Discovering patient groups in sequential electronic healthcare data using unsupervised representation learning

Unsupervised feature learning methods inspired by natural language processing (NLP) models are capable of constructing patient-specific features from longitudinal Electronic Health Records (EHR).

We applied document embedding algorithms to real-world paediatric intensive care (PICU) EHR data to extract patient-specific features from 1853 patients' PICU journeys using 647 unique lab tests and medication events. We evaluated the clinical utility of the patient features via a K-means clustering analysis.

We trained a document embedding model under a unique evaluation pipeline and obtained latent patient feature vectors for all 1853 patients. We performed unsupervised clustering to the patient vectors as a downstream analysis and obtained 5 distinct clusters via hyperparameter optimisation. Significant variations (p<0.0001) within both patient characteristics and surgery intervention and diagnostic profiles were detected.

The K-means clustering results demonstrated the clinical utilities of the patient-specific features learned from the embedding algorithms. The latent patient features obtained via the embedding process enabled direct applications of other machine learning algorithms. Future work will focus on utilising the temporal information within EHR and extending EHR embedding algorithms to develop personalised patient journey predictions.