English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Population modeling with machine learning can enhance measures of mental health

Dadi, K., Varoquaux, G., Houenou, J., Bzdok, D., Thirion, B., & Engemann, D. A. (2021). Population modeling with machine learning can enhance measures of mental health. GigaScience, 10(10): giab071. doi:10.1093/gigascience/giab071.

Item is

Basic

show hide
Genre: Journal Article

Files

show Files
hide Files
:
Dadi_2022.pdf (Publisher version), 9MB
Name:
Dadi_2022.pdf
Description:
-
OA-Status:
Visibility:
Public
MIME-Type / Checksum:
application/pdf / [MD5]
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Dadi, Kamalaker1, Author
Varoquaux, Gaël1, 2, 3, Author
Houenou, Josselin4, 5, Author
Bzdok, Danilo1, 3, 6, Author
Thirion, Bertrand1, Author
Engemann, Denis A.1, 7, Author           
Affiliations:
1Parietal Team, Neurospin, Institut national de recherche en informatique et en automatique (INRIA), Gif-sur-Yvette, France, ou_persistent22              
2Montreal Neurological Institute and Hospital, McGill University, QC, Canada, ou_persistent22              
3Mila – Quebec Artificial Intelligence Institute, Montréal, QC, Canada, ou_persistent22              
4Neurospin, French Alternative Energies and Atomic Energy Commission (CEA), Saclay, France, ou_persistent22              
5Translational Psychiatry, Hospital Henri Mondor, Créteil, France, ou_persistent22              
6Department of Biomedical Engineering, Douglas Mental Health University Institute, McGill University, Montréal, QC, Canada, ou_persistent22              
7Department Neurology, MPI for Human Cognitive and Brain Sciences, Max Planck Society, ou_634549              

Content

show
hide
Free keywords: Brain imaging; Machine learning; Mental health; Proxy measures; Sociodemographic factors
 Abstract: Background: Biological aging is revealed by physical measures, e.g., DNA probes or brain scans. In contrast, individual differences in mental function are explained by psychological constructs, e.g., intelligence or neuroticism. These constructs are typically assessed by tailored neuropsychological tests that build on expert judgement and require careful interpretation. Could machine learning on large samples from the general population be used to build proxy measures of these constructs that do not require human intervention? Results: Here, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic information from the largest biomedical cohort to date: the UK Biobank. Objective model comparisons revealed that all proxies captured the target constructs and were as useful, and sometimes more useful, than the original measures for characterizing real-world health behavior (sleep, exercise, tobacco, alcohol consumption). We observed this complementarity of proxy measures and original measures at capturing multiple health-related constructs when modeling from, both, brain signals and sociodemographic data. Conclusion: Population modeling with machine learning can derive measures of mental health from heterogeneous inputs including brain signals and questionnaire data. This may complement or even substitute for psychometric assessments in clinical populations.

Details

show
hide
Language(s): eng - English
 Dates: 2021-07-142021-03-102021-09-222021-10-15
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1093/gigascience/giab071
PMID: 34651172
PMC: PMC8559220
 Degree: -

Event

show

Legal Case

show

Project information

show hide
Project name : -
Grant ID : 438531
Funding program : -
Funding organization : Canadian Institutes of Health Research

Source 1

show
hide
Title: GigaScience
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Oxford : Oxford University Press
Pages: - Volume / Issue: 10 (10) Sequence Number: giab071 Start / End Page: - Identifier: ISSN: 2047-217X
CoNE: https://pure.mpg.de/cone/journals/resource/2047-217X