@article{2fe52b0bf3fc4fbabe2bbd3fc76bdf27,
title = "Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes",
abstract = "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.",
keywords = "cognition, deep learning, diffusion tensor imaging, general psychopathology, structural connectomes",
author = "Yeung, {Hon Wah} and Aleks Stolicyn and Buchanan, {Colin R.} and Tucker-Drob, {Elliot M.} and Bastin, {Mark E.} and Saturnino Luz and McIntosh, {Andrew M.} and Whalley, {Heather C.} and Cox, {Simon R.} and Keith Smith",
note = "Funding Information: This study was supported by Wellcome Trust awards (References 104036/Z/14/Z; 220857/Z/20/Z), and Colin R. Buchanan, Elliot M. Tucker‐Drob, Mark E. Bastin and Simon R. Cox were also supported by the National Institutes of Health (NIH) research grant R01AG054628. The research was conducted using the UK Biobank resource, with approved project number 10279. Structural brain imaging data from UK Biobank was processed using facilities within the Lothian Birth Cohort group at the University of Edinburgh, which is supported by Age UK (as The Disconnected Mind project), the Medical Research Council (MR/R024065/1) and the University of Edinburgh. This work has made use of the resources provided by the Edinburgh Compute and Data Facility (ECDF). The Population Research Center (PRC) and Center on Aging and Population Sciences (CAPS) at The University of Texas at Austin are supported by the National Institutes of Health (NIH) grants P2CHD042849 and P30AG066614, respectively. Keith Smith was supported by Health Data Research UK, an initiative funded by UK Research and Innovation Councils, NIH Research (England) and the UK devolved administrations, and leading medical research charities. Simon R. Cox was also supported by a Sir Henry Dale Fellowship jointly funded by the Wellcome Trust and the Royal Society (221890/Z/20/Z). Andrew M. McIntosh and Heather C. Whalley are additionally supported by a UKRI award (Reference MC_PC_17209). Funding Information: Medical Research Council, Grant/Award Number: MR/R024065/1; National Institutes of Health, Grant/Award Numbers: P2CHD042849, P30AG066614, R01AG054628; UK Research and Innovation, Grant/Award Number: MC_PC_17209; Wellcome Trust, Grant/Award Numbers: 104036/Z/14/Z, 220857/Z/20/Z, 221890/Z/20/Z Funding information Publisher Copyright: {\textcopyright} 2022 The Authors. Human Brain Mapping published by Wiley Periodicals LLC.",
year = "2023",
month = apr,
day = "1",
doi = "10.1002/hbm.26182",
language = "English",
volume = "44",
pages = "1913--1933",
journal = "Human Brain Mapping",
issn = "1065-9471",
publisher = "Wiley-Liss Inc.",
number = "5",
}