Epilepsy is the fourth most common neurological disorder and affects around 50 million people worldwide. Today diagnosis is based on clinical history, EEG measurements and MRI imaging. However, 50-99% of the MRIs and up to 70% of the EEGs may give negative results, despite an underlying epileptic disorder. Differential diagnosis of epilepsy is further complicated by isolated seizures and other disorders that may give rise to seizure-like symptoms. This amounts to a large number of patients that arrive at the emergency department in whom seizures and epilepsy is suspected. Unfortunately, not more than 50% of these patients are diagnosed appropriately. False diagnosis of epilepsy may lead to patients needlessly taking anti-epileptic drugs and absence of treatment of the undetected disorder that gave rise to the epilepsy-like symptoms. Missed diagnosis on the other hand poses a potentially dangerous situation for the patient in case of subsequent seizures. Since EEG measures brain activity, it's reasonable to assume the functional effects of epilepsy on the brain can be detected through this technique. The high number of false negatives using EEG indicates that the diagnostic information is hidden in the more high-level attributes of the signal. The aim of this study is to develop a software tool that can asses and combine these features, with the help of the functional connectome and artificial intelligence, to increase the diagnostic value of EEG measurements,