Enhancing In-Hospital Mortality Prediction Using Multi-Representational Learning with LLM-Generated Expert Summaries

TL;DR

This paper presents a multi-representational learning framework that combines physiological data, clinical notes, and LLM-generated expert summaries to significantly improve in-hospital mortality prediction accuracy for ICU patients.

Contribution

It introduces a novel integration of LLM-generated summaries with structured and unstructured data, enhancing predictive performance and interpretability in ICU mortality prediction.

Findings

Achieved 36.41% improvement in AUPRC over baseline

Enhanced AUROC to 0.8955 with the proposed model

Expert summaries outperform clinical notes or time-series data alone

Abstract

In-hospital mortality (IHM) prediction for ICU patients is critical for timely interventions and efficient resource allocation. While structured physiological data provides quantitative insights, clinical notes offer unstructured, context-rich narratives. This study integrates these modalities with Large Language Model (LLM)-generated expert summaries to improve IHM prediction accuracy. Using the MIMIC-III database, we analyzed time-series physiological data and clinical notes from the first 48 hours of ICU admission. Clinical notes were concatenated chronologically for each patient and transformed into expert summaries using Med42-v2 70B. A multi-representational learning framework was developed to integrate these data sources, leveraging LLMs to enhance textual data while mitigating direct reliance on LLM predictions, which can introduce challenges in uncertainty quantification and interpretability. The proposed model achieved an AUPRC of 0.6156 (+36.41%) and an AUROC of 0.8955 (+7.64%) compared to a time-series-only baseline. Expert summaries outperformed clinical notes or time-series data alone, demonstrating the value of LLM-generated knowledge. Performance gains were consistent across demographic groups, with notable improvements in underrepresented populations, underscoring the framework's equitable application potential. By integrating LLM-generated summaries with structured and unstructured data, the framework captures complementary patient information, significantly improving predictive performance. This approach showcases the potential of LLMs to augment critical care prediction models, emphasizing the need for domain-specific validation and advanced integration strategies for broader clinical adoption.