سامانه همایش‌ها TSTA | ثبت‌نام و ارسال مقاله کنفرانس‌ها و کنگره‌های ملی

Home / سی و دومین کنفرانس ملی و دهمین کنفرانس بین المللی مهندسی زیست پزشکی ایران

Diagnosis of Multiple Sclerosis Using Recurrence Plot of EEG

Authors :

Neda Baghestani¹ Amin Janghorbani²

1- دانشگاه سمنان 2- دانشگاه سمنان

Keywords :

Electroencephalogram (EEG)،Phase Space Reconstruction،Multiple Sclerosis (MS)،(Recurrence Plot (RP،Recurrence Quantification Analysis (RQA)

Abstract :

Multiple sclerosis (MS) is a chronic disease of the central nervous system, and early diagnosis plays a crucial role in reducing complications and improving patients’ quality of life. This study aims to detect MS using EEG signals. The signals include visual responses from three pathways Magno, Parvo, and Konio and were extracted from 9 occipital channels. From this plot, recurrence quantification analysis (RQA) features were extracted and classified using the Random Forest algorithm. The method’s performance was evaluated using accuracy, sensitivity, specificity, and AUC metrics. Results showed that the Parvo pathway, in O2 and PO3 channels, achieved the best performance with 90.63% accuracy. Sensitivity was 93.75% and 87.50%, specificity was 87.50% and 93.75%, and AUCs were 93% and 89%, respectively. Sensitivity analysis to the parameter ε indicated that proper tuning plays a key role in improving performance. Overall, the RP method, combined with RQA features and appropriate ε selection, provides an effective tool for MS diagnosis.