以质量求发展，以服务铸品牌

护理学报 ›› 2023, Vol. 30 ›› Issue (23): 57-61.doi: 10.16460/j.issn1008-9969.2023.23.057

• 调查研究 • 上一篇    下一篇

基于机器学习的主观认知下降老年人认知功能状况的影响因素分析

刘海虹1,2,3, 张小雷4,5, 薛茹6, 陶佳雨1, 李晓敏1, 李峰7, 刘海宁1,2   

  1. 1.承德医学院 心理学系,河北 承德 067000;
    2.河北省神经损伤与修复重点实验室,河北 承德 067000;
    3.马来西亚国民大学 社会科学与人文学院心理学与人类福祉研究中心,马来西亚 班吉 43600;
    4.承德医学院 生物医学工程系,河北 承德 067000;
    5.博特拉大学 工程学院,马来西亚 沙登 43400;
    6.承德医学院 护理系,河北 承德 067000;
    7.北京师范大学 中国基础教育质量监测协同创新中心,广东 珠海 519087
  • 收稿日期:2023-04-21 出版日期:2023-12-10 发布日期:2024-01-09
  • 通讯作者: 刘海宁（1985-）,女,河北承德人,博士,副教授。E-mail: liuhn0401@sina.com
  • 作者简介:刘海虹（1992-）,女,河北张家口人,硕士,博士研究生在读,讲师。
  • 基金资助:
    河北省神经损伤与修复重点实验室开放课题（NJKF202302）; 河北省高等学校人文社会科学研究项目（SQ2023137）; 河北省自然科学基金（C2022406010）; 国家自然科学基金（32300931）; 教育部人文社科基金青年项目（23YJCZH130）

Influencing factors of cognitive function of older adults with subjective cognitive decline based on machine learning

LIU Hai-hong1,2,3, ZHANG Xiao-lei4,5, XUE Ru6, TAO Jia-yu1, LI Xiao-min1, LI Feng7, LIU Hai-ning1,2   

  1. 1. Department of Psychology, Chengde Medical University, Chengde 067000, China;
    2. Hebei Key Laboratory of Nerve Injury and Repair, Chengde 067000, China;
    3. Centre for Research on Psychology and Human Well-Being, Faculty of Social Sciences and Humanities, Universiti Kebangsaan Malaysia, Bangi 43600, Malaysia;
    4. Department of Biomedical Engineering, Chengde Medical University, Chengde 067000, China;
    5. Faculty of Engineering, Universiti Putra Malaysia, Serdang 43400, Malaysia;
    6. Department of Nursing, Chengde Medical University, Chengde 067000, China;
    7. China Basic Education Quality Monitoring Collaborative Innovation Center,Beijing Normal University, Zhuhai 519087,China
  • Received:2023-04-21 Online:2023-12-10 Published:2024-01-09

PDF (PC)

517

赞

摘要： 目的 通过比较主观认知下降老年人认知功能的3种机器学习预测模型,探索其影响因素,为其预防和干预提供依据。方法 利用2018年中国健康与养老追踪调查数据库相关条目,筛选出2 969名主观认知下降老年人,运用Lasso回归、支持向量回归、随机森林回归3种机器学习方法构建认知功能预测模型,并依据最优预测模型提取影响因素。结果 随机森林预测模型的准确度最高（R2=0.864,MAE=1.988,MSE=5.879）,主观认知下降老年人认知功能的影响因素按重要性排序依次为：身体功能障碍、年龄、抑郁总分、自评健康、教育程度、娱乐总分、整洁度、午睡时间、IADL总分、是否有宽带。结论 随机森林构建的主观认知下降老年人认知功能预测模型,预测效能优于Lasso回归和支持向量回归构建的预测模型。临床结合老年人具体情况及危险因素,从学习、娱乐、日常活动、午睡时间和网络使用等影响因素制定个性化和多维度的干预方案,预防主观认知下降老年人的认知功能下降。

