Using Biomedical Knowledge Graphs to Identify High-Risk Patients for Multiple Sclerosis via Electronic Health Record Retrieval Methods

Supervisor:  Dr Seyhan Yazar

Project Description

This collaborative project aims to identify patients at risk for developing Multiple Sclerosis (MS) by analysing their electronic health records (EHRs) through the lens of a biomedical knowledge graph (KG). Early detection of MS is crucial for timely intervention and improved patient
outcomes. MS is a chronic, demyelinating disease of the central nervous system, affecting nearly 2.9 million people worldwide. Currently, diagnosing MS can be a slow process. This project seeks to develop a novel approach to identify individuals in the prodromal phase (early stage
with subtle symptoms) by leveraging the power of EHR data and network analysis. The project is led by researchers from the Open Coast-to-Coast Australian Multiple Sclerosis (OCCAMS) consortium, who are committed to improving the quality of life for MS patients (Dr Seyhan Yazar from Garvan Institute as primary supervisor and Dr Sara Ballouz from School of Computer Science and Engineering as expert in AI methods).

Project Aims: 

This project aims to build a knowledge graph (KG) of MS prodrome and link it to electronic health records (EHRs) to study its characteristics. The KG will gather information from various sources and connect entities like genes, symptoms, and medications. By linking the KG to EHRs, candidate can analyse patient data to identify potential MS prodrome cases, study its progression, and develop better diagnostic tools. This will ultimately aid in monitoring high-risk patients and implementing early interventions.