Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers.

Saved in:
Bibliographic Details
Title: Feature selection leads to divergent neurobiological interpretations of brain-based machine learning biomarkers.
Authors: Adkinson BD; Yale School of Medicine, New Haven, CT, USA. brendan.adkinson@yale.edu., Rosenblatt M; Department of Biomedical Engineering, Yale University, New Haven, CT, USA., Sun H; Yale School of Medicine, New Haven, CT, USA., Dadashkarimi J; Department of Radiology, Perelman School of Medicine, Philadelphia, PA, USA., Tejavibulya L; Yale School of Medicine, New Haven, CT, USA., Horien C; Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, USA., Westwater ML; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.; Department of Psychiatry, University of Oxford, Warneford Hospital, Oxford, UK., Rodriguez RX; Yale School of Medicine, New Haven, CT, USA., Noble S; Department of Bioengineering, Northeastern University, Boston, MA, USA.; Department of Psychology, Northeastern University, Boston, MA, USA.; Institute for Cognitive & Behavioral Health, Northeastern University, Boston, MA, USA., Scheinost D; Yale School of Medicine, New Haven, CT, USA.; Department of Biomedical Engineering, Yale University, New Haven, CT, USA.; Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.; Department of Statistics & Data Science, Yale University, New Haven, CT, USA.; Child Study Center, Yale School of Medicine, New Haven, CT, USA.; Wu Tsai Institute, Yale University, New Haven, CT, USA.
Source: Nature human behaviour [Nat Hum Behav] 2026 Apr 15. Date of Electronic Publication: 2026 Apr 15.
Publication Type: Journal Article
Journal Info: Publisher: Springer Nature Publishing Country of Publication: England NLM ID: 101697750 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2397-3374 (Electronic) Linking ISSN: 23973374 NLM ISO Abbreviation: Nat Hum Behav Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:2397-3374
DOI:10.1038/s41562-026-02447-y