Scholarlink

<p>Predicting multiple postoperative complications remains challenging in perioperative care. Current approaches often address complications individually, limiting the potential for integrated risk assessment. We developed and externally validated a scalable, interpretable, tree-based multitask learning model to predict three critical postoperative outcomes—acute kidney injury (AKI), postoperative respiratory failure (PRF), and in-hospital mortality—using 16 preoperative features generally available in electronic health records. Our model achieved AUROCs of 0.805, 0.789, and 0.863 for AKI; 0.886, 0.925, and 0.911 for PRF; and 0.907, 0.913, and 0.849 for mortality in the derivation cohort and external validation cohorts A and B, respectively (all <i>p</i> &lt; 0.001, except for AKI in derivation and PRF in cohort B). We also elucidated the contribution of each input variable to predictions among different outcomes. Our findings highlight the potential of multitask learning to streamline preoperative risk assessment and present a scalable, interpretable, and generalizable framework for improving perioperative care.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Multicenter validation of a scalable, interpretable, multitask prediction model for multiple clinical outcomes

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年9月30日

查看全文
  • Hyun-Kyu Yoon,
  • Bo Rim Kim,
  • Hyo Young Kim,
  • Dae Keun Park,
  • Hyo Sung Kim,
  • Hye-Yeon Cho,
  • Hyung-Chul Lee,
  • Hyeonhoon Lee

摘要

Predicting multiple postoperative complications remains challenging in perioperative care. Current approaches often address complications individually, limiting the potential for integrated risk assessment. We developed and externally validated a scalable, interpretable, tree-based multitask learning model to predict three critical postoperative outcomes—acute kidney injury (AKI), postoperative respiratory failure (PRF), and in-hospital mortality—using 16 preoperative features generally available in electronic health records. Our model achieved AUROCs of 0.805, 0.789, and 0.863 for AKI; 0.886, 0.925, and 0.911 for PRF; and 0.907, 0.913, and 0.849 for mortality in the derivation cohort and external validation cohorts A and B, respectively (all p < 0.001, except for AKI in derivation and PRF in cohort B). We also elucidated the contribution of each input variable to predictions among different outcomes. Our findings highlight the potential of multitask learning to streamline preoperative risk assessment and present a scalable, interpretable, and generalizable framework for improving perioperative care.