Machine learning for post‐traumatic stress disorder identification utilizing resting‐state functional magnetic resonance imaging

• Published in: Microscopy research and technique Vol. 85; no. 6; pp. 2083 - 2094
• Main Authors: Saba, Tanzila, Rehman, Amjad, Shahzad, Mirza Naveed, Latif, Rabia, Bahaj, Saeed Ali, Alyami, Jaber
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.06.2022; Wiley Subscription Services, Inc
• Subjects: Algorithms; Brain; Brain - diagnostic imaging; Brain - pathology; Brain cancer; Brain mapping; Brain Mapping - methods; brain tumor; functional connectivity; Functional magnetic resonance imaging; healthcare; human & diseases; Humans; Kernel functions; Learning algorithms; Machine Learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Neural networks; Neuroimaging; Patients; Polynomials; Post traumatic stress disorder; Psychological stress; Radial basis function; resting‐state functional magnetic resonance imaging; Stress Disorders, Post-Traumatic - diagnostic imaging; Stress Disorders, Post-Traumatic - pathology; Support Vector Machine; Support vector machines; Variance analysis; resting-state functional magnetic resonance imaging; human & diseases; brain tumor; post-traumatic stress disorder; functional connectivity; healthcare
• ISSN: 1059-910X; 1097-0029; 1097-0029
• DOI: 10.1002/jemt.24065

Early detection of post‐traumatic stress disorder (PTSD) is essential for proper treatment of the patients to recover from this disorder. The aligned purpose of this study was to investigate the performance deviations in regions of interest (ROI) of PTSD than the healthy brain regions, to assess interregional functional connectivity and applications of machine learning techniques to identify PTSD and healthy control using resting‐state functional magnetic resonance imaging (rs‐fMRI). The rs‐fMRI data of 10 ROI was extracted from 14 approved PTSD subjects and 14 healthy controls. The rs‐fMRI data of the selected ROI were used in ANOVA to measure performance level and Pearson's correlation to investigate the interregional functional connectivity in PTSD brains. In machine learning approaches, the logistic regression, K‐nearest neighbor (KNN), support vector machine (SVM) with linear, radial basis function, and polynomial kernels were used to classify the PTSD and control subjects. The performance level in brain regions of PTSD deviated as compared to the regions in the healthy brain. In addition, significant positive or negative functional connectivity was observed among ROI in PTSD brains. The rs‐fMRI data have been distributed in training, validation, and testing group for maturity, implementation of machine learning techniques. The KNN and SVM with radial basis function kernel were outperformed for classification among other methods with high accuracies (96.6%, 94.8%, 98.5%) and (93.7%, 95.2%, 99.2%) to train, validate, and test datasets, respectively. The study's findings may provide a guideline to observe performance and functional connectivity of the brain regions in PTSD and to discriminate PTSD subject using only the suggested algorithms. Comparison of the performance in the brain regions‐of‐interest (hippocampus, amygdala, precuneus, medial prefrontal cortex, and thalamus) of PTSD than the healthy brain regions, interregional functional connectivity in the regions‐of‐interest, and applications of machine learning techniques to identify PTSD and healthy control using rs‐fMRI data. Highlights Machine learning techniques are applied to identify cancerous patients utilizing resting‐state fMRI data. Among several MLAs, the SVM‐RBF performed a better prediction rate at higher reliability than other competitive models.