Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes

Tools

Yeung, Hon Wah and Stolicyn, Aleks and Buchanan, Colin R. and Tucker-Drob, Elliot M. and Bastin, Mark E. and Luz, Saturnino and McIntosh, Andrew M. and Whalley, Heather C. and Cox, Simon R. and Smith, Keith (2023) Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes. Human Brain Mapping, 44 (5). pp. 1913-1933. ISSN 1065-9471 (https://doi.org/10.1002/hbm.26182)

[thumbnail of Yeung-etal-HBM-2023-Predicting-sex-age-general-cognition-and-mental-health-with-machine-learning-on-brain-structural-connectomes]
Preview
 Text. Filename: Yeung-etal-HBM-2023-Predicting-sex-age-general-cognition-and-mental-health-with-machine-learning-on-brain-structural-connectomes.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (5MB)| Preview

Abstract

There is an increasing expectation that advanced, computationally expensive machine learning (ML) techniques, when applied to large population-wide neuroimaging datasets, will help to uncover key differences in the human brain in health and disease. We take a comprehensive approach to explore how multiple aspects of brain structural connectivity can predict sex, age, general cognitive function and general psychopathology, testing different ML algorithms from deep learning (DL) model (BrainNetCNN) to classical ML methods. We modelled N = 8183 structural connectomes from UK Biobank using six different structural network weightings obtained from diffusion MRI. Streamline count generally provided the highest prediction accuracies in all prediction tasks. DL did not improve on prediction accuracies from simpler linear models. Further, high correlations between gradient attribution coefficients from DL and model coefficients from linear models suggested the models ranked the importance of features in similar ways, which indirectly suggested the similarity in models' strategies for making predictive decision to some extent. This highlights that model complexity is unlikely to improve detection of associations between structural connectomes and complex phenotypes with the current sample size.

ORCID iDs

Yeung, Hon Wah, Stolicyn, Aleks, Buchanan, Colin R., Tucker-Drob, Elliot M., Bastin, Mark E., Luz, Saturnino, McIntosh, Andrew M., Whalley, Heather C., Cox, Simon R. and Smith, Keith ORCID logoORCID: https://orcid.org/0000-0002-4615-9020;
CORE (COnnecting REpositories)