跳到正文
原文
Nature 健康护理主题·· 8 天前AI 评分43

联邦学习保持可解释性用于临床决策:SHAP分析ICU死亡率预测模型的可解释性一致性

Preserving explainability in federated learning for clinical decision-making: SHAP explainability consistency analysis of ICU mortality prediction models

AI 导读

该研究评估了联邦学习(FL)与集中式学习(CL)在ICU死亡率预测中对特征重要性的排序一致性。使用MIMIC-III、MIMIC-IV和eICU三个电子健康记录数据集,SHAP分析显示联邦蒸馏学生模型的SRCC值在0.6463至0.8374之间,AUROC分别为0.8294、0.8402和0.8515。

正文

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

As medical privacy regulations restrict the centralized aggregation of Electronic Health Records (EHRs), Federated Learning (FL) has emerged as a promising alternative for training predictive models across distributed clinical sites. However, clinical deployment of Machine Learning (ML) models requires not only a high predictive performance but also clinical trustworthiness, which can be supported by eXplainable Artificial Intelligence (XAI). In this paper, explainability consistency, defined as the quantitative consistency of feature importance rankings between Centralized Learning (CL) and FL models, is systematically evaluated by analyzing SHapley Additive exPlanations (SHAP) feature importances using Spearman’s Rank Correlation Coefficient (SRCC). Using three benchmark EHR datasets (MIMIC-III, MIMIC-IV, and eICU), explainability consistency in mortality prediction is evaluated across tree-based ensembles (LightGBM and XGBoost) utilizing cyclic boosting and TabPFN teachers with distilled XGBoost students. Experimental results demonstrate explainability consistency across nine architecture-matched comparisons, with SRCC values ranging from 0.6463 to 0.8374. Federated distilled students achieve Area Under the Receiver Operating Characteristic Curve (AUROC) values of 0.8294 (MIMIC-III), 0.8402 (MIMIC-IV) and 0.8515 (eICU), close to centralized students. These findings provide a quantitative framework for evaluating explainability consistency alongside the predictive performance when comparing centralized and federated mortality prediction models.

Acknowledgements

This research was supported by Korea Institute for Advancement of Technology (KIAT) grant funded by the Korea Government (MOTIE) (RS-2024-00420590, HRD Program for Industrial Innovation).

Author information

Authors and Affiliations

  1. School of Electrical and Electronic Engineering, College of Engineering, Yonsei University, 50 Yonsei-Ro, Seodaemun-Gu, 03722, Seoul, South Korea

    Byounghoon Son & Jong-Moon Chung

  2. Department of Emergency Medicine, College of Medicine, Yonsei University, 50 Yonsei-Ro, Seodaemun-Gu, 03722, Seoul, South Korea

    Jong-Moon Chung

Authors

  1. Byounghoon Son
  2. Jong-Moon Chung

Corresponding author

Correspondence to Jong-Moon Chung.

Ethics declarations

Competing interests

The authors declare no competing interests.

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

Son, B., Chung, JM. Preserving explainability in federated learning for clinical decision-making: SHAP explainability consistency analysis of ICU mortality prediction models. Sci Rep (2026). https://doi.org/10.1038/s41598-026-79688-4

Download citation

  • Received: 04 July 2026

  • Accepted: 03 November 2026

  • Published: 12 November 2026

  • DOI: https://doi.org/10.1038/s41598-026-79688-4

Keywords

来源:Nature 健康护理主题 · nature.com