Unsupervised Learning Approaches for Identifying ICU Patient Subgroups: Do Results Generalise?

TL;DR

This study investigates whether ICU patient subgroups identified through unsupervised learning are consistent across different hospitals, finding significant variation and suggesting tailored approaches are more effective than standardised restructuring.

Contribution

The paper tests the generalisability of ICU patient subgroups across different datasets, revealing limited overlap and highlighting the need for ICU-specific subgrouping strategies.

Findings

Limited similarity between subgroups across ICUs

Significant variation suggests standardised approaches are ineffective

Tailored ICU restructuring may improve efficiency

Abstract

The use of unsupervised learning to identify patient subgroups has emerged as a potentially promising direction to improve the efficiency of Intensive Care Units (ICUs). By identifying subgroups of patients with similar levels of medical resource need, ICUs could be restructured into a collection of smaller subunits, each catering to a specific group. However, it is unclear whether common patient subgroups exist across different ICUs, which would determine whether ICU restructuring could be operationalised in a standardised manner. In this paper, we tested the hypothesis that common ICU patient subgroups exist by examining whether the results from one existing study generalise to a different dataset. We extracted 16 features representing medical resource need and used consensus clustering to derive patient subgroups, replicating the previous study. We found limited similarities between our results and those of the previous study, providing evidence against the hypothesis. Our findings imply that there is significant variation between ICUs; thus, a standardised restructuring approach is unlikely to be appropriate. Instead, potential efficiency gains might be greater when the number and nature of the subunits are tailored to each ICU individually.