老年慢性心力衰竭患者可逆性认知衰弱风险预测模型的比较

摘要/Abstract

摘要： 目的采用3种机器学习算法构建老年慢性心力衰竭（CHF）患者可逆性认知衰弱（RCF）风险预测模型,比较3种机器学习算法的预测性能,为临床医护人员早期识别老年CHF的RCF发生提供筛查工具。方法于2024年6月—10月,便利选取衡阳市某三级甲等医院心内科就诊的300例老年CHF患者为研究对象,通过问卷调查和查阅病历收集资料。采用Logistic回归、CART决策树和随机森林3种机器学习算法构建老年CHF患者RCF风险预测模型,对3种算法的预测性能进行比较。结果老年CHF患者RCF的发生率为28%。年龄、每周体育锻炼频率和双向社会支持是3种机器学习模型共同的预测因子（P<0.05）。对3种机器学习算法的预测性能进行比较,随机森林模型的预测性能最佳,其AUC、准确率、精确率、召回率和F1分别为0.884、0.789、0.963、0.591和0.732。结论年龄、每周体育锻炼频率和双向社会支持是3种机器学习模型共同的预测因子。构建的风险预测模型中随机森林模型预测性能最佳,可用于老年CHF患者RCF的筛查。

关键词: 老年人, CHF, 可逆性认知衰弱, 影响因素, 风险预测模型

中图分类号:

R473

宋珍, 江雪萌, 伍春. 老年慢性心力衰竭患者可逆性认知衰弱风险预测模型的比较[J]. 承德医学院学报, 2026, 43(1): 37-43.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://tougao.cdmc.edu.cn:8088/CN/

