跳到正文
原文
Nature 健康护理主题·· 2026-10-20AI 评分42

机器学习模型用于全因死亡及心血管病、卒中死亡的状态分类

Machine learning models for classifying all-cause mortality and deaths from cardiovascular disease and stroke

AI 导读

一项基于4137名参与者的机器学习研究评估了全因、心血管及卒中死亡分类模型。全因死亡分类中,Elastic Net与支持向量机AUROC值均为0.925;心血管死亡Elastic Net最优(AUROC 0.873),卒中死亡支持向量机最优(AUROC 0.837)。校准偏差显示重平衡概率不能直接作为绝对风险估计,且联合模型未提升判别力。

正文

Scientific Reports (2026) Cite this article

We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.

Abstract

All-cause, cardiovascular, and stroke mortality are major public-health burdens, but mortality-status classifiers require rigorous validation and cautious calibration interpretation. We analyzed 4,137 sampled participants with linked binary mortality labels: 1,473 all-cause deaths, including 821 cardiovascular deaths and 223 stroke deaths. Single-task Elastic Net, Random Forest, XGBoost, and support vector machine models, together with an exploratory joint multinomial Elastic Net, were evaluated using 5-fold outer and 3-fold inner nested stratified cross-validation. Imputation, encoding, normalization, and class up-sampling were restricted to training folds, and performance was calculated from pooled out-of-fold predictions. For all-cause mortality, Elastic Net and the support vector machine achieved similar AUROC values of 0.925 after rounding, whereas Elastic Net achieved the highest AUPRC (0.886). Elastic Net performed best for cardiovascular mortality (AUROC 0.873; AUPRC 0.550). For stroke mortality, the support vector machine achieved both the highest AUROC (0.837) and AUPRC (0.189). The joint model did not improve discrimination and performed worse than single-task Elastic Net for cardiovascular mortality. Calibration curves and statistics showed meaningful deviations from ideal calibration; therefore, class-rebalanced probabilities should not be interpreted as validated absolute-risk estimates. SHAP beeswarm and dependence plots identified age and lactate dehydrogenase as prominent nonlinear model-attribution features. These models provide internally validated mortality-status classification, but clinical risk prediction requires outcome dates, fold-contained recalibration, and external validation.

Acknowledgements

The authors thank all subjects who participated in the study.

Funding

This research was funded by Tri-Service General Hospital (grant number TSGH_D_114117).

Author information

Authors and Affiliations

  1. Graduate Institute of Applied Science and Engineering, Fu Jen Catholic University, No.510, Zhongzheng Rd., Xinzhuang Dist, New Taipei City, 242062, Taiwan

    Yi-Liang Lee & Yao-Jen Liang

  2. Department of Obstetrics and Gynecology, Kang Ning General Hospital, Neihu, Taipei, Taiwan

    Yi-Liang Lee

  3. Department of Obstetrics and Gynecology, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan

    Yi-Liang Lee, Chen-Yu Wang & Ta-Wei Chu

  4. Graduate Institute of Life Sciences, College of Biomedical Sciences, National Defense Medical University, Taipei, Taiwan

    Kuei-Han Tsai

  5. MJ Health Research Foundation, Taipei, Taiwan

    Ta-Wei Chu

  6. Division of Neurology, Department of Internal Medicine, Hsinchu Branch, Taipei Veterans General Hospital, Hsinchu City, Taiwan

    Jiu-Haw Yin

  7. Department of Neurology, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan

    Jiu-Haw Yin

Authors

  1. Yi-Liang Lee
  2. Chen-Yu Wang
  3. Kuei-Han Tsai
  4. Ta-Wei Chu
  5. Jiu-Haw Yin
  6. Yao-Jen Liang

Corresponding author

Correspondence to Yao-Jen Liang.

Ethics declarations

Competing interests

The authors declare no competing interests.

Ethics approval

The study was conducted in accordance with the Declaration of Helsinki, and approved by the Institutional Review Board of Tri-Service General Hospital (protocol code B202405064 and date of approval 11 April 2024).

Informed consent

Informed consent for the use of anonymized data in future research was obtained from participants at the time of their health examinations. Additional project-specific informed consent was not required for this secondary analysis of an existing database.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, YL., Wang, CY., Tsai, KH. et al. Machine learning models for classifying all-cause mortality and deaths from cardiovascular disease and stroke. Sci Rep (2026). https://doi.org/10.1038/s41598-026-75245-1

Download citation

  • Received: 20 April 2026

  • Accepted: 06 October 2026

  • Published: 20 October 2026

  • DOI: https://doi.org/10.1038/s41598-026-75245-1

Keywords

来源:Nature 健康护理主题 · nature.com