关键词: 主观认知下降, 老年人, 机器学习, 认知功能

Abstract: Objective To explore the influencing factors and provide reference for the prevention and intervention of cognitive decline in elderly people with subjective cognitive decline (SCD) by comparing cognitive function predictive models based on machine learning. Methods With the data of China Health and Retirement Longitudinal Study (CHARLS) in 2018, 2,969 elderly people with SCD were screened out. The least absolute shrinkage and selection operator (LASSO) regression, support vector regression (SRV), and random forest (RF) regression were used to construct predictive models for cognitive function of the elderly with SCD. The influencing factors of cognitive function were extracted based on the optimal predictive model. Results Among the three models, the one constructed by RF regression demonstrated the highest accuracy in predicting cognitive function in older adults experiencing SCD (R2=0.864, MAE=1.988, MSE=5.879). The factors affecting the cognitive function of the elderly with SCD can be ranked in order of importance as follows: physical dysfunction, age, the total score of depression, self-assessment of health, education background, the total score of entertainment, cleanliness, nap time, total score of IADL, with broadband or not. Conclusion Cognitive function predictive model constructed using RF regression demonstrates superior performance compared to models constructed using LASSO regression and SVR. By integrating the specific circumstances and risk factors of older adults, clinical professionals can develop personalized and multidimensional intervention plans that address factors such as learning, leisure activities, daily routines, nap time, and internet usage, so as to prevent cognitive function decline in older adults experiencing SCD.

Key words: subjective cognitive decline, older adult, machine learning, cognitive function

中图分类号: 