http://tougao.cdmc.edu.cn:8088/CN/Y2026/V43/I1/37

参考文献

[1] Mcdonagh TA, Metra M, Adamo M, et al.[2021 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure. Developed by the Task Force for the diagnosis and treatment of acute and chronic heart failure of the European Society of Cardiology (ESC). With the special contribution of the Heart Failure Association (HFA) of the ESC] [J]. G Ital Cardiol (Rome), 2022, 23(4 Suppl 1): e1-e127.
[2] Ruan Q, Yu Z, Chen M, et al.Cognitive frailty, a novel target for the prevention of elderly dependency[J]. Ageing Res Rev, 2015, 20: 1-10.
[3] Solfrizzi V, Scafato E, Seripa D, et al.Reversible Cognitive Frailty, Dementia, and All-Cause Mortality. The Italian Longitudinal Study on Aging[J]. J Am Med Dir Assoc, 2017, 18(1): 81-89.
[4] Xu J, Xiang L, Zhang H, et al.Prevalence and modifiable risk factors of cognitive frailty in patients with chronic heart failure in China: a cross-sectional study[J]. BMC Cardiovasc Disord, 2024, 24(1): 93.
[5] 中华医学会心血管病学分会,中国医师协会心血管内科医师分会,中国医师协会心力衰竭专业委员会,等. 中国心力衰竭诊断和治疗指南2024[J]. 中华心血管病杂志,2024,52(3):235-275.
[6] 高永祥,张晋昕. Logistic回归分析的样本量确定[J]. 循证医学,2018,18(2):122-124.
[7] 韩君,王君俏,谢博钦,等. Fried衰弱表型和FRAIL量表及埃德蒙顿衰弱评估量表在社区高龄老年人衰弱筛查中一致性和适用性的比较研究[J]. 中国全科医学,2021,24(21):2669-2675.
[8] 王炜,王鲁宁. “蒙特利尔认知评估量表”在轻度认知损伤患者筛查中的应用[J]. 中华内科杂志,2007,46(5):414-416.
[9] Hughes CP, Berg L, Danziger W, et al.A New Clinical Scale for the Staging of Dementia[J]. British J Psychiatry, 1982, 140(6): 566-572.
[10] 郝立晓,胡笑晨,韩璎,等. 英文版主观认知下降问卷的汉化及信效度分析[J]. 中国全科医学,2019,22(26):3238-3245.
[11] Sheikh JI, Yesavage JA, Brooks JR, et al.Proposed factor structure of the Geriatric Depression Scale[J]. Int Psychogeriatr, 1991, 3(1): 23-28.
[12] 唐丹. 简版老年抑郁量表(GDS-15)在中国老年人中的使用[J]. 中国临床心理学杂志,2013,21(3):402-405.
[13] 崔玉,赵秋平,赵彤,等. 简化版双向社会支持量表的汉化及在社区老年人中的信效度检验[J]. 护理学杂志,2022,37(13):94-97.
[14] Liu Q, Si H, Li Y, et al.Development and validation of a risk scoring tool for predicting incident reversible cognitive frailty among community‐dwelling older adults: A prospective cohort study[J]. Geriatr Gerontol Int, 2024, 24(9): 874-882.
[15] Zhang Y, Li MR, Chen X, et al.Prevalence and risk factors of cognitive frailty among pre‐frail and frail older adults in nursing homes[J]. Psychogeriatrics, 2024, 24(3): 529-541.
[16] 李晨,徐敏. 老年心力衰竭患者合并衰弱的最新研究进展[J]. 中华老年多器官疾病杂志,2023,22(6):471-475.
[17] Yamamoto S, Yamasaki S, Higughi S, et al.Prevalence and prognostic impact of cognitive frailty in elderly patients with heart failure: sub‐analysis of FRAGILE‐HF[J]. ESC Heart Fail, 2022, 9(3): 1574-1583.
[18] Ghanbarni MJ, Hosseini SR, Ahangar AA, et al.Prevalence of cognitive frailty and its associated factors in a population of Iranian older adults[J]. Aging Clin Exp Res, 2024, 36(1): 134.
[19] Yilmaz D, Mathavan N, Wehrle E, et al.Mouse models of accelerated aging in musculoskeletal research for assessing frailty, sarcopenia, and osteoporosis-A review[J]. Ageing Res Rev, 2024, 93: 102118.
[20] Peng S, Zhou J, Xiong S, et al.Construction and validation of cognitive frailty risk prediction model for elderly patients with multimorbidity in Chinese community based on non-traditional factors[J]. BMC Psychiatry, 2023, 23(1): 266.
[21] Liang M, Li R, Feng L, et al.Construction and verification of a risk prediction model for cognitive frailty in older patients with chronic obstructive pulmonary disease and diabetes mellitus[J]. J Int Med Res, 2024, 52(9): 3000605241274211.
[22] Ye Y, Wan M, Lin H, et al.Effects of Baduanjin exercise on cognitive frailty, oxidative stress, and chronic inflammation in older adults with cognitive frailty: a randomized controlled trial[J]. Front Public Health, 2024, 12: 1385542.
[23] Dai S, Shi Y, Zhang Y, et al.Influencing factors of two-way social support for the old adults in China: A cross-sectional study[J]. Geriatr Nurs, 2023, 54: 192-198.
[24] 卢静,孙国珍,王洁,等. CHF患者社会衰弱现状及其影响因素可解释性分析研究[J]. 中国全科医学,2025,28(2):220-227.
[25] Geng Z, Yang C, Zhao Z, et al.Development and validation of a machine learning-based predictive model for assessing the 90-day prognostic outcome of patients with spontaneous intracerebral hemorrhage[J]. J Transl Med, 2024, 22(1): 236.
[26] Liu R, Wu S, Yu HY, et al.Prediction model for hepatocellular carcinoma recurrence after hepatectomy: Machine learning-based development and interpretation study[J]. Heliyon, 2023, 9(11): e22458.
[27] 汪丹丹,姚侃斐,祝雪花. 3种机器学习算法对维持性血液透析病人衰弱风险预测性能比较[J]. 护理研究,2024,38(1):8-16.