Development and validation of a stacking ensemble model for death prediction in the Chinese Longitudinal Healthy Longevity Survey (CLHLS)
Maturitas · 2024
DOI: 10.1016/j.maturitas.2024.107919 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift Maturitas, 2024. Verfasst von Muqi Xing und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Big Data in Health Science School of Public Health, Center of Clinical Big Data and Analytics of The Second Affiliated Hospital, Zhejia…. Hauptthemen laut MEDLINE: Mortality. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 30 Literaturangaben.
Abstract (Originalsprache)
OBJECTIVE: This study aimed to develop and validate a mortality risk prediction model for older people based on the Chinese Longitudinal Healthy Longevity Survey using the stacking ensemble strategy. MATERIAL AND METHODS: A total of 12,769 participants aged 65 or more at baseline were included. Ensemble machine learning models were applied to develop a mortality prediction model. We selected three base learners, including logistic regression, eXtreme Gradient Boosting, and Categorical + Boosting, and used logistic regression as the meta-learner. The primary outcome was five-year survival. Variable importance was evaluated by the SHapley Additive exPlanations method. RESULTS: The mean age at baseline was 88, and 57.8 % of participants were women. The CatBoost model performed the best among the three base learners, the area under the receiver operating characteristics curve (AUC) reached 0.8469 (95%CI: 0.8345-0.8593), and the stacking ensemble model further improved the discrimination ability (AUC = 0.8486, 95%CI: 0.8367-0.8612, P = 0.046). Conventional logistic regression had comparable performance (AUC = 0.8470, 95 % CI: 0.8346-0.8595). Older age, higher scores for self-care activities of daily living, being male, higher objective physical performance capacity scores, not undertaking housework, and lower scores on the Mini-Mental State Examination contributed to higher risk. CONCLUSIONS: We successfully constructed and validated a few death risk prediction models for a Chinese population of older adults. While the stacking ensemble approach had the best prediction performance, the improvement over conventional logistic regression was insubstantial.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Big Data in Health Science School of Public Health, Center of Clinical Big Data and Analytics of The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China.
- School of Public Health, Zhejiang University School of Medicine, Zhejiang University, Hangzhou, Zhejiang, China.
- Department of Biostatistics and Epidemiology, School of Public Health, China Medical University, Shenyang 110122, China.
- Peking University Institute of Mental Health (Sixth Hospital), National Clinical Research Center for Mental Disorders, NHC Key Laboratory of Mental Health, Peking University, 51 Huayuan North Road, Haidian District, Bei…
- Department of Biostatistics and Epidemiology, School of Public Health, China Medical University, Shenyang 110122, China. Electronic address: ynma@cmu.edu.cn.
- Department of Big Data in Health Science School of Public Health, Center of Clinical Big Data and Analytics of The Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou, Zhejiang, China. Electroni…
Zitieren
APA
Xing, M., Zhao, Y., Li, Z., Zhang, L., Yu, Q., Zhou, W., Huang, R., Lv, X., Ma, Y., & Li, W. (2024). Development and validation of a stacking ensemble model for death prediction in the Chinese Longitudinal Healthy Longevity Survey (CLHLS). Maturitas. https://doi.org/10.1016/j.maturitas.2024.107919
Vancouver
Xing M, Zhao Y, Li Z, Zhang L, Yu Q, Zhou W, et al. Development and validation of a stacking ensemble model for death prediction in the Chinese Longitudinal Healthy Longevity Survey (CLHLS). Maturitas. 2024. doi:10.1016/j.maturitas.2024.107919
BibTeX
@article{Xing2024,
author = {Xing, Muqi and Zhao, Yunfeng and Li, Zihan and Zhang, Lingzhi and Yu, Qi and Zhou, Wenhui and Huang, Rong and Lv, Xiaozhen and Ma, Yanan and Li, Wenyuan},
title = {Development and validation of a stacking ensemble model for death prediction in the Chinese Longitudinal Healthy Longevity Survey (CLHLS)},
journal = {Maturitas},
year = {2024},
doi = {10.1016/j.maturitas.2024.107919}
}
EUVIMED