Using Minimal-Redundant and Maximal-Relevant Whole-Brain Functional Connectivity to Classify Bipolar Disorder

Frontiers in Neuroscience

Yu-Te Wu¹  Tung-Ping Su³  Mu-Hong Chen⁵  Ya-Mei Bai⁵  Yen-Ling Chen⁶  Tzu-Hsuan Huang⁶  Pei-Chi Tu⁷ 

[1] Brain Research Center, National Yang-Ming University, Taipei, Taiwan;Department of Medical Research and Education, Taipei Veterans General Hospital, Taipei, Taiwan;Department of Psychiatry, Cheng-Hsin General Hospital, Taipei, Taiwan;Department of Psychiatry, Taipei Veterans General Hospital, Taipei, Taiwan;Division of Psychiatry, Faculty of Medicine, National Yang-Ming University, Taipei, Taiwan;Institute of Biophotonics, National Yang-Ming University, Taipei, Taiwan;Institute of Philosophy of Mind and Cognition, National Yang-Ming University, Taipei, Taiwan;

关键词: classification;    bipolar disorder;    functional connectivity;    feature selection;    machine learning;   

DOI  :  10.3389/fnins.2020.563368

来源: DOAJ

【 摘 要 】

BackgroundA number of mental illness is often re-diagnosed to be bipolar disorder (BD). Furthermore, the prefronto-limbic-striatal regions seem to be associated with the main dysconnectivity of BD. Functional connectivity is potentially an appropriate objective neurobiological marker that can assist with BD diagnosis.MethodsHealth controls (HC; n = 173) and patients with BD who had been diagnosed by experienced physicians (n = 192) were separated into 10-folds, namely, a ninefold training set and a onefold testing set. The classification involved feature selection of the training set using minimum redundancy/maximum relevance. Support vector machine was used for training. The classification was repeated 10 times until each fold had been used as the testing set.ResultsThe mean accuracy of the 10 testing sets was 76.25%, and the area under the curve was 0.840. The selected functional within-network/between-network connectivity was mainly in the subcortical/cerebellar regions and the frontoparietal network. Furthermore, similarity within the BD patients, calculated by the cosine distance between two functional connectivity matrices, was smaller than between groups before feature selection and greater than between groups after the feature selection.LimitationsThe major limitations were that all the BD patients were receiving medication and that no independent dataset was included.ConclusionOur approach effectively separates a relatively large group of BD patients from HCs. This was done by selecting functional connectivity, which was more similar within BD patients, and also seems to be related to the neuropathological factors associated with BD.

【 授权许可】

Unknown