Predicting the decline of physical function among the older adults in China: A cohort study based on China longitudinal health and longevity survey (CLHLS)

Liang Wang; Xiaobing Xian; Meiling Liu; Jie Li; Qi Shu; Siyi Guo; Ke Xu; Shiwei Cao; Wenjia Zhang; Wenyan Zhao; Mengliang Ye

doi:10.1016/j.gerinurse.2024.11.019

Predicting the decline of physical function among the older adults in China: A cohort study based on China longitudinal health and longevity survey (CLHLS)

Geriatr Nurs. 2024 Nov 28:61:378-389. doi: 10.1016/j.gerinurse.2024.11.019. Online ahead of print.

Authors

Liang Wang¹, Xiaobing Xian², Meiling Liu³, Jie Li⁴, Qi Shu⁵, Siyi Guo⁵, Ke Xu¹, Shiwei Cao⁶, Wenjia Zhang¹, Wenyan Zhao⁷, Mengliang Ye⁸

Affiliations

¹ School of Public Health, Chongqing Medical University, Chongqing, PR China.
² Chongqing Geriatrics Hospital, Chongqing, PR China; The Thirteenth People's Hospital of Chongqing, Chongqing, PR China.
³ Department of Gastroenterology, The First Affiliated Hospital of Chongqing Medical University, Chongqing, PR China.
⁴ Academy of Mathematical Sciences, Chongqing Normal University, Chongqing, PR China.
⁵ The First Clinical College, Chongqing Medical University, Chongqing, PR China.
⁶ The Second Clinical College, Chongqing Medical University, Chongqing, PR China.
⁷ Stomatological Hospital of Chongqing Medical University, Chongqing Key Laboratory of Oral Diseases and Biomedical Sciences, Chongqing Municipal Key Laboratory of Oral Biomedical Engineering of Higher Education, Chongqing, PR China.
⁸ School of Public Health, Chongqing Medical University, Chongqing, PR China. Electronic address: yemengliang@cqmu.edu.cn.

PMID: 39612589
DOI: 10.1016/j.gerinurse.2024.11.019

Abstract

Background: As the arrival of healthy aging, maintaining physical function (PF) in older adults is crucial for their health, so it is necessary to detect the decline of PF among them and take intervention measures.

Methods: We construct eight machine learning models to predict declines of PF in this study. The performance of the models was tested by Area Under Curve (AUC), sensitivity, specificity, accuracy, precision-recall (PR) curve and calibration degree. Decision Curve Analysis (DCA) curve was used to evaluate their discrimination ability and clinical practicability.

Results: There were 2,017 participants in this study. We found that logistic regression models performed the best, with AUC, sensitivity, specificity and accuracy of 0.803, 0.698, 0.761 and 0.744 respectively, and its DCA curve, calibration degree and PR curve also performed well.

Conclusion: Logistic regression can be used as optimal model to identify the risk of PF decline among older adults in China.

Keywords: Cohort study; Machine learning; Older adults; Physical function; Prediction model.