The Development of Machine Learning Method for Analyzing EEG Signals for Diagnosisng Alzheimer Diesease

The prevalence of mental disorders is on the rise in the present era, significantly impacting individuals' lives and overall health. It is crucial to have accurate methods for diagnosing such conditions. Unfortunately, there is currently no specific method developed for predicting Alzheimer's disease. The diagnosis is typically based on clinical data and laboratory tests. Although techniques like genetic biomarkers can be useful, they are expensive and time-consuming. As a result, electroencephalography (EEG) emerges as a valuable technique for Alzheimer's disease diagnosis. This study assesses the efficacy of machine learning algorithms, namely Support Vector Machine (SVM) and Decision Tree, in forecasting Alzheimer's disease based on the analysis of PhysioNet datasets. The accuracy achieved using the Decision Tree algorithm is 60%, while the SVM algorithm achieves an accuracy of 90%.