Background: Epilepsy is a neurological disease characterized by seizures which occur due to sudden and synchronized bursts of excessive electrical energy in the brain. An electroencephalogram can detect seizures in real time but requires trained medical expertise for extended periods of time.  The main objective of this research was to devise a more efficient method (SeizureSeeker) for analyzing EEG data using machine learning algorithms that allows for complex data processing and can automatically distinguish between normal EEG signal and epileptic seizures. Methods and Study Design: We used an open access EEG dataset containing de-identified records of 500 patients and used machine learning three classification models including Logistic Regression, Support Vector Machines (SVM) and Long Short-Term Memory (LSTM) to programmatically distinguish between seizure and normal EEG signal. Results: The LSTM classifier provides near perfect results with an accuracy of 99%.  Although the SVM model performed well, the long-term memory characteristic of LSTM makes it the best performer across all evaluation metrics for this type of data. Conclusions: Our research has demonstrated the potential to use complex machine learning classification models such as LSTM to accurately identify seizure activity in EEG data.  Programs such as SeizureSeeker can be developed to reach a diagnoses in a much more timely fashion and can be used around the globe where access to specialized medical expertise is especially limited.