Hierarchical Pretraining on Multimodal Electronic Health Records

TL;DR

This paper introduces MEDHMP, a hierarchical pretraining framework for multimodal electronic health records, improving generalization across diverse medical tasks by capturing the data's hierarchical structure.

Contribution

The paper presents a novel unified pretraining method tailored for hierarchically structured multimodal EHR data, addressing limitations of previous models.

Findings

Outperforms 18 baseline models across 8 downstream tasks

Effectively captures hierarchical and multimodal features of EHR data

Enhances model generalization in medical NLP applications

Abstract

Pretraining has proven to be a powerful technique in natural language processing (NLP), exhibiting remarkable success in various NLP downstream tasks. However, in the medical domain, existing pretrained models on electronic health records (EHR) fail to capture the hierarchical nature of EHR data, limiting their generalization capability across diverse downstream tasks using a single pretrained model. To tackle this challenge, this paper introduces a novel, general, and unified pretraining framework called MEDHMP, specifically designed for hierarchically multimodal EHR data. The effectiveness of the proposed MEDHMP is demonstrated through experimental results on eight downstream tasks spanning three levels. Comparisons against eighteen baselines further highlight the efficacy of our approach.