Good things come in threes: evaluating clinical utility of machine learning-derived clusters
JAMIA Open · 05.05.2026 · 9 (3)
DOI: 10.1093/jamiaopen/ooag098 ↗Kurz gefasst
Übersichtsarbeit in der Zeitschrift JAMIA Open, online erschienen am 12.06.2026. Verfasst von Daniil Lisik und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Public Health and Clinical Medicine, The OLIN and Sunderby Research Unit, Umeå University, Umeå, Sweden. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Swedish government under the ALF agreement with the county councils, Swedish Asthma & Allergy Foundation.
Abstract (Originalsprache)
Background
Machine learning (ML)-based cluster analysis is a common method for subtyping medical conditions and presentations of disease states. Recent advancements in algorithms and increasing access to vast healthcare data have further increased the use of such ML models. However, practical implementation is lacking, largely due to methodological limitations and insufficient reporting and clinical contextualization in the extant literature, with no existing guidelines for this purpose.
Objective
To propose a general framework to assess and ensure clinical utility of ML-derived clusters.
Discussion
The proposed framework encompasses three domains, focusing on clinical relevance, stability and generalizability, and ease of identification, enabling researchers and readers to ensure clinical utility of ML-generated subgroups.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Public Health and Clinical Medicine, The OLIN and Sunderby Research Unit, Umeå University, Umeå, Sweden.
- Krefting Research Centre, Institute of Medicine, Sahlgrenska Academy, University of Gothenburg, Gothenburg, Sweden.
- Department of Intensive Care Medicine, Maastricht University Medical Centre, Maastricht, the Netherlands.
- Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, the Netherlands.
- COPD Center, Sahlgrenska University Hospital, University of Gothenburg, Gothenburg, Sweden.
- Wallenberg Centre for Molecular and Translational Medicine, University of Gothenburg, Gothenburg, Sweden.
ORCID-Profile: Daniil Lisik, Jip W T M De Kok, Nicolás Bermúdez Barón, Lowie E G W Vanfleteren, Bright I Nwaru, Rani Basna
Förderung
- Swedish government under the ALF agreement with the county councils
- Swedish Asthma & Allergy Foundation
Zitieren
APA
Lisik, D., De Kok, J. W. T. M., Bermúdez Barón, N., Vanfleteren, L. E. G. W., Nwaru, B. I., & Basna, R. (2026). Good things come in threes: evaluating clinical utility of machine learning-derived clusters. JAMIA Open, 9(3). https://doi.org/10.1093/jamiaopen/ooag098
Vancouver
Lisik D, De Kok JWTM, Bermúdez Barón N, Vanfleteren LEGW, Nwaru BI, Basna R. Good things come in threes: evaluating clinical utility of machine learning-derived clusters. JAMIA Open. 2026;9(3). doi:10.1093/jamiaopen/ooag098
BibTeX
@article{Lisik2026,
author = {Lisik, Daniil and De Kok, Jip W T M and Bermúdez Barón, Nicolás and Vanfleteren, Lowie E G W and Nwaru, Bright I and Basna, Rani},
title = {Good things come in threes: evaluating clinical utility of machine learning-derived clusters},
journal = {JAMIA Open},
year = {2026},
volume = {9},
number = {3},
doi = {10.1093/jamiaopen/ooag098}
}
EUVIMED