Support vector machine-based classification of first episode drug-naïve schizophrenia patients and healthy controls using structural MRI

Structural changes in the hippocampus and amygdala have been demonstrated in schizophrenia patients. However, whether morphological information from these subcortical regions could be used by machine learning algorithms for schizophrenia classification were unknown. The aim of this study was to use volume of the amygdaloid and hippocampal subregions for schizophrenia classification. The dataset consisted of 57 patients with schizophrenia and 69 healthy controls. The volume of 26 hippocampal and 20 amygdaloid subregions were extracted from T1 structural MRI images. Sequential backward elimination (SBE) algorithm was used for feature selection, and a linear support vector machine (SVM) classifier was configured to explore the feasibility of hippocampal and amygdaloid subregions in the classification of schizophrenia. The proposed SBE-SVM model achieved a classification accuracy of 81.75% on 57 patients and 69 healthy controls, with a sensitivity of 84.21% and a specificity of 81.16%. AUC was 0.8241 (p < 0.001 tested with 1000-times permutation). The results demonstrated evidence of hippocampal and amygdaloid structural changes in schizophrenia patients, and also suggested that morphological features from the amygdaloid and hippocampal subregions could be used by machine learning algorithms for the classification of schizophrenia.

Download Full-text

O4-07-04: Support vector machine-based classification of 18F-flutemetamol scans in Alzheimer's disease, MCI and controls: comparison with visual reads and structural MRI-based classification

Alzheimer s & Dementia ◽

10.1016/j.jalz.2011.05.2015 ◽

2011 ◽

Vol 7 ◽

pp. S697-S697

Author(s):

Rik Vandenberghe ◽

Natalie Nelissen ◽

Koen Van Laere ◽

Lennart Thurfjell ◽

Chris Buckley ◽

...

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Support Vector Machine ◽

Structural Mri ◽

Support Vector

Download Full-text

Abnormal neural activity as a potential biomarker for drug-naive first-episode adolescent-onset schizophrenia with coherence regional homogeneity and support vector machine analyses

Schizophrenia Research ◽

10.1016/j.schres.2017.04.028 ◽

2018 ◽

Vol 192 ◽

pp. 408-415 ◽

Cited By ~ 19

Author(s):

Yi Liu ◽

Yan Zhang ◽

Luxian Lv ◽

Renrong Wu ◽

Jingping Zhao ◽

...

Keyword(s):

Support Vector Machine ◽

Neural Activity ◽

Regional Homogeneity ◽

First Episode ◽

Support Vector ◽

Potential Biomarker ◽

Drug Naïve

Download Full-text

Ensemble support vector machine classification of dementia using structural MRI and mini-mental state examination

Journal of Neuroscience Methods ◽

10.1016/j.jneumeth.2018.01.003 ◽

2018 ◽

Vol 302 ◽

pp. 66-74 ◽

Cited By ~ 18

Author(s):

Lauge Sørensen ◽

Mads Nielsen

Keyword(s):

Support Vector Machine ◽

Mental State ◽

Mini Mental State Examination ◽

Structural Mri ◽

Support Vector ◽

Support Vector Machine Classification ◽

State Examination

Download Full-text

Classification of first-episode psychosis in a large cohort of patients using support vector machine and multiple kernel learning techniques

NeuroImage ◽

10.1016/j.neuroimage.2015.12.007 ◽

2017 ◽

Vol 145 ◽

pp. 238-245 ◽

Cited By ~ 32

Author(s):

Letizia Squarcina ◽

Umberto Castellani ◽

Marcella Bellani ◽

Cinzia Perlini ◽

Antonio Lasalvia ◽

...

Keyword(s):

Support Vector Machine ◽

Multiple Kernel Learning ◽

First Episode Psychosis ◽

Kernel Learning ◽

First Episode ◽

Support Vector ◽

Multiple Kernel ◽

Learning Techniques ◽

Episode Psychosis

Download Full-text

Abnormal Fractional Amplitude of Low-Frequency Fluctuation as a Potential Imaging Biomarker for First-Episode Major Depressive Disorder: A Resting-State fMRI Study and Support Vector Machine Analysis

Frontiers in Neurology ◽

10.3389/fneur.2021.751400 ◽

2021 ◽

Vol 12 ◽

Author(s):

Yujun Gao ◽

Xi Wang ◽

Zhenying Xiong ◽

Hongwei Ren ◽

Ruoshi Liu ◽

...

Keyword(s):

Support Vector Machine ◽

Major Depressive Disorder ◽

Resting State ◽

Low Frequency ◽

Diagnostic Value ◽

First Episode ◽

Support Vector ◽

Healthy Controls ◽

Major Depressive ◽

The Right

Objective: Major depressive disorder (MDD) is a psychiatric disorder with serious negative health outcomes; however, there is no reliable method of diagnosis. This study explored the clinical diagnostic value of the fractional amplitude of low-frequency fluctuation (fALFF) based on the support vector machine (SVM) method for the diagnosis of MDD.Methods: A total of 198 first-episode MDD patients and 234 healthy controls were involved in this study, and all participants underwent resting-state functional magnetic resonance imaging (fMRI) scanning. Imaging data were analyzed with the fALFF and SVM methods.Results: Compared with the healthy controls, the first-episode MDD patients showed higher fALFF in the left mid cingulum, right precuneus, and left superior frontal gyrus (SFG). The increased fALFF in these three brain regions was positively correlated with the executive control reaction time (ECRT), and the increased fALFF in the left mid cingulum and left SFG was positively correlated with the 17-item Hamilton Rating Scale for Depression (HRSD-17) scores. The SVM results showed that increased fALFF in the left mid cingulum, right precuneus, and left SFG exhibited high diagnostic accuracy of 72.92% (315/432), 71.76% (310/432), and 73.84% (319/432), respectively. The highest diagnostic accuracy of 76.39% (330/432) was demonstrated for the combination of increased fALFF in the right precuneus and left SFG, along with a sensitivity of 84.34% (167/198), and a specificity of 70.51% (165/234).Conclusion: Increased fALFF in the left mid cingulum, right precuneus, and left SFG may serve as a neuroimaging marker for first-episode MDD. The use of the increased fALFF in the right precuneus and left SFG in combination showed the best diagnostic value.

Download Full-text