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

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.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-12
DOI
https://doi.org/10.1038/s41598-026-79688-4
Primary Topic
Explainable Artificial Intelligence (XAI)
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

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

Jong-Moon Chung, Byounghoon Son
Scientific Reports
Explainable Artificial Intelligence (XAI)
article

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

Jong-Moon Chung, Byounghoon Son
article en

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.

Scientific Reports
Yonsei University (KR), Yonsei University Health System (KR)
Ministry of Trade, Industry and Energy, Korea Institute for Advancement of Technology
Good health and well-being
Explainable Artificial Intelligence (XAI)
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon