A neurological event characterized by excessive, and synchronized electrical discharges in the brain, often leading to temporary alterations in behavior, sensation, or consciousness is termed as epileptic seizure. This chapter particularly presents a comparative study of different machine learning models for detecting epileptic seizures using electroencephalography (EEG) and electromyography (EMG) data. It is found that the model trained on both EEG and EMG data combined showed higher accuracy relative to those trained on either modality independently. The chapter also briefly describes results from feature extraction performed in both time and frequency domain, and their inference with regards to the differentiation between EEG and EMG patterns in both epileptic patient and control group. The classification accuracy using Random Forest model with the combination of EEG and EMG features showed the highest accuracy rate of 90% as compared to only EEG (80.33%) and only EMG feature (77.44%). The integration of EEG and EMG data with machine learning techniques holds promise for advancing epilepsy diagnosis and management. However, ongoing research is necessary to refine the model's performance, validate its clinical efficacy, and ensure seamless integration into existing healthcare workflows.