@article{f8cdaa92483f4ee09c0c12c888dbf74e,
title = "Discriminating Bipolar Disorder from Major Depression using Whole-Brain Functional Connectivity: a Feature Selection Analysis with SVM-FoBa Algorithm",
abstract = "It is known that both bipolar disorder (BD) and major depressive disorder (MDD) can manifest depressive symptoms, especially in the early phase of illness. Therefore, discriminating BD from MDD is a major clinical challenge due to the absence of biomarkers. Feature selection is especially important in neuroimaging applications, yet high feature dimensions, low sample size and poor model understanding present huge challenges. Here we developed an advanced feature selection algorithm, “SVM-FoBa”, which enables adaptive selection of informative feature subsets from high dimensional resting-state functional connectives (rsFC) data. By comparing SVM-FoBa with conventional feature selection methods on several public biomedical data sets, the proposed method was proven to be increasingly superior as the feature dimension became high. When applying SVM-FoBa to brain data, with 38 significant rsFCs chosen from 6670 in total, an 88 % classification accuracy between BD and MDD was achieved using leave-one-out cross-validation. Further, by conducting weight analysis, the most discriminative FCs were revealed, providing which adds to our understanding of functional deficits and may serve as potential biomarkers for mood disorders.",
keywords = "Bipolar disorder, Feature selection, Functional connectivity, Major depression disorder, SVM-FoBa",
author = "Jie, {Nan Feng} and Osuch, {Elizabeth A.} and Zhu, {Mao Hu} and Michael Wammes and Ma, {Xiao Ying} and Jiang, {Tian Zi} and Jing Sui and Calhoun, {Vince D.}",
note = "Funding Information: Acknowledgments This work was partially supported by B100 Talents Plan^ of Chinese Academy of Sciences (to J. Sui); Chinese National Science Foundation No. 81471367, the State High-Tech Development Plan (863), grant No. 2015AA020513 (to J. Sui); and the Strategic Priority Research Program of the Chinese Academy of Sciences, grant No. XDB02060005 (to J. Sui); PhD Research Startup Foundation of Jiangxi Normal University, grant No. 6247 (to M.-H. Zhu); National Institutes of Health grants R01EB006841, and P20GM103472 (to V.D. Calhoun); the Lawson Health Research Institute, grant No. LHR D1374 (to E.A. Osuch); and a Pfizer Independent Investigator Award, grant No. WS2249136 (to E.A. Osuch). Funding Information: This work was partially supported by ?100 Talents Plan? of Chinese Academy of Sciences (to J. Sui); Chinese National Science Foundation No. 81471367, the State High-Tech Development Plan (863), grant No. 2015AA020513 (to J. Sui); and the Strategic Priority Research Program of the Chinese Academy of Sciences, grant No. XDB02060005 (to J. Sui); PhD Research Startup Foundation of Jiangxi Normal University, grant No. 6247 (to M.-H. Zhu); National Institutes of Health grants R01EB006841, and P20GM103472 (to V.D. Calhoun); the Lawson Health Research Institute, grant No. LHR D1374 (to E.A. Osuch); and a Pfizer Independent Investigator Award, grant No. WS2249136 (to E.A. Osuch). Publisher Copyright: {\textcopyright} 2016, Springer Science+Business Media New York.",
year = "2018",
month = feb,
day = "1",
doi = "10.1007/s11265-016-1159-9",
language = "English (US)",
volume = "90",
pages = "259--271",
journal = "Journal of Signal Processing Systems",
issn = "1939-8018",
publisher = "Springer New York",
number = "2",
}