

16.王越, 陈晴, 刘鲁蓉. 中国老年人抑郁检出率及影响因素的Meta分析[J]. 中国全科医学, 2023, 26(34): 4329-4335. [Wang  Y, Chen Q, Liu LR. Meta analysis of depression detection rate and influencing factors among elderly people in China[J]. Chinese Journal of General Practice, 2023, 26(34): 4329-4335.]

17.刘艳, 宋新明. 残疾状况对我国老年人抑郁症状的影响[J]. 医学与社会, 2023, 36(9): 68-73. [Liu Y, Song XM. The impact of disability status on depression symptoms in elderly people in China[J]. Journal of Medicine and Society, 2023, 36(9): 68-73.]

18.崔珑严, 丁玎, 王明慧, 等. 不同类型日常生活活动能力与老年人抑郁的关联[J]. 中华疾病控制杂志, 2023, 27(6): 717-721. [Cui  LY, Ding D, Wang MH, et al. The association between different types of activities of daily living and depression in the elderly[J]. Chinese Journal of Disease Control and Prevention, 2023, 27(6): 717-721.]

19.Cornwell EY, Waite LJ. Social disconnectedness, perceived isolation, and health among older adults[J]. J Health Soc Behav, 2009, 50(1): 31-48.

20.Gutierrez S, Milani SA, Wong R. Is "busy" always better? Time-use activities and depressive symptoms among older Mexican adults[J]. Innov Aging, 2020, 4(5): igaa030.

21.Raymond É. The challenge of inclusion for older people with impairments: insights from a stigma-based analysis[J]. J Aging Stud, 2019, 49: 9-15.

22.Cavusoglu C, Ileri I, Tuna Dogrul R, et al. Relationship between psychological pain and death anxiety with comprehensive geriatric assessment in older adults[J]. Geriatr Gerontol Int, 2020, 20(11): 1056-1060.

23.Ahmad NA, Abd Razak MA, Kassim MS, et al. Association between functional limitations and depression among community-dwelling older adults in Malaysia[J]. Geriatr Gerontol Int, 2020, 20Suppl 2: 21-25.

24.王丹, 齐士格, 王宝华, 等. 中国3省60岁及以上老年人抑郁情况及其影响因素研究[J]. 中华流行病学杂志, 2022, 43(12): 1925-1931. [Wang D, Qi SG, Wang BH, et al. Depression status and its influencing factors among the elderly aged 60 years and above in three provinces of China[J]. Chinese Journal of Epidemiology, 2022, 43(12): 1925-1931.]

25.Makovski TT, Le Coroller G, Putrik P, et al. Role of clinical, functional and social factors in the association between multimorbidity and quality of life: findings from the survey of health, ageing and retirement in Europe (share)[J]. PLoS One, 2020, 15(10): e0240024.

26.Xu H, Qin L, Wang J, et al. A cross-sectional study on risk factors and their interactions with suicidal ideation among the elderly in rural communities of Hunan, China[J]. BMJ Open, 2016, 6(4): e010914.

27.张敏, 顾婷婷, 关蔚, 等. 基于机器学习算法构建中重度围绝经期综合征预测模型[J]. 医学新知, 2024, 34(8): 871-879. [Zhang M, Gu TT, Guan W, et al. Constructing a prediction model for moderate to severe perimenopausal syndrome based on machine learning algorithms[J]. Yixue Xinzhi Zazhi, 2024, 34(8): 871-879.]

28.Dimitriadis SI, Liparas D. How random is the random forest? Random forest algorithm on the service of structural imaging biomarkers for Alzheimer's disease: from Alzheimer's disease neuroimaging initiative (ADNI) database[J]. Neural Regen Res, 2018, 13(6): 962-970.

29.王怀昭, 乔婷婷, 范艳存. 老年人日常生活活动能力、自评健康状况在慢性病影响抑郁症状中的效应研究[J]. 预防医学, 2023, 35(7): 574-577. [Wang HZ, Qiao TT, Fan YC. A study on the effect of activities of daily living and self assessed health status of elderly people on depression symptoms affected by chronic diseases[J]. Preventive Medicine, 2023, 35(7): 574-577.]

30.邢贤晋, 王健, 高天, 等. 我国老年人日常生活活动能力与慢性病共病和抑郁症状的关系分析[J]. 医学与社会, 2023, 36(8): 123-128. [Xing XJ, Wang J, Gao T, et al. Analysis of the relationship between daily living activities and chronic disease comorbidity and depression symptoms in elderly people in China[J]. Journal of Medicine and Society, 2023, 36(8): 123-128.]

31.Qian J, Li N, Ren X. Obesity and depressive symptoms among Chinese people aged 45 and over[J]. Sci Rep, 2017, 7: 45637.

32.安慧妍, 瓮长水, 蒋天裕, 等. 老年男性人群跌倒发生率及相关危险因素的现况调查[J]. 武警医学, 2024, 35(5): 410-416. [An HY, Weng CS, Jiang TY, et al. A current survey on the incidence of falls and related risk factors in elderly male population[J]. Armed Police Medicine, 2024, 35(5): 410-416.]

33.Hyejin L, Bumjo O, Sunyoung K, et al. ADL/IADL dependencies and unmet healthcare needs in older persons: a nationwide survey[J]. Arch Gerontol Geriatr, 2021, 96: 104458.