Predicting clinical outcomes from patient care pathways represented with temporal knowledge graphs

TL;DR

This study explores the use of temporal knowledge graphs and Graph Convolutional Networks for predicting clinical outcomes from patient care pathways, highlighting the importance of data schema and temporal encoding.

Contribution

It demonstrates that graph-based representations and GCN embeddings outperform tabular data in clinical outcome prediction, emphasizing schema design and temporal data handling.

Findings

Graph representations with GCNs achieve superior predictive performance.

Schema design and literal value inclusion significantly impact results.

Temporal encoding choices influence GCN effectiveness.

Abstract

Background: With the increasing availability of healthcare data, predictive modeling finds many applications in the biomedical domain, such as the evaluation of the level of risk for various conditions, which in turn can guide clinical decision making. However, it is unclear how knowledge graph data representations and their embedding, which are competitive in some settings, could be of interest in biomedical predictive modeling. Method: We simulated synthetic but realistic data of patients with intracranial aneurysm and experimented on the task of predicting their clinical outcome. We compared the performance of various classification approaches on tabular data versus a graph-based representation of the same data. Next, we investigated how the adopted schema for representing first individual data and second temporal data impacts predictive performances. Results: Our study illustrates that in our case, a graph representation and Graph Convolutional Network (GCN) embeddings reach the best performance for a predictive task from observational data. We emphasize the importance of the adopted schema and of the consideration of literal values in the representation of individual data. Our study also moderates the relative impact of various time encoding on GCN performance.