Health AI Central
Peer-Reviewed Publication
Nat Hum Behav2026;10(7):1356-1370.July 1, 2026Journal Article

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

Brendan D Adkinson1, Matthew Rosenblatt2, Huili Sun3, Javid Dadashkarimi4, Link Tejavibulya3, Corey Horien5, Margaret L Westwater6,7, Raimundo X Rodriguez3, Stephanie Noble8,9,10, Dustin Scheinost3,2,6,11,12,13
1Yale School of Medicine, New Haven, CT, USA. brendan.adkinson@yale.edu.
2Department of Biomedical Engineering, Yale University, New Haven, CT, USA.
3Yale School of Medicine, New Haven, CT, USA.
4Department of Radiology, Perelman School of Medicine, Philadelphia, PA, USA.
5Department of Psychiatry, University of Pennsylvania, Philadelphia, PA, USA.
6Department of Radiology & Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA.
7Department of Psychiatry, University of Oxford, Warneford Hospital, Oxford, UK.
8Department of Bioengineering, Northeastern University, Boston, MA, USA.
9Department of Psychology, Northeastern University, Boston, MA, USA.
10Institute for Cognitive & Behavioral Health, Northeastern University, Boston, MA, USA.
11Department of Statistics & Data Science, Yale University, New Haven, CT, USA.
12Child Study Center, Yale School of Medicine, New Haven, CT, USA.
13Wu Tsai Institute, Yale University, New Haven, CT, USA.
PubMed PMC DOI PDF

Abstract

A central objective in human neuroimaging is to understand the neurobiology underlying cognition and mental health. Machine learning models trained on neuroimaging data are increasingly used as tools for predicting behavioural phenotypes, enhancing precision medicine and improving generalizability compared with traditional MRI studies. However, the high dimensionality of brain connectivity data ma…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free AccountSign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.