Evaluation of machine learning algorithms performance for the prediction of early multiple sclerosis from resting-state FMRI connectivity data

• Published in: Brain imaging and behavior 2019-08, Vol.13 (4), p.1103-1114
• Main Authors: Saccà, Valeria, Sarica, Alessia, Novellino, Fabiana, Barone, Stefania, Tallarico, Tiziana, Filippelli, Enrica, Granata, Alfredo, Chiriaco, Carmelina, Bruno Bossio, Roberto, Valentino, Paola, Quattrone, Aldo
• Format: Article
• Language: English
• Subjects: Adult; Algorithms; Artificial intelligence; Artificial neural networks; Bayes Theorem; Bayesian analysis; Biomedical and Life Sciences; Biomedicine; Brain; Brain mapping; Classification; Cognition; Connectome - methods; Data processing; Diagnosis; Evaluation; Feature extraction; Female; Forecasting - methods; Functional magnetic resonance imaging; Humans; Independent component analysis; Learning algorithms; Machine Learning; Magnetic Resonance Imaging - methods; Male; Middle Aged; Multiple sclerosis; Multiple Sclerosis - diagnostic imaging; Nearest-neighbor; Neural networks; Neuropsychology; Neuroradiology; Neurosciences; Original Research; Psychiatry; Rest; Sensorimotor integration; Signal classification; Support Vector Machine; Support vector machines
• ISSN: 1931-7557; 1931-7565
• DOI: 10.1007/s11682-018-9926-9

Machine Learning application on clinical data in order to support diagnosis and prognostic evaluation arouses growing interest in scientific community. However, choice of right algorithm to use was fundamental to perform reliable and robust classification. Our study aimed to explore if different kinds of Machine Learning technique could be effective to support early diagnosis of Multiple Sclerosis and which of them presented best performance in distinguishing Multiple Sclerosis patients from control subjects. We selected following algorithms: Random Forest, Support Vector Machine, Naïve-Bayes, K-nearest-neighbor and Artificial Neural Network. We applied the Independent Component Analysis to resting-state functional-MRI sequence to identify brain networks. We found 15 networks, from which we extracted the mean signals used into classification. We performed feature selection tasks in all algorithms to obtain the most important variables. We showed that best discriminant network between controls and early Multiple Sclerosis, was the sensori-motor I, according to early manifestation of motor/sensorial deficits in Multiple Sclerosis. Moreover, in classification performance, Random Forest and Support Vector Machine showed same 5-fold cross-validation accuracies (85.7%) using only this network, resulting to be best approaches. We believe that these findings could represent encouraging step toward the translation to clinical diagnosis and prognosis.