Introduction to using symbolic regression for interpretable machine learning in healthcare

Abstract

The past decade has seen machine learning play an increasingly important role in medicine. However, many of the state-of-the-art models being developed and deployed suffer from a lack of transparency, limiting integration into the clinical decision-making process and raising concerns about patient safety. Here we call attention to symbolic regression, a largely overlooked machine learning technique that aims to be both accurate and interpretable by learning readable mathematical models from data. In recent years, it has undergone rapid advancements with successful application to problems across a wide range of disciplines. In this perspective, we provide an approachable introduction to symbolic regression, highlight its strengths and limitations, and explore its potential applications in medicine.

Symbolic and domain-generalized machine learning for interpretable solubility modeling in supercritical CO₂
Sameer Alshehri, Mahboubeh Pishnamazi
Scientific Reports1 Jul 2026Peer-reviewedCC BYFull textGeneral medicineDOAJ
Physics-consistent equation discovery for drug solubility in supercritical CO₂ through symbolic regression and domain generalization
Adel Alhowyan, Ahmad J. Obaidullah, Wael A. Mahdi
Frontiers in medicine19 Oct 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
From tumor regression grading to interpretable endpoints in neoadjuvant oncology
Cédric Schraepen, Albert Wolthuis, Wentao Tang +10
NPJ Precision Oncology3 Jul 2026Peer-reviewedCC BY-NC-ND 4.0Full textOncologyPMC
Costs of influenza-associated healthcare: an umbrella review and meta-regression analysis
L. Goodfellow, G. T. B. Young, E. van Leeuwen +4
medRxiv8 Oct 2026PreprintCC BY-NCFull textEpidemiology & public healthmedRxiv
Scalable Causal-Interpretable Machine Learning for Cancer Prescreening Using Electronic Health Records
S. Zhang, F. Xue
medRxiv21 Sep 2026PreprintAll rights reservedFull textEpidemiology & public healthmedRxiv

Cite

BibTeX RIS

BibTeX

@article{ferguson2026introduction,
  title = {{Introduction to using symbolic regression for interpretable machine learning in healthcare}},
  author = {Michael Ferguson and Feifan Liu and Honghuang Lin and David D. McManus and Ben S. Gerber},
  journal = {Communications Medicine},
  year = {2026},
  month = oct,
  doi = {10.1038/s43856-026-01914-x},
  url = {https://www.nature.com/articles/s43856-026-01914-x},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - Introduction to using symbolic regression for interpretable machine learning in healthcare
AU  - Michael Ferguson
AU  - Feifan Liu
AU  - Honghuang Lin
AU  - David D. McManus
AU  - Ben S. Gerber
PY  - 2026
DA  - 2026/10/09
JO  - Communications Medicine
DO  - 10.1038/s43856-026-01914-x
UR  - https://www.nature.com/articles/s43856-026-01914-x
AB  - The past decade has seen machine learning play an increasingly important role in medicine. However, many of the state-of-the-art models being developed and deployed suffer from a lack of transparency, limiting integration into the clinical decision-making process and raising concerns about patient safety. Here we call attention to symbolic regression, a largely overlooked machine learning technique that aims to be both accurate and interpretable by learning readable mathematical models from data. In recent years, it has undergone rapid advancements with successful application to problems across a wide range of disciplines. In this perspective, we provide an approachable introduction to symbolic regression, highlight its strengths and limitations, and explore its potential applications in medicine.
SN  - 2730-664X
ER  -

Abstract

Related

Cite