Identification, explanation and clinical evaluation of hospital patient subtypes
This work addresses the challenge of understanding patient heterogeneity in healthcare for clinicians and researchers, but it appears incremental as it applies existing methods to a new dataset without claiming major breakthroughs.
The researchers tackled the problem of identifying and interpreting hospital patient subtypes using unsupervised machine learning, resulting in a pipeline that automatically identified subtypes and used explainability techniques to assign clinical meaning, with clinicians evaluating these subtypes to highlight the benefits of combining machine learning with clinical expertise.
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.