Objective  Based on the China Health and Retirement Longitudinal Study (CHARLS) database, this study aimed to conduct an in-depth analysis of the factors affecting cognitive function of middle-aged and elderly people, so as to provide a reference for preventing cognitive function damage.

Methods  A total of 9,431 middle-aged and elderly people aged 45 and above were selected as the research subjects. Cognitive function was comprehensively assessed using the telephone interview for cognitive status, drawing task, and word recall. The influencing factors of cognitive function were screened by Lasso-Logistic regression model, and the influencing factors were sorted by random forest model. Receiver operating characteristic (ROC) curves were plotted, and the predictive performance of the models was evaluated using the area under the curve (AUC), sensitivity, and specificity.

Results  The mean comprehensive cognitive score of the middle-aged and elderly people, with 4,816 people (51.07%) scoring below the median. Las-so-Logistic analysis showed that gender, age, residential area, baseline cognitive test score in 2011, self-assessment of health, night sleep time, social activities, exercise habits, pension insurance and education level were the main influencing factors of cognitive function in middle-aged and elderly people (P < 0.05). The random forest model ranked the importance of these factors in descending order as follows: education level, baseline cognitive test score in 2011, residential area, age, gender, self-assessment of health, social activities, exercise habits, pension insurance and night sleep time. The AUC values for the Logistic regression model and the random forest model were both 0.82.

Conclusions  Logistic regression model and random forest model both have high predictive value for middle-aged and elderly people's cognitive function, which could a provide powerful tool and method for early identification of the risk of cognitive function decline in clinical practice and timely formulation of effective intervention measures to prevent or delay the occurrence of cognitive function impairment.

1.刘凌晨, 程宏宇, 彭希哲. 中国老年人社会参与模式对认知衰退的影响[J]. 中国人口科学, 2022, (04): 103-114. [[Liu LC, Cheng HY, Peng XZ. The influence of social participation patterns on cognitive decline in older adults in China[J]. Chinese Journal of Population Science, 2022, (4): 103-114, 128.https://d.wanfangdata.com.cn/periodical/ChdQZXJpb2RpY2FsQ0hJU29scjlRdWljaxIPemdya2t4MjAyMjA0MDA5GghieDE5cDcyaQ%3D%3D

2.黄晓彤, 王琼, 刘晨, 等. 童年社会经济地位对中老年认知功能影响的中介效应路径分析[J]. 中国全科医学, 2024, 27(3): 322-327, 334. [Huang XT, Wang Q, Liu C, et al. A path analysis of the effect of childhood socioeconomic status on cognitive function in middle-aged and older adults [J]. Chinese General Practice, 2024, 27(3): 322-327, 334.] DOI: 10.12114/j.issn.1007-9572.2023.0359.

3.班春霞, 石文磊, 高红艳, 等. 社区老年人认知功能障碍现状及影响因素调查[J]. 国际精神病学杂志, 2025, 52(3): 852-856. [Ban CX, Shi WL, Gao HY, et al. Investigation on the status quo and related influencing factors of cognitive dysfunction in elderly people in community[J]. Journal of International Psychiatry, 2025, 52(3): 852-856.] DOI: 10.13479/j.cnki.jip.2025.03.051.

4.高娇娇, 王小楠, 吴抗, 等. 上海浦东新区中老年2型糖尿病患者轻度认知功能障碍的现状及其影响因素分析[J]. 公共卫生与预防医学, 2025, 36(3): 32-36. [Gao JJ, Wang XN, Wu K, et al. Current status and influencing factors of mild cognitive impairment in middle-aged and elderly patients with type 2 diabetes in Pudong New Area of Shanghai[J]. Journal of Public Health and Preventive Medicine, 2025, 36(3): 32-36.] DOI: 10. 3969/j. issn.1006-2483.2025.03.007.

