Cells within the brain communicate via electrical impulses and maintain activity even during sleep. When a cell fires, electrical current moves through it. Detection of simultaneous firing of multiple cells by scalp sensors results in observable electrical changes. This exertion appears as crimpy lines on the EEG recording. It serves to measure the brain’s conductivity to electricity. It analyzes the postsynaptic potential in order to identify the activity of a large number of neurons that are active sequentially. This study aims to verify the outcomes of machine learning algorithms based on the idea of training extraction and preparation of EEG data, and to categorize the patient into four disease categories: generalized rhythmic delta activity, lateralized rhythmic discharges, extended periodic discharges, and generalized rhythmic delta and physical activity. Low signal-to-noise ratios, electronics, variations in seizure frequency across epileptic patients, and data scarcity all make it more challenging to classify EEG. The authors have used machine learning algorithms like Gradient Boosting, Hidden Markov Model, AdaBoost, and Logistic Regression to increase the accuracy of the model so that it can predict the diseases up to the topmost efficiency. Therefore, this article reviews the latest techniques for epilepsy techniques and provides researchers with insights and ideas to propose machine learning application of EEG-based seizure technology in the context of rural patient healthcare.