Application of Support Vector Machine on fMRI Data as Biomarkers in Schizophrenia Diagnosis: A Systematic Review

Steardo, Luca; Carbone, Elvira Anna; Filippis, Renato de; Pisanu, Claudia; Segura-Garcìa, Cristina; Squassina, Alessio; Fazio, Pasquale De

doi:10.3389/fpsyt.2020.00588

Cited by 85 publications

(54 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Diagnosis of schizophrenia is clinically dependent on psychiatric examinations since biomarkers that could accurately classify schizophrenia remain unknown [ 15 , 29 ]. Machine learning algorithms associated with neuroimaging features provide a promising way for schizophrenia diagnosis [ 18 ]. To date, machine learning algorithms including SVM, RF, KNN, FNN, and deep learning algorithms associated with fMRI and sMRI features have been used in schizophrenia diagnosis [ 17 , 18 ].…”

Section: Discussionmentioning

confidence: 99%

“…Machine learning algorithms associated with neuroimaging features provide a promising way for schizophrenia diagnosis [ 18 ]. To date, machine learning algorithms including SVM, RF, KNN, FNN, and deep learning algorithms associated with fMRI and sMRI features have been used in schizophrenia diagnosis [ 17 , 18 ]. The performance of machine learning algorithms varied from 70% to 90% in terms of accuracy and from 0.54 to 0.95 in terms of AUC [ 17 ].…”

Section: Discussionmentioning

confidence: 99%

“…In this study, LIBSVM toolbox based on the MATLAB platform was used to implement SVM classifier [ 27 , 28 ]. Linear SVM has been widely applied in multivariate pattern analysis due to its high accuracy, generalization, and interpretability [ 15 , 17 , 18 ]. Therefore, in this study, linear kernel was selected.…”

Section: Methodsmentioning

confidence: 99%

“…Cao et al achieved classification of schizophrenia patients with combined analysis of single nucleotide polymorphisms and fMRI data based on sparse representation [ 16 ]. Recent studies have reviewed MRI-based machine learning methods for classification of schizophrenia and have found that the performance of machine learning methods for schizophrenia classification varied from 0.54 to 0.95 in terms of area under the curve (AUC) [ 17 , 18 ]. The machine learning algorithms used for classification included SVM, neural network, k-nearest neighbors (KNN), random forest (RF), etc.…”

Section: Introductionmentioning

confidence: 99%

“…The machine learning algorithms used for classification included SVM, neural network, k-nearest neighbors (KNN), random forest (RF), etc. [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions

Guo

Qiu

2020

Brain Sciences

View full text Add to dashboard Cite

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.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The machine learning algorithms used for classification included SVM, neural network, k-nearest neighbors (KNN), random forest (RF), etc. [ 17 , 18 ].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions

Guo

Qiu

2020

Brain Sciences

View full text Add to dashboard Cite

show abstract

Role of serum cytokines in the prediction of heart failure in patients with coronary artery disease

Hou,

Sun,

Zhao

et al. 2023

ESC Heart Failure

View full text Add to dashboard Cite

AimsCoronary artery disease (CAD) is the most common cause of heart failure (HF). This study aimed to identify cytokine biomarkers for predicting HF in patients with CAD.Methods and resultsTwelve patients with CAD without HF (CAD‐non HF), 12 patients with CAD complicated with HF (CAD‐HF), and 12 healthy controls were enrolled for Human Cytokine Antibody Array, which were used as the training dataset. Then, differentially expressed cytokines among the different groups were identified, and crucial characteristic proteins related to CAD‐HF were screened using a combination of the least absolute shrinkage and selection operator, recursive feature elimination, and random forest methods. A support vector machine (SVM) diagnostic model was constructed based on crucial characteristic proteins, followed by receiver operating characteristic curve analysis. Finally, two validation datasets, GSE20681 and GSE59867, were downloaded to verify the diagnostic performance of the SVM model and expression of crucial proteins, as well as enzyme‐linked immunosorbent assay was also used to verify the levels of crucial proteins in blood samples. In total, 12 differentially expressed proteins were overlapped in the three comparison groups, and then four optimal characteristic proteins were identified, including VEGFR2, FLRG, IL‐23, and FGF‐21. After that, the area under the receiver operating characteristic curve of the constructed SVM classification model for the training dataset was 0.944. The accuracy of the SVM classification model was validated using the GSE20681 and GSE59867 datasets, with area under the receiver operating characteristic curve values of 0.773 and 0.745, respectively. The expression trends of the four crucial proteins in the training dataset were consistent with those in the validation dataset and those determined by enzyme‐linked immunosorbent assay.ConclusionsThe combination of VEGFR2, FLRG, IL‐23, and FGF‐21 can be used as a candidate biomarker for the prediction and prevention of HF in patients with CAD.

show abstract

A multimodal vision transformer for interpretable fusion of functional and structural neuroimaging data

Bi,

Abrol,

et al. 2024

Human Brain Mapping

View full text Add to dashboard Cite

Multimodal neuroimaging is an emerging field that leverages multiple sources of information to diagnose specific brain disorders, especially when deep learning‐based AI algorithms are applied. The successful combination of different brain imaging modalities using deep learning remains a challenging yet crucial research topic. The integration of structural and functional modalities is particularly important for the diagnosis of various brain disorders, where structural information plays a crucial role in diseases such as Alzheimer's, while functional imaging is more critical for disorders such as schizophrenia. However, the combination of functional and structural imaging modalities can provide a more comprehensive diagnosis. In this work, we present MultiViT, a novel diagnostic deep learning model that utilizes vision transformers and cross‐attention mechanisms to effectively fuse information from 3D gray matter maps derived from structural MRI with functional network connectivity matrices obtained from functional MRI using the ICA algorithm. MultiViT achieves an AUC of 0.833, outperforming both our unimodal and multimodal baselines, enabling more accurate classification and diagnosis of schizophrenia. In addition, using vision transformer's unique attentional maps in combination with cross‐attentional mechanisms and brain function information, we identify critical brain regions in 3D gray matter space associated with the characteristics of schizophrenia. Our research not only significantly improves the accuracy of AI‐based automated imaging diagnostics for schizophrenia, but also pioneers a rational and advanced data fusion approach by replacing complex, high‐dimensional fMRI information with functional network connectivity, integrating it with representative structural data from 3D gray matter images, and further providing interpretative biomarker localization in a 3D structural space.

show abstract

Application of Support Vector Machine on fMRI Data as Biomarkers in Schizophrenia Diagnosis: A Systematic Review

Cited by 85 publications

References 45 publications

Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions

Support Vector Machine-Based Schizophrenia Classification Using Morphological Information from Amygdaloid and Hippocampal Subregions

Role of serum cytokines in the prediction of heart failure in patients with coronary artery disease

A multimodal vision transformer for interpretable fusion of functional and structural neuroimaging data

Contact Info

Product

Resources

About