  • R473.2
[1] Jessen F, Amariglio RE, Van Boxtel M, et al.A conceptual framework for research on subjective cognitive decline in preclinical Alzheimer's disease[J].Alzheimers Dement,2014,10(6):844-852. DOI:10.1016/j.jalz.2014.01.001.
[2] Jessen F, Wiese B, Bachmann C, et al.Prediction of dementia by subjective memory impairment: effects of severity and temporal association with cognitive impairment[J]. Arch Gen Psychiatry, 2010,67(4):414-422. DOI:10.1001/archgenpsychiatry.2010.30.
[3] 周滢,甘珊,李峥.社区老年人主观认知下降现状及影响因素分析[J]. 解放军护理杂志, 2021,38(4):21-24. DOI:10.3969/j.issn.1008-9993.2021.04.006.
[4] Trivedi UB, Bhatt M, Srivastava P.Prevent overfitting problem in machine learning: a case focus on linear regression and logistics regression[M]. Switzerland: Springer International Publishing. 2021:345-349. DOI:10.1007/978-3-030-66218-9_40.
[5] 李超,求文星.基于机器学习的因果推断方法研究进展[J]. 统计与决策,2021,37(11):10-15. DOI:10.13546/j.cnki.tjyjc.2021.11.002.
[6] Gillain S, Boutaayamou M, Schwartz C, et al.Using supervised learning machine algorithm to identify future fallers based on gait patterns: a two-year longitudinal study[J]. Exp Gerontol,2019, 27:110730. DOI:10.1016/j.exger.2019.110730.
[7] 北京大学健康老龄与发展研究中心.北京大学开放研究数据平台[EB/OL]. (2021-06-01)[2023-04-05]. https://charls.charlsdata.com/pages/data/111/zh-cn.html.
[8] Xu W, Bai A, Liang Y, et al.Association between depression and motoric cognitive risk syndrome among community-dwelling older adults in china: a 4-year prospective cohort study[J]. Eur J Neurol, 2022,29(5):1377-1384. DOI:10.1111/ene.15262.
[9] Folstein M, Folstein S, Mchugh P.Mini-mental state a practical method for grading the cognitive state of patients for the clinician[J]. J Psychiatr Res, 1975, 12(3):189-198. DOI: 10.1016/0022-3956(75)90026-6.
[10] 李格,沈渔邨,陈昌惠,等.老年痴呆简易测试方法研究——MMSE在城市老年居民中的测试[J].中国心理卫生杂志,1988,2(1):13-19.
[11] 魏霞霞,郝志梅,陈玲,等.简版CSI-D与MMSE在我国中老年人痴呆筛查中的应用效果比较研究[J].中国全科医学, 2022,25(31):3866-3871.DOI:10.3969/j.issn.2097-1826.2022.08.017.
[12] Aschwanden D, Aichele S, Ghisletta P, et al.Predicting cognitive impairment and dementia: a machine learning approach[J]. J Alzheimers Dis, 2020, 75(3):717-728. DOI: 10.3233/JAD-190967.
[13] Troyer AK.Activities of daily living (adl)[M]. New York: Springer New York. 2011:28-30.DOI:10.1007/978-0-387-79948-3_1077.
[14] 黄庆波,王晓华,陈功.10项流调中心抑郁自评量表在中国中老人群中的信效度[J]. 中国健康心理学杂志,2015, 23(7):1036-1041. DOI:10.13342/j.cnki.cjhp.2015.07.023.
[15] Williams MW, Li CY, Hay CC.Validation of the 10-item center for epidemiologic studies depression scale post stroke[J]. J Stroke Cerebrovasc Dis, 2020, 29(12):105334. DOI:10.1016/j.jstr okecerebrovasdis.2020.105334.
[16] Chicco D, Warrens M J, Jurman G.The coefficient of determination r-squared is more informative than smape, MAE, mape, MSE and RMSE in regression analysis evaluation[J]. PeerJ Comput Sci,2021,7:e623. DOI:10.7717/peerj-cs.623.
[17] Doganer A, Yaman S, Eser N, et al.Different machine learning methods based prediction of mild cognitive impairment[J]. Annals of Medical Research, 2020, 27(3):833-939. DOI:10.5455/annals medres.2019.10.683.
[18] Maroco J, Silva D, Rodrigues A, et al.Data mining methods in the prediction of dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forests[J]. BMC Res Notes, 2011, 4(1):299.DOI:10.1186/1756-0500-4-299.
