In:
PLOS Biology, Public Library of Science (PLoS), Vol. 18, No. 12 ( 2020-12-7), p. e3000966-
Abstract:
Many studies have highlighted the difficulty inherent to the clinical application of fundamental neuroscience knowledge based on machine learning techniques. It is difficult to generalize machine learning brain markers to the data acquired from independent imaging sites, mainly due to large site differences in functional magnetic resonance imaging. We address the difficulty of finding a generalizable marker of major depressive disorder (MDD) that would distinguish patients from healthy controls based on resting-state functional connectivity patterns. For the discovery dataset with 713 participants from 4 imaging sites, we removed site differences using our recently developed harmonization method and developed a machine learning MDD classifier. The classifier achieved an approximately 70% generalization accuracy for an independent validation dataset with 521 participants from 5 different imaging sites. The successful generalization to a perfectly independent dataset acquired from multiple imaging sites is novel and ensures scientific reproducibility and clinical applicability.
Type of Medium:
Online Resource
ISSN:
1545-7885
DOI:
10.1371/journal.pbio.3000966
DOI:
10.1371/journal.pbio.3000966.g001
DOI:
10.1371/journal.pbio.3000966.g002
DOI:
10.1371/journal.pbio.3000966.g003
DOI:
10.1371/journal.pbio.3000966.g004
DOI:
10.1371/journal.pbio.3000966.g005
DOI:
10.1371/journal.pbio.3000966.t001
DOI:
10.1371/journal.pbio.3000966.s001
DOI:
10.1371/journal.pbio.3000966.s002
DOI:
10.1371/journal.pbio.3000966.s003
DOI:
10.1371/journal.pbio.3000966.s004
DOI:
10.1371/journal.pbio.3000966.s005
DOI:
10.1371/journal.pbio.3000966.s006
DOI:
10.1371/journal.pbio.3000966.s007
DOI:
10.1371/journal.pbio.3000966.s008
DOI:
10.1371/journal.pbio.3000966.s009
DOI:
10.1371/journal.pbio.3000966.s010
DOI:
10.1371/journal.pbio.3000966.s011
DOI:
10.1371/journal.pbio.3000966.s012
DOI:
10.1371/journal.pbio.3000966.s013
DOI:
10.1371/journal.pbio.3000966.s014
DOI:
10.1371/journal.pbio.3000966.s015
DOI:
10.1371/journal.pbio.3000966.s016
DOI:
10.1371/journal.pbio.3000966.s017
DOI:
10.1371/journal.pbio.3000966.s018
DOI:
10.1371/journal.pbio.3000966.s019
DOI:
10.1371/journal.pbio.3000966.s020
DOI:
10.1371/journal.pbio.3000966.r001
DOI:
10.1371/journal.pbio.3000966.r002
DOI:
10.1371/journal.pbio.3000966.r003
DOI:
10.1371/journal.pbio.3000966.r004
DOI:
10.1371/journal.pbio.3000966.r005
DOI:
10.1371/journal.pbio.3000966.r006
Language:
English
Publisher:
Public Library of Science (PLoS)
Publication Date:
2020
detail.hit.zdb_id:
2126773-X
Bookmarklink