Evaluating the performance of machine learning models for automatic diagnosis of patients with schizophrenia based on a single site dataset of 440 participants

Keyphrases

• Support Vector Machine 100%
• Evaluating Performance 100%
• Patients with Schizophrenia 100%
• Machine Learning Models 100%
• Automatic Diagnosis 100%
• Training Sample Size 37%
• Classification Accuracy 25%
• Incremental Training 25%
• Single-subject Prediction 25%
• Healthy Controls 12%
• Large Sample Size 12%
• High Classification Accuracy 12%
• Model Accuracy 12%
• Automatic Classification 12%
• Linear Support Vector Machine 12%
• Functional Connectivity 12%
• Establish Model 12%
• Female Participants 12%
• Schizophrenia 12%
• Small Sample Size 12%
• Older Participants 12%
• Resting-state Functional Magnetic Resonance Imaging (rs-fMRI) 12%
• Female-to-male 12%
• Nested Cross-validation 12%
• Heterogeneous Properties 12%

Psychology

• Learning Model 100%
• Schizophrenia 100%
• Cross-Validation 25%
• Functional Magnetic Resonance Imaging 25%
• Functional Connectivity 25%

Neuroscience

• Support Vector Machine 100%
• Functional Magnetic Resonance Imaging 11%
• Functional Connectivity 11%