Machine learning detects hidden treatment response patterns only in the presence of comprehensive clinical phenotyping
File(s)
Published version
Author(s)
Auger, Stephen D
Scott, Gregory
Type
Journal Article
Abstract
Inferential statistics traditionally used in clinical trials can miss relationships between clinical phenotypes and treatment responses. We simulated a randomised clinical trial to explore how gradient boosting (XGBoost) machine learning compares with traditional analysis when ‘ground truth’ treatment responsiveness depends on the interaction of multiple phenotypic variables. As expected, traditional analysis detected a significant treatment benefit (outcome measure change from baseline = 4.23; 95% CI 3.64–4.82). However, recommending treatment based upon this evidence would lead to 56.3% of patients failing to respond. In contrast, machine learning correctly predicted treatment response in 97.8% (95% CI 96.6–99.1) of patients, with model interrogation showing the critical phenotypic variables and the values determining treatment response had been identified. Importantly, when a single variable was omitted, accuracy dropped to 69.4% (95% CI 65.3–73.4). This proof of principle underscores the significant potential of machine learning to maximise the insights derived from clinical research studies. However, the effectiveness of machine learning in this context is highly dependent on the comprehensive capture of phenotypic data.
Editor(s)
Wang, Ziheng
Date Issued
2025-10-21
Date Acceptance
2025-10-02
Citation
PLoS ONE, 2025, 20 (10)
ISSN
1932-6203
Publisher
Public Library of Science (PLoS)
Journal / Book Title
PLoS ONE
Volume
20
Issue
10
Copyright Statement
© 2025 Auger, Scott. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
License URL
Identifier
https://www.ncbi.nlm.nih.gov/pubmed/41118359
PII: PONE-D-25-17285
Subjects
ELECTRONIC HEALTH RECORDS
Multidisciplinary Sciences
Science & Technology
Science & Technology - Other Topics
THROMBOLYSIS
TRIALS
Publication Status
Published
Coverage Spatial
United States
Article Number
e0334858
Date Publish Online
2025-10-21