Unsupervised Learning to Subphenotype Delirium Patients from Electronic Health Records

TL;DR

This study uses unsupervised learning on electronic health records to identify subphenotypes of delirium, enabling more precise detection and monitoring tailored to different patient subgroups in ICU and emergency settings.

Contribution

It introduces a method to discover delirium subtypes and develop subgroup-specific predictive models, enhancing the accuracy of delirium detection in heterogeneous patient populations.

Findings

Existence of distinct delirium clusters identified

Feature importance varies across subgroups

Potential to improve delirium prediction accuracy

Abstract

Delirium is a common acute onset brain dysfunction in the emergency setting and is associated with higher mortality. It is difficult to detect and monitor since its presentations and risk factors can be different depending on the underlying medical condition of patients. In our study, we aimed to identify subtypes within the delirium population and build subgroup-specific predictive models to detect delirium using Medical Information Mart for Intensive Care IV (MIMIC-IV) data. We showed that clusters exist within the delirium population. Differences in feature importance were also observed for subgroup-specific predictive models. Our work could recalibrate existing delirium prediction models for each delirium subgroup and improve the precision of delirium detection and monitoring for ICU or emergency department patients who had highly heterogeneous medical conditions.