Identification, explanation and clinical evaluation of hospital patient subtypes

TL;DR

This study develops an unsupervised machine learning pipeline to identify and interpret hospital patient subtypes, combining automated explainability with clinician insights to enhance clinical understanding.

Contribution

The paper introduces a novel pipeline that integrates unsupervised learning and explainability techniques with clinical evaluation for patient subtype identification.

Findings

Successful identification of patient subtypes with clinical relevance

Enhanced interpretability through explainability techniques

Clinician validation supports the clinical meaningfulness of subtypes

Abstract

We present a pipeline in which unsupervised machine learning techniques are used to automatically identify subtypes of hospital patients admitted between 2017 and 2021 in a large UK teaching hospital. With the use of state-of-the-art explainability techniques, the identified subtypes are interpreted and assigned clinical meaning. In parallel, clinicians assessed intra-cluster similarities and inter-cluster differences of the identified patient subtypes within the context of their clinical knowledge. By confronting the outputs of both automatic and clinician-based explanations, we aim to highlight the mutual benefit of combining machine learning techniques with clinical expertise.