AUTHOR=Steardo Luca , Carbone Elvira Anna , de Filippis Renato , Pisanu Claudia , Segura-Garcia Cristina , Squassina Alessio , De Fazio Pasquale , Steardo Luca 

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

JOURNAL=Frontiers in Psychiatry

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/psychiatry/articles/10.3389/fpsyt.2020.00588

DOI=10.3389/fpsyt.2020.00588

ISSN=1664-0640

ABSTRACT=Non-invasive measurements of brain function and structure in patients with mental illnesses, such as neuroimaging, are useful and powerful tools for studying discriminatory biomarkers. To date, functional MRI (fMRI), and morphostructural MRI (sMRI) represent the techniques more frequently used to provide multiple perspective on brain function, structure, and its connectivity. There has been growing interest in using machine‐learning (ML) techniques and pattern recognition methods applied to neuroimaging data. These approaches aim at characterizing disease related alterations in brain structure and functioning and identifying phenotypes useful for early diagnosis. The current review aim is to summarize the evidence supporting the potential of Support Vector Machine (SVM) techniques in making diagnostic discrimination in patients with schizophrenia (SCZ) from healthy controls using as input neuroimaging data from fMRI. We identified 660 papers, of which 22 were included in this systematic review after the screening process. This technique can be a valid, cheap and non-invasive support for physicians to detect patients, even in the early stage of the disorder, conferring an important clinical advantage. It is possible to hypothesize that the greater accuracy demonstrated by the SVM models and new integrated methods of ML techniques could be increasingly crucial in the future for an early diagnosis and a prompt evaluation of treatment response as well as to establish the prognosis of patients with SCZ.