EUVIMEDEUVIMED entdecken
Crossref

Developing a machine learning-based predictive model for depression risk in patients with cardiovascular diseases

Lin Zhang, Wenjing Li, Pengxin Fan, Jiale Xue, Juanjuan Xie, Wenjun Gui, Yujiang Zhou

Journal of Affective Disorders · 2026-08 · 406 · 121667

DOI: 10.1016/j.jad.2026.121667 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Affective Disorders, 2026-08. Verfasst von Lin Zhang und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department and Institute of Psychology, Ningbo University, Ningbo, 315211, China. Electronic address: zhanglin1@nbu.edu.cn. Hauptthemen laut MEDLINE: Cardiovascular Diseases, Depression, Machine Learning. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Zhejiang Office of Philosophy and Social Science.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Cardiovascular Diseases (CVD) are frequently comorbid with depression, significantly affecting patient prognosis and quality of life. This study aimed to develop and validate a prediction model using Machine Learning (ML) for estimating current depression risk in patients with CVD. METHODS: Data were obtained from the China Health and Retirement Longitudinal Study (CHARLS). The 2020 wave was used for model training and testing, while the 2018 wave served as temporal validation. Eight ML models, including Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Tree (GBT), Adaptive Boosting (AdaBoost), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN), were employed to construct a depression risk prediction model for patients with CVD. The model performance was evaluated using the receiver operating characteristic (ROC) curve, precision-recall (PR) curve, calibration curve, and decision curve analysis (DCA), while model interpretability was assessed via the Shapley additive explanations (SHAP) method. RESULTS: The AdaBoost model showed superior performance. SHAP analysis revealed life satisfaction, instrumental activities of daily living (IADL), sleep time, and self-rated health as the top four predictors of depression risk. CONCLUSION: We developed a model for estimating current depression risk in patients with CVD, which may aid in the early identification of high-risk individuals.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Cardiovascular DiseasesDepressionMachine LearningHumansPredictive Learning ModelsFemaleMaleBoosting Machine Learning AlgorithmsAgedRandom ForestMiddle AgedLongitudinal StudiesChinaClassification AlgorithmsPrediction AlgorithmsRisk AssessmentRisk FactorsROC Curve

Stichwörter der Autor:innen

Cardiovascular DiseasesDepressionMachine LearningOlder AdultsRisk Prediction Model

Autor:innen und Institutionen

  • Department and Institute of Psychology, Ningbo University, Ningbo, 315211, China. Electronic address: zhanglin1@nbu.edu.cn.
  • Department and Institute of Psychology, Ningbo University, Ningbo, 315211, China.

Förderung

  • Zhejiang Office of Philosophy and Social Science

Zitieren

APA

Zhang, L., Li, W., Fan, P., Xue, J., Xie, J., Gui, W., & Zhou, Y. (2026). Developing a machine learning-based predictive model for depression risk in patients with cardiovascular diseases. Journal of Affective Disorders, 406, 121667. https://doi.org/10.1016/j.jad.2026.121667

Vancouver

Zhang L, Li W, Fan P, Xue J, Xie J, Gui W, et al. Developing a machine learning-based predictive model for depression risk in patients with cardiovascular diseases. Journal of Affective Disorders. 2026;406:121667. doi:10.1016/j.jad.2026.121667

BibTeX
@article{Zhang2026,
  author = {Zhang, Lin and Li, Wenjing and Fan, Pengxin and Xue, Jiale and Xie, Juanjuan and Gui, Wenjun and Zhou, Yujiang},
  title = {Developing a machine learning-based predictive model for depression risk in patients with cardiovascular diseases},
  journal = {Journal of Affective Disorders},
  year = {2026},
  volume = {406},
  pages = {121667},
  doi = {10.1016/j.jad.2026.121667}
}
Kostenlos starten →