Towards symbolic regression for interpretable clinical decision scores
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences · 09.04.2026 · 384 (2317)
DOI: 10.1098/rsta.2024.0588 ↗Kurz gefasst
Fachartikel in der Zeitschrift Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, online erschienen am 09.04.2026. Verfasst von Guilherme Seidyo Imai Aldeia und 4 weiteren Autor:innen. Beteiligte Einrichtung: Federal University of the ABC , Santo André, São Paulo, Brazil. Hauptthemen laut MEDLINE: Clinical Decision-Making. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, U.S. National Library of Medicine, Conselho Nacional de Desenvolvimento Científico e Tecnológico.
Abstract (Originalsprache)
Medical decision-making makes frequent use of algorithms that combine risk equations with rules, providing clear and standardized treatment pathways. Symbolic regression (SR) traditionally limits its search space to continuous function forms and their parameters, making it difficult to model this decision-making. However, owing to its ability to derive data-driven, interpretable models, SR holds promise for developing data-driven clinical risk scores. To that end, we introduce Brush, an SR algorithm that combines decision-tree-like splitting algorithms with nonlinear constant optimization, allowing for seamless integration of rule-based logic into SR and classification models. Brush achieves Pareto-optimal performance on SRBench and was applied to recapitulate two widely used clinical scoring systems, achieving high accuracy and interpretable models. Compared with decision trees (DTs), random forests (RFs) and other SR methods, Brush achieves comparable or superior predictive performance while producing simpler models. This article is part of the discussion meeting issue ‘Symbolic regression in the physical sciences’.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Federal University of the ABC , Santo André, São Paulo, Brazil.
- Computational Health Informatics Program, Boston Children's Hospital, Boston, MA, USA.
- Harvard Medical School , Boston, MA, USA.
- Institute for Biomedical Informatics, University of Pennsylvania, Philadelphia, PA, USA.
- Department of Pathology and Laboratory Medicine, University of Pennsylvania, Philadelphia, PA, USA.
ORCID-Profile: Guilherme Seidyo Imai Aldeia, Fabricio Olivetti de França, William G La Cava
Förderung
- Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
- U.S. National Library of Medicine
- Conselho Nacional de Desenvolvimento Científico e Tecnológico
- NLM NIH HHS
- Patient-Centered Outcomes Research Institute
Zitieren
APA
Imai Aldeia, G. S., Romano, J. D., Olivetti de França, F., Herman, D. S., & La Cava, W. G. (2026). Towards symbolic regression for interpretable clinical decision scores. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, 384(2317). https://doi.org/10.1098/rsta.2024.0588
Vancouver
Imai Aldeia GS, Romano JD, Olivetti de França F, Herman DS, La Cava WG. Towards symbolic regression for interpretable clinical decision scores. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences. 2026;384(2317). doi:10.1098/rsta.2024.0588
BibTeX
@article{ImaiAldeia2026,
author = {Imai Aldeia, Guilherme Seidyo and Romano, Joseph D and Olivetti de França, Fabricio and Herman, Daniel S and La Cava, William G},
title = {Towards symbolic regression for interpretable clinical decision scores},
journal = {Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences},
year = {2026},
volume = {384},
number = {2317},
doi = {10.1098/rsta.2024.0588}
}
EUVIMED