PhD Student in Machine Learning

With a Passion for the Biomedical Domain

Health Care, Biomedical Applications, Time-Series, Graph Neural Networks

Multi-modal Graph Learning over UMLS Knowledge Graphs

Paper: https://arxiv.org/abs/2307.04461 GitHub: https://github.com/ratschlab/mmugl 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.