Early Risk Prediction of Pediatric Cardiac Arrest from Electronic Health Records via Multimodal Fused Transformer

TL;DR

This paper presents PedCA-FT, a transformer-based model that fuses tabular and textual EHR data to improve early prediction of pediatric cardiac arrest, demonstrating superior performance over existing models.

Contribution

Introduction of a novel multimodal transformer framework for early pediatric cardiac arrest prediction using fused EHR data.

Findings

Outperforms ten AI models across five metrics

Identifies clinically meaningful risk factors

Effective multimodal fusion enhances early detection

Abstract

Early prediction of pediatric cardiac arrest (CA) is critical for timely intervention in high-risk intensive care settings. We introduce PedCA-FT, a novel transformer-based framework that fuses tabular view of EHR with the derived textual view of EHR to fully unleash the interactions of high-dimensional risk factors and their dynamics. By employing dedicated transformer modules for each modality view, PedCA-FT captures complex temporal and contextual patterns to produce robust CA risk estimates. Evaluated on a curated pediatric cohort from the CHOA-CICU database, our approach outperforms ten other artificial intelligence models across five key performance metrics and identifies clinically meaningful risk factors. These findings underscore the potential of multimodal fusion techniques to enhance early CA detection and improve patient care.