Scholarlink

<p>Challenges with model generalizability and data privacy have led to a shift in health artificial intelligence (AI) models being trained locally within individual health systems rather than relying on multicenter data. Localization carries the promise of capturing local practice patterns and patient demographics, presumably resulting in better models. Our study empirically tests this hypothesis in a national research network by comparing locally trained models predicting acute kidney injury (AKI) after cardiac surgery with two multicenter modeling approaches, pooling and a novel federated model stacking method. Trained on 43,926 cases across 23 hospitals, the study finds that multicenter models outperform single-center approaches, with higher area under the receiver operating characteristic curves (AUCs) for all AKI severity levels in both temporal and external validation sets. Hospitals with smaller case volumes benefit the most from multicenter approaches, showing the greatest AUC increase over locally trained models.</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

Exploring the limits of localization: federated model stacking improves hospital-level prediction in a national research network

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年4月24日

查看全文
  • Jie Cao,
  • Emily Balczewski,
  • Rahul Ladhania,
  • Paramveer Dhillon,
  • Donald S. Likosky,
  • Allison M. Janda,
  • Nathan L. Pace,
  • Robert E. Freundlich,
  • Douglas A. Colquhoun,
  • Bradley A. Fritz,
  • Robert B. Schonberger,
  • Sachin Kheterpal,
  • Michael R. Mathis,
  • Karandeep Singh

摘要

Challenges with model generalizability and data privacy have led to a shift in health artificial intelligence (AI) models being trained locally within individual health systems rather than relying on multicenter data. Localization carries the promise of capturing local practice patterns and patient demographics, presumably resulting in better models. Our study empirically tests this hypothesis in a national research network by comparing locally trained models predicting acute kidney injury (AKI) after cardiac surgery with two multicenter modeling approaches, pooling and a novel federated model stacking method. Trained on 43,926 cases across 23 hospitals, the study finds that multicenter models outperform single-center approaches, with higher area under the receiver operating characteristic curves (AUCs) for all AKI severity levels in both temporal and external validation sets. Hospitals with smaller case volumes benefit the most from multicenter approaches, showing the greatest AUC increase over locally trained models.