5.张沥今, 魏夏琰, 陆嘉琦, 等. Lasso回归: 从解释到预测[J]. 心理科学进展, 2020, 28(10): 1777-1791. [[Zhang LJ, Wei XY, Lu JQ, et al. Lasso regression: from explanation to prediction[J]. Advances in Psychological Science, 2020, 28(10): 1777-1791.https://d.wanfangdata.com.cn/periodical/ChdQZXJpb2RpY2FsQ0hJU29scjlRdWljaxIOeGx4ZHQyMDIwMTAwMTUaCDRhbXJiaDg4.

6.宋雅云. 中老年人认知功能与握力的相关性研究——基于CHARLS数据[J]. 中华养生保健, 2022, 40 (19): 1-5. [Song YY. Association between cognitive functions and grip strength among the older adults: based on CHARLS data[J]. ZHONGHUA YANGSHENG BAOJIAN, 2022, 40(19): 1-5. https://d.wanfangdata.com.cn/periodical/QKBJBD20222022100100007910

7.Hua J, Dong J, Chen GC, et al. Trends in cognitive function before and after stroke in China[J]. BMC Med, 2023, 21(1): 204. DOI: 10.1186/s12916-023-02908-5.

8.盛丹, 高宁, 唐绍琰, 等. 基于LASSO-logistic回归模型的糖尿病周围神经病变预测模型[J]. 中国慢性病预防与控制, 2024, 32(10): 733-740. [Sheng D, Gao N, Tang SY, et al. Prediction model of diabetic peripheral neuropathy based on LASSO-logistic regression model[J]. Chinese Journal of Prevention and Control of Chronic Diseases, 2024, 32(10): 733-740.] DOI: 10.16386/j.cjpccd.issn.1004-6194.2024.10.003.

9.王洪川, 陈怡莹, 王聪. 人口老龄化背景下体育消费的健康效应——基于全国消费大数据的实证证据[J]. 上海体育大学学报, 2024, 48(3): 75-84. [Wang HC, Chen YY, Wang C. Health effect of sports consumption in aging society: empirical evidence from nationwide consumption big data[J]. Journal of Shanghai University of Sport, 2024, 48(3): 75-84.] DOI: 10.16099/j.sus.2023.04.04.0002.

10.冯薇. 老年人认知功能障碍与阿尔茨海默病的研究进展[J]. 公共卫生与预防医学, 2024, 35(6):123-126. [Feng W. Research progress of elderly cognitive impairment and Alzheimer's disease[J]. Journal of Public Health and Preventive Medicine, 2024, 35(6): 123-126.] DOI: 10.3969/j.issn.1006-2483.2024.06.028.

11.Xiong J, Kang SS, Wang Z, et al. FSH blockade improves cognition in mice with Alzheimer′s disease[J]. Nature, 2022, 603(7901): 470-476. DOI: 10.1038/s41586-022-04463-0.

12.景璟, 王丹阳. 社区老年人群轻度认知障碍发生情况及其相关危险因素调查分析[J]. 安徽医药, 2023, 27(3): 542-545. [Jing J, Wang DY. Investigation and analysis of the occurrence of mild cognitive impairment and related risk factors in the elderly in the community[J]. Anhui Medical and Pharmaceutical Journal, 2023, 27(3): 542-545.] DOI: 10.3969/j.issn.1009-6469.2023.03.026..

13.Wang Y, Jiang Y, Wu W, et al. Education, neighborhood environment, and cognitive decline: findings from two prospective cohort studies of older adults in China[J]. Alzheimer's Dement. 2023, 19(2): 560–568. DOI: 10.1002/alz.12679.

14.余成, 孙景贤. 农村地区轻度认知障碍老年人睡眠时长与睡眠效率对认知功能的影响[J]. 实用老年医学, 2022, 36(3): 295-298. [Yu C, Sun JX. Effects of sleep duration and sleep efficiency on cognitive function of the elderly with mild cognitive impairment in rural areas[J]. Practical Geriatrics, 2022, 36(3): 295-298.] DOI: 10.3969/j.issn1003-9198.2022.03.021.

