EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey

Sozioökonomischer Status und Lebensstil als Faktoren von Multimorbidität bei älteren Erwachsenen in China: Ergebnisse aus der China Health and Retirement Longitudinal Survey

Wei Gong, Xiaoxiao Hu, Huimin Cui, Yuxin Zhao, Hong Lin, Peng Sun, Jianjun Yang

Frontiers in Public Health · 30.07.2025 · 13

DOI: 10.3389/fpubh.2025.1586091 ↗

Auf einen Blick

Bei 34.755 Personen ab 60 Jahren sagte ein XGBoost-Modell Multimorbidität am besten voraus (AUC 0,788). Bildung, ADL, Arbeitsstatus, Selbsteinschätzung der Gesundheit und Pro-Kopf-Einkommen waren die wichtigsten Faktoren.

Fragestellung

Welche Rolle spielen sozioökonomische und Lifestyle-Faktoren für Multimorbidität bei älteren Erwachsenen in China?

Methode

Auswertung national repräsentativer CHARLS-Daten; 34.755 Personen ab 60 Jahren; 17 Merkmale; LASSO und 8 Machine-Learning-Algorithmen; Bewertung mit AUC, Accuracy, Precision, Recall, F1, RMSE und DCA; SHAP-Analyse.

Ergebnisse

XGBoost erzielte die beste Vorhersageleistung (AUC 0,788 im Testset) und war den linearen und nichtlinearen Modellen in den meisten Metriken überlegen. SHAP zeigte Bildung, ADL, Arbeitsstatus, Selbsteinschätzung der Gesundheit und Pro-Kopf-Einkommen als Top-Faktoren.

Schlussfolgerung der Autor:innen

Die Studie zeigte die Machbarkeit und Interpretierbarkeit von Machine Learning zur Modellierung komplexer Risikomuster von Multimorbidität. Sozioökonomische und funktionelle Variablen waren dominierende Faktoren und weisen auf strukturelle Ursachen von Ungleichheit hin.

Kernaussagen

  • XGBoost: beste Vorhersage von Multimorbidität mit AUC 0,788
  • Bildung, ADL, Arbeitsstatus und Einkommen waren zentrale Faktoren
  • Assoziationen variierten nach Alter und Geschlecht

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Public Health, online erschienen am 30.07.2025. Verfasst von Wei Gong und 6 weiteren Autor:innen. Beteiligte Einrichtung: Public Health School, Ningxia Medical University, Yinchuan, China. Hauptthemen laut MEDLINE: Multimorbidity, Life Style, Social Class. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 64 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

Auf einen BlickAbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Multimorbidity is increasingly prevalent among older adults and poses significant challenges to public health systems. While previous studies have highlighted the role of individual behaviors, the complex interaction between lifestyle factors and socioeconomic status (SES) in multimorbidity remains unclear.

Methods

Using nationally representative data from the China Health and Retirement Longitudinal Study (CHARLS), we developed predictive models to identify key determinants of multimorbidity among individuals aged ≥60 years. A total of 34,755 participants were included, and 17 features related to demographics, SES, and lifestyle were selected via LASSO regression. Eight machine learning algorithms including logistic regression, decision tree, naive Bayes, neural network, support vector machine, random forest, XGBoost and Bayesian Ridge Regression were applied to build predictive models. Model performance was evaluated using AUC, accuracy, precision, recall, F1-score, RMSE, and decision curve analysis (DCA). SHapley Additive exPlanations (SHAP) were used to interpret model outputs.

Results

XGBoost achieved the best predictive performance (AUC = 0.788 on the test set), outperforming both linear and non-linear models across most evaluation metrics. SHAP analysis revealed that education level, activities of daily living (ADL), work status, self-assessed health status, and per capita income were the top factors associated with of multimorbidity. Subgroup analyses showed variated associations by age and sex, with psychological and geographic factors playing a larger role among those aged ≥80.

Conclusion

This study demonstrated the feasibility and interpretability of using machine learning to model complex risk patterns of multimorbidity. Socioeconomic and functional variables were dominant factors associated with multimorbidity, suggesting structural roots of health inequality. These findings offered empirical and theoretical support for early risk stratification and targeted public health interventions aimed at mitigating multimorbidity in aging populations.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultimorbidityLife StyleSocial ClassHumansMaleFemaleChinaLongitudinal StudiesAgedMiddle AgedAged, 80 and overRetirementMachine Learning

Stichwörter der Autor:innen

Chinese older adultSHAPXGBoostmachine learningmultimorbiditypredictive model

Autor:innen und Institutionen

  • Public Health School, Ningxia Medical University, Yinchuan, China.
  • Key Laboratory of Environmental Factors and Chronic Disease Control, Yinchuan, China.
  • School of Medical Information and Engineering, Ningxia Medical University, Yinchuan, China.
  • School of Nursing, Ningxia Medical University, Yinchuan, China.
  • Institute of Medical Science and Technology, Ningxia Medical University, Yinchuan, China.

Zitieren

APA

Gong, W., Hu, X., Cui, H., Zhao, Y., Lin, H., Sun, P., & Yang, J. (2025). Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey. Frontiers in Public Health, 13. https://doi.org/10.3389/fpubh.2025.1586091

Vancouver

Gong W, Hu X, Cui H, Zhao Y, Lin H, Sun P, et al. Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey. Frontiers in Public Health. 2025;13. doi:10.3389/fpubh.2025.1586091

BibTeX
@article{Gong2025,
  author = {Gong, Wei and Hu, Xiaoxiao and Cui, Huimin and Zhao, Yuxin and Lin, Hong and Sun, Peng and Yang, Jianjun},
  title = {Socioeconomic status and lifestyle as factors of multimorbidity among older adults in China: results from the China Health and Retirement Longitudinal Survey},
  journal = {Frontiers in Public Health},
  year = {2025},
  volume = {13},
  doi = {10.3389/fpubh.2025.1586091}
}
Kostenlos starten →