Differences Between Schizophrenic and Normal Subjects Using Network Properties from fMRI.

Area of Science:

• Neuroscience
• Psychiatry
• Medical Imaging

Background:

• Schizophrenia is a complex mental disorder.
• Functional connectivity impairments are hypothesized to underlie schizophrenia.
• Neuroimaging techniques like fMRI are crucial for studying brain function.

Purpose of the Study:

• To differentiate individuals with schizophrenia from healthy controls using machine learning.
• To identify specific functional connectivity patterns associated with schizophrenia.
• To assess the diagnostic potential of fMRI-derived connectivity metrics.

Main Methods:

• Utilized a publicly available functional MRI (fMRI) dataset.
• Extracted global and local functional connectivity parameters.
• Employed machine learning algorithms, including support vector machine with 10-fold cross-validation.

Main Results:

• Identified decreased global and local network connectivity in schizophrenia subjects.
• Observed significant connectivity differences in specific brain regions: anterior right cingulate cortex, superior right temporal region, and inferior left parietal region.
• Achieved 92.1% prediction accuracy in distinguishing schizophrenia patients from controls using nine selected features.

Conclusions:

• Functional connectivity alterations are significant in schizophrenia.
• fMRI-based analysis of brain activity can effectively distinguish schizophrenia patients from healthy individuals.
• Machine learning models show promise for objective diagnostic tools in schizophrenia research.