[19] 吕欢欢, 张玉召.基于机器学习的地铁列车牵引能耗预测研究[J]. 铁道科学与工程学报,2019, 16(7):1835-1844. DOI:10.19713/j.cnki.43-1423/u.2019.07.030.
[20] 朱明月,丁晓彤,史纪元,等.自我感知老化对老年人认知功能影响的系统评价[J]. 护理学报, 2023,30(8):52-57. DOI:10.16460/j.issn1008-9969.2023.08.052.
[21] Park S, Choi B, Choi C, et al.Relationship between education, leisure activities, and cognitive functions in older adults[J]. Aging Ment Health, 2019, 23(12):1651-1660. DOI:10.1080/13607863. 2018.1512083.
[22] Wang K, Maglalang DD, Woo B, et al.Perceived discrimination and cognitive function among older puerto ricans in boston: the mediating role of depression[J]. Int J Geriatr Psychiatry, 2022, 37(5):1-10. DOI:10.1002/gps.5717.
[23] Mcdermott LM, Ebmeier KP.A Meta-analysis of depression severity and cognitive function[J]. J Affect Disord, 2009, 119(1):1-8. DOI:10.1016/j.jad.2009.04.022.
[24] Lee J, Sung J, Choi M.The factors associated with subjective cognitive decline and cognitive function among older adults[J]. J Adv Nurs, 2020, 76(2):555-565. DOI:10.1111/jan.14261.
[25] 孟凯涛,张建国,刘崇,等.不同严重程度阿尔茨海默病患者血清mir-128,mir-223表达水平变化与炎症反应及认知功能的相关性分析[J].卒中与神经疾病, 2021,28(6):667-671. DOI:10.3969/j.issn.1007-0478.2021.06.012.
[26] Dodge HH, Kadowaki T, Hayakawa T, et al.Cognitive impairment as a strong predictor of incident disability in specific ADL-IADL tasks among community-dwelling elders: the Azuchi study[J]. The Gerontologist, 2005, 45(2):222-230. DOI:10.1093/geront/45.2.222.
[27] 蔡菡,沈棫华,李伟,等.午睡对阿尔茨海默病认知功能的作用及其相关机制[J].中华行为医学与脑科学杂志, 2020,29(5):471-474. DOI:10.3760/cma.j.cn371468-20190927-00675.
[28] 吉慧聪,姚淑娟,李倩阳,等.居家老年人认知功能及其影响因素[J].中国老年学杂志, 2018, 38(4):974-976. DOI:10.3969/j.issn.1005-9202.2018.04.084.
[29] Berner J, Comijs H, Elmstahl S, et al.Maintaining cognitive function with internet use: a two-country, six-year longitudinal study[J]. Int Psychogeriatr, 2019, 31(7):929-936. DOI:10.1017/s 1041610219000668.
[30] Ihle A, Gouveia éR, Gouveia BR, et al.The relation of education, occupation, and cognitive activity to cognitive status in old age: the role of physical frailty[J]. Int Psychogeriatr,2017,29(9):1469-1474.DOI:10.1017/S1041610217000795.
[1] 焦雪萍, 王志稳, 韩舒羽. ICU老年患者躁动行为的干预研究进展[J]. 护理学报, 2025, 32(3): 38-42.
[2] 陈玉英, 王海彦, 陈思颖, 杨雪娟. 老年人自立支援照护模式的照护技巧及启示[J]. 护理学报, 2025, 32(2): 31-36.
[3] 谭丘羽, 邓一芯, 冀婉倩, 王冬华. 农村老年人自我刻板化与主观记忆抱怨在自我感知老化与痴呆恐惧间的链式中介效应[J]. 护理学报, 2025, 32(1): 56-61.
[4] 丁心舒, 孙乐菲, 高伟, 鲁琦, 闫畅, 刘德山. 矛盾年龄歧视量表在社区老年人中的信效度检验[J]. 护理学报, 2024, 31(7): 12-16.
[5] 王薇, 周演铃, 薛文萍, 张淋淋, 林书球. 老年髋部骨折患者衰弱评估工具的范围综述[J]. 护理学报, 2024, 31(4): 42-47.
[6] 邓岚心, 张宇, 李敏锐, 高钰琳. 养老机构老年人认知功能与身体衰弱变化的交叉滞后分析[J]. 护理学报, 2024, 31(23): 8-12.
[7] 李明哲, 田一川, 王成龙, 王晶晶. 社会网络在智能手机使用与老年人孤独感的因果中介作用[J]. 护理学报, 2024, 31(20): 45-49.
[8] 王之仪, 颜立春, 胡雅静, 易小聪, 谭素文, 张银华. 养老机构老年人身体约束护理方案的构建与检验[J]. 护理学报, 2024, 31(20): 55-59.
[9] 郝杨, 秦艳梅, 毛美琦, 赵雅宁, 刘瑶, 韩影. 基于贝叶斯网络模型的社区老年人认知衰弱的影响因素分析[J]. 护理学报, 2024, 31(19): 12-18.
[10] 杨侠, 于卫华, 张雨溪, 邓曼, 任影, 张利, 张海燕. 377例社区老年多重慢病患者心理困扰现状及影响因素分析[J]. 护理学报, 2024, 31(18): 50-55.
[11] 康俊贤, 崔玉, 张小丽, 邢凤梅, 汪凤兰. 共病老年人及其配偶内在力量、赋权水平与生存质量的关系研究[J]. 护理学报, 2024, 31(17): 8-12.
[12] 施杨, 顾志娥, 朱彤, 喻静, 王林. 社会网络和自我忽视在老年缺血性脑卒中患者衰弱与认知功能间的链式中介效应[J]. 护理学报, 2024, 31(17): 40-45.
[13] 吴双赢, 谢子恒, 庄严. 2 888名老年人抑郁症状发展轨迹及影响因素研究[J]. 护理学报, 2024, 31(14): 6-12.
[14] . 老年人社会参与能力的潜在剖面分析及其对衰弱的影响[J]. 护理学报, 2024, 31(12): 1-6.
[15] . 老年人咀嚼功能临床研究现状[J]. 护理学报, 2024, 31(12): 21-25.
Viewed
Full text


Abstract

Cited
  Shared   
No Suggested Reading articles found!