Towards accurate and reliable ICU outcome prediction: a multimodal learning framework based on belief function theory using structured EHRs and free-text notes

TL;DR

This paper introduces a multimodal learning framework based on belief function theory that effectively integrates structured EHR data and free-text notes to improve ICU outcome prediction accuracy and reliability, outperforming existing methods.

Contribution

The study proposes a novel belief function-based fusion strategy for multimodal EHR data, enhancing prediction accuracy and uncertainty management in ICU outcome prediction.

Findings

Outperformed baseline by 1.05%/1.02% in BACC for mortality/PLOS

Reduced Brier score by 26.8%/15.1% for mortality/PLOS

Improved AUROC and AUPRC metrics significantly

Abstract

Accurate Intensive Care Unit (ICU) outcome prediction is critical for improving patient treatment quality and ICU resource allocation. Existing research mainly focuses on structured data, e.g. demographics and vital signs, and lacks effective frameworks to integrate clinical notes from heterogeneous electronic health records (EHRs). This study aims to explore a multimodal framework based on belief function theory that can effectively fuse heterogeneous structured EHRs and free-text notes for accurate and reliable ICU outcome prediction. The fusion strategy accounts for prediction uncertainty within each modality and conflicts between multimodal data. The experiments on MIMIC-III dataset show that our framework provides more accurate and reliable predictions than existing approaches. Specifically, it outperformed the best baseline by 1.05%/1.02% in BACC, 9.74%/6.04% in F1 score, 1.28%/0.9% in AUROC, and 6.21%/2.68% in AUPRC for predicting mortality and PLOS, respectively. Additionally, it improved the reliability of the predictions with a 26.8%/15.1% reduction in the Brier score and a 25.0%/13.3% reduction in negative log-likelihood. By effectively reducing false positives, the model can aid in better allocation of medical resources in the ICU. Furthermore, the proposed method is very versatile and can be extended to analyzing multimodal EHRs for other clinical tasks. The code implementation is available on https://github.com/yuchengruan/evid_multimodal_ehr.