Multi-modal Graph Learning over UMLS Knowledge Graphs

TL;DR

This paper introduces MMUGL, a multi-modal graph neural network approach that leverages UMLS knowledge graphs to improve patient visit predictions by integrating prior medical knowledge and multiple data modalities.

Contribution

The paper presents a novel multi-modal graph learning framework that enhances medical concept representations for patient prediction tasks using UMLS-based knowledge graphs.

Findings

Outperforms existing methods on MIMIC-III dataset

Demonstrates the importance of multi-modal representations

Shows the benefit of incorporating prior medical knowledge

Abstract

Clinicians are increasingly looking towards machine learning to gain insights about patient evolutions. We propose a novel approach named Multi-Modal UMLS Graph Learning (MMUGL) for learning meaningful representations of medical concepts using graph neural networks over knowledge graphs based on the unified medical language system. These representations are aggregated to represent entire patient visits and then fed into a sequence model to perform predictions at the granularity of multiple hospital visits of a patient. We improve performance by incorporating prior medical knowledge and considering multiple modalities. We compare our method to existing architectures proposed to learn representations at different granularities on the MIMIC-III dataset and show that our approach outperforms these methods. The results demonstrate the significance of multi-modal medical concept representations based on prior medical knowledge.