15.曹璐, 王迎斌, 张伟, 等. 睡眠障碍对老年认知功能的影响机制及防治研究进展[J]. 世界睡眠医学杂志, 2024, 11(4): 778-783. [Cao L, Wang YB, Zhang W, et al. Research progress on the mechanism of sleep disorders affecting cognitive function in elderly patients and its prevention and treatment strategies [J]. World Journal of Sleep Medicine, 2024, 11(4): 778-783.] DOI: 10.3969/j.issn.2095-7130.2024.04.019.

16.朱正杰, 施正丽, 张浩, 等. 我国老年人社会参与情况及其与认知障碍的关系[J]. 医学与社会, 2023, 36(12): 53-58. [Zhu ZJ, Shi ZL, Zhang H, et al. Status of social participation and its relationship with cognitive impairment among the elderly in China [J]. Medicine and society, 2023, 36(12): 53-58.] DOI: 10.13723/j.yxysh.2023.12.009.

17.刘东祺, 李荣梅, 张美琪, 等. 有氧运动干预老年轻度认知功能障碍的Meta分析[J]. 中国组织工程研究, 2019, 23(35): 5727-5731. [Liu DQ, Li RM, Zhang MQ, et al. Meta-analysis of the effect of aerobic exercise on mild cognitive impairment in the elderly[J]. Chinese Journal of Tissue Engineering Research, 2019, 23(35): 5727-5731.] DOI: 10.3969/j.issn.2095-4344.1943.

18.朱雅丽, 李慧, 赵豪. 养老保险提高了老年人的健康水平吗?——基于CLHLS数据的实证分析[J]. 中国经贸导刊, 2020, (05): 136-138. [Zhu YL, Li H, Zhao H. Does endowment insurance improve the health status of the elderly?-An empirical analysis based on CLHLS data[J]. China Economic & Trade Herald, 2020, (05): 136-138.] DOI: 10.3969/j.issn.1007-9777.2020.14.041.

19.毛晓雨, 黄雅莲, 蔡清艳, 等. 中国失能老年人认知功能现况及影响因素[J]. 中华老年多器官疾病杂志, 2022, 21(2): 91-94. [Mao XY, Huang YL, Cai QY, et al. Cognitive function and its influencing factors in the disabled elderly in China[J]. Chinese Journal of Multiple Organ Diseases in the Elderly, 2022, 21(2): 91-94.] DOI: 10.11915/j.issn.1671-5403.2022.02.020.

20.袁菲, 刘溯, 梁小妞, 等. 社区老年人群高血压情况与痴呆症发病风险的关联研究[J]. 中国临床神经科学, 2021, 29(5): 519-526. [[Yuan F, Liu S, Liang XN, et al. Relationship between hypertension and incidence risk of dementia in community elderly[J]. Chinese Journal of Clinical Neuroscience, 2021, 29(5): 519-526.https://d.wanfangdata.com.cn/periodical/ChdQZXJpb2RpY2FsQ0hJU29scjlRdWljaxIRemdsY3Nqa3gyMDIxMDUwMDYaCDZjdW90YXBt

21.张华, 高少芳, 赵欣, 等. 基于随机森林、Logistic回归的角膜塑形镜近视控制效果及预测模型构建和评价[J]. 眼科新进展, 2024, 44(8): 637-642. [Zhang H, Gao SF, Zhao X, et al. Myopia control effect of orthokeratology lens and construction and evaluation of prediction model based on random forest and Logistic regression[J]. Recent Advances in Ophthalmology, 2024, 44(8): 637-642.] DOI: 10.13389/j.cnki.rao.2024.0122.

22.胡小琴, 黄原义, 王勤, 等. 基于LASSO-Logistic回归的肺亚实性结节浸润性预测模型的建立与验证[J]. 放射学实践, 2025, 40(11): 1410-1415. [Hu XQ, Huang YY, Wang Q, et al. Establishment and validation of the LASSO-logistic regression-based model for invasiveness prediction in pulmonary subsolid nodules[J]. Radiologic Practice, 2025, 40(11):1410-1415.] DOI: 10.13609/j.cnki.1000-0313.2025.11.011.