Expanding interpretability through complexity reduction in machine learning‐based modelling of cardiovascular disease: A myocardial perfusion imaging PET/CT prognostic study
The sum-of-sigmoids model is interpretable and simple, while achieving similar prediction accuracy to significantly more complex machine learning models in the considered prediction task. It should be suitable for applications such as automated clinical risk stratification, where clear and explicit justification of the classification procedure is highly pertinent.
Authors
- Remco J.J. Knol (ORCID: https://orcid.org/0000-0003-1089-2981)
- Luis Eduardo Juárez‐Orozco (ORCID: https://orcid.org/0000-0001-6798-7864)
- Maryam Vatandoust
- Jarmo Teuho (ORCID: https://orcid.org/0000-0001-9401-0725)
- Riku Klén (ORCID: https://orcid.org/0000-0002-0982-8360)
- Juhani Knuuti (ORCID: https://orcid.org/0000-0003-3156-9593)
- Eero Lehtonen (ORCID: https://orcid.org/0000-0002-7327-7938)
- Friso M. van der Zant
Institutions
- University of Turku (FI)
- Utrecht University (NL)
- Turku University Hospital (FI)
- University Medical Center Utrecht (NL)
- Turku PET Centre (FI)
- Medisch Centrum Alkmaar (NL)
Publication Details
- Journal
- European Journal of Clinical Investigation
- Published
- 2025-04-01
- DOI
- https://doi.org/10.1111/eci.14391
- Citations
- 2
- Primary Topic
- Cardiac Imaging and Diagnostics
- Type
- article
- Field-Weighted Citation Impact
- 2.72
Funders
- Academy of Finland
- Suomen Kulttuurirahasto
- Turun Yliopistollinen Keskussairaala