Comprehensive Review of Machine Learning Approaches for Analysing EEG-Based Neurological Disorders

Electroencephalography is a fast, inexpensive and non-invasive technology for analysing neurological disorders. Neurological disorders have a profound impact on the Autonomic Nervous System and the brain significantly influencing individual’s health and well-being. This review focuses on the analysis of EEG signals related to three significant neurological disorders: Alzheimer’s disease (AD), Parkinson’s disease (PD), and Epilepsy. The EEG parameters serve as potential markers for cognitive status in these disorders. Since the inspection of large amount of EEG by neurologist is time-consuming and inconsistent so the machine learning algorithms have made significant strides in identifying unique EEG patterns associated with each disorder which not only enables early diagnosis and timely preventive interventions but also helps to develop personalized treatment strategies. This review delves into the process of analysing EEG signals and integrating machine learning and deep learning algorithms for robust classification of neurological disorders. In addition, it intends to provide a comprehensive overview of the modern advancements in using EEG and ML for improved diagnosis and potential treatment monitoring of PD, AD, and epilepsy.