Machine learning-based predictive model for postoperative delirium of elderly patients with coronary heart disease undergoing non-cardiac surgery: a retrospective cohort study - Summary - MDSpire

Machine learning-based predictive model for postoperative delirium of elderly patients with coronary heart disease undergoing non-cardiac surgery: a retrospective cohort study

  • By

  • Wenjie Kong

  • Jing Jiang

  • Yuanlong Wang

  • Jiayi Chen

  • Bin Wang

  • Kun Wang

  • Yizhi Liang

  • Jiahan Wang

  • Chuan Li

  • Yanan Lin

  • Hongyan Gong

  • Yongxin Liang

  • Yanlin Bi

  • Xu Lin

  • March 27, 2026

  • 0 min

Share

Objective:

To develop a predictive model for postoperative delirium (POD) in elderly patients with coronary heart disease (CHD) undergoing non-cardiac surgery.

Key Findings:
  • The incidence of POD was 16.6% among the studied patients.
  • Seven key features were identified, with CFS grade, MMSE score, and AIS score being significant predictors.
  • The GBM model achieved an AUC of 0.856, indicating good predictive performance.
Interpretation:

Higher CFS grade, lower MMSE score, and higher AIS score significantly enhance the predictive ability of the model for POD in elderly CHD patients.

Limitations:
  • The study is retrospective and conducted at a single center, which may limit generalizability.
  • External validation of the model is needed before clinical application.
Conclusion:

A reliable GBM model for predicting POD in elderly CHD patients was developed, highlighting the importance of specific clinical assessments in risk stratification.

Original Source(s)

Machine learning-based predictive model for postoperative delirium of elderly patients with coronary heart disease undergoing non-cardiac surgery: a retrospective cohort study

  • by Wenjie Kong, Jing Jiang, Yuanlong Wang, Jiayi Chen, Bin Wang, Kun Wang, Yizhi Liang, Jiahan Wang, Chuan Li, Yanan Lin, Hongyan Gong, Yongxin Liang, Yanlin Bi, Xu Lin

  • March 27, 2026

Related Content

Alexithymia and its subgroup characteristics in Chinese empty-nesters with multiple chronic diseases: an exploration based on latent class analysis

Distinct sleep-disordered breathing phenotypes in elderly patients with depressive disorder: links to hypoxemia severity and inflammatory burden

Wearables May Boost T2D Mobility

Outpatient intervention combined physiotherapist counseling with wrist-worn activity monitoring.