Predicting 14-day readmission in middle-aged and elderly patients with pneumonia using emergency department data: a multicentre retrospective cohort study with a survival machine learning approach.

Journal: BMJ open
Published Date: Jun 17, 2025

Abstract

OBJECTIVES: Unplanned pneumonia readmissions increase patient morbidity, mortality and healthcare costs. Among pneumonia patients, the middle-aged and elderly (≥45 years old) have a significantly higher risk of readmission compared with the young. Given that the 14-day readmission rate is considered a healthcare quality indicator, this study is the first to develop survival machine learning (ML) models using emergency department (ED) data to predict 14-day readmission risk following pneumonia-related admissions.

Authors

  • Nguyen Thanh Nhu
    International Ph.D. Program in Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
  • Jiunn-Horng Kang
    Department of Physical Medicine and Rehabilitation, Taipei Medical University Hospital, 252 Wuxing St, Xinyi District, 11031, Taipei City, Taiwan.
  • Tian-Shin Yeh
    Department of Physical Medicine and Rehabilitation, School of Medicine, College of Medicine, Taipei Medical University, Taipei, Taiwan.
  • Jer-Hwa Chang
    Division of Pulmonary Medicine, Department of Internal Medicine, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.
  • Yu-Tien Tzeng
    Division of Pulmonary Medicine, Department of Internal Medicine, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.
  • Ta-Chien Chan
    Research Center for Humanities and Social Sciences, Academia Sinica, Taiwan.
  • Chia-Chieh Wu
    Emergency Department, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.
  • Carlos Lam
    Emergency Department, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.

Keywords

External Resources

Popular Topics
Recent Journals