 Epilepsy is a common neurological disorder characterized by recurring seizures. Traditional EEG monitoring is the gold standard for diagnosis, but it can be inconvenient, uncomfortable, and ineffective for patients. Additionally, EEG monitoring over a short period of time may not provide accurate results due to varying patient tolerance and seizure frequency. Limited hospital resources and hardware or software specifications limit the options for comfortable, long-term data collection, which limits the amount of data available for training machine learning models. This review provides an overview of current EEG monitoring practices, as well as opportunities for improved data reliability through multimodal data fusion. Future research should focus on reducing the number of electrodes used during EEG monitoring to make the process more portable, reliable, and efficient. This article was authored by Christina Mayer, Ikai Young, Nandue Trung, and others. We are article.tv, links in the description below.