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.
@article{arxiv.2301.08019,
title = {Identification, explanation and clinical evaluation of hospital patient subtypes},
author = {Enrico Werner and Jeffrey N. Clark and Ranjeet S. Bhamber and Michael Ambler and Christopher P. Bourdeaux and Alexander Hepburn and Christopher J. McWilliams and Raul Santos-Rodriguez},
journal= {arXiv preprint arXiv:2301.08019},
year = {2023}
}