A federated learning framework with knowledge graph and temporal transformer for early sepsis prediction in multi-center ICUs

TL;DR

This paper introduces a privacy-preserving federated learning framework that combines knowledge graphs and temporal transformers, enhanced with meta-learning, to improve early sepsis prediction across multiple ICUs, achieving significant accuracy gains.

Contribution

It presents a novel integration of federated learning, knowledge graphs, and temporal transformers with meta-learning for multi-center sepsis prediction, addressing data privacy and complex temporal data challenges.

Findings

Achieved an AUC of 0.956 on MIMIC-IV and eICU datasets.

Improved prediction accuracy by 22.4% over centralized models.

Enhanced model adaptability with meta-learning strategies.

Abstract

The early prediction of sepsis in intensive care unit (ICU) patients is crucial for improving survival rates. However, the development of accurate predictive models is hampered by data fragmentation across healthcare institutions and the complex, temporal nature of medical data, all under stringent privacy constraints. To address these challenges, we propose a novel framework that uniquely integrates federated learning (FL) with a medical knowledge graph and a temporal transformer model, enhanced by meta-learning capabilities. Our approach enables collaborative model training across multiple hospitals without sharing raw patient data, thereby preserving privacy. The model leverages a knowledge graph to incorporate structured medical relationships and employs a temporal transformer to capture long-range dependencies in clinical time-series data. A model-agnostic meta-learning (MAML) strategy is further incorporated to facilitate rapid adaptation of the global model to local data distributions. Evaluated on the MIMIC-IV and eICU datasets, our method achieves an area under the curve (AUC) of 0.956, which represents a 22.4% improvement over conventional centralized models and a 12.7% improvement over standard federated learning, demonstrating strong predictive capability for sepsis. This work presents a reliable and privacy-preserving solution for multi-center collaborative early warning of sepsis.