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

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 mu...

Full description

Saved in:
Bibliographic Details
Published in:Human brain mapping Vol. 44; no. 5; pp. 1913 - 1933
Main Authors: 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., Smith, Keith
Format: Journal Article
Language:English
Published: Hoboken, USA John Wiley & Sons, Inc 01.04.2023
Subjects:
Accuracy
Algorithms
Brain
Brain - diagnostic imaging
Brain - pathology
Cognition
Cognitive ability
Complexity
Connectome - methods
Decision making
Deep learning
diffusion tensor imaging
general psychopathology
Humans
Learning algorithms
Machine Learning
Magnetic resonance imaging
Mathematical models
Medical imaging
Mental disorders
Mental Health
Neural networks
Neuroimaging
Phenotypes
Predictions
Psychopathology
Sex
Statistical methods
structural connectomes
deep learning
diffusion tensor imaging
cognition
structural connectomes
general psychopathology
ISSN:1065-9471, 1097-0193, 1097-0193
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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. We explore how multiple aspects of brain structural connectivity can predict general cognitive function and general psychopathology. To do this, we modelled six different structural network weightings obtained from diffusion MRI and tested different machine learning (ML) algorithms from deep learning (DL) model (BrainNetCNN) to classical ML methods. DL did not improve on prediction accuracies from simpler linear models, indicating that most of the variation between phenotypes in weighted structural connectomes is linear rather than non‐linear in nature. This may have implied that model complexity is unlikely to improve detection of associations between structural connectomes and complex phenotypes with the current sample size.
Bibliography:Funding information
Heather C. Whalley, Simon R. Cox and Keith Smith contributed equally to senior authorship.
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
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
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
ISSN:1065-9471
1097-0193
1097-0193
DOI:10.1002/hbm.26182