Abstract—In this study, the problem of discriminating between interictal epileptic and non- epileptic pathological EEG cases, which present episodic loss of consciousness, investigated. We verify the accuracy of the feature extraction method of autocross-correlated coefficients which extracted and studied in previous study. For this purpose we used in one hand a suitable constructed artificial supervised LVQ1 neural network and in other a cross-correlation technique. To enforce the above verification we used a statistical procedure which based on a chi- square control. The classification and the statistical results showed that the proposed feature extraction is a significant accurate method for diagnostic discrimination cases between interictal and non-interictal EEG events and specifically the classification procedure showed that the LVQ neural method is superior than the cross-correlation one. Keywords—Cross-Correlation Methods, Diagnostic Test, Interictal Epileptic, LVQ1 neural network, Auto-Cross-Correlation Methods, chi-square test. I. INTRODUCTION T is known that determining whether a person with "seizures", "spells" or other episodic unusual behaviour, actually has epilepsy presents difficulties. For example episodic loss of consciousness need not signal epilepsy but could result from loss of blood supply to the brain from diseases of the blood vessels or the heart itself. Periodic low blood sugar and certain types of migraine headache may also lead to loss of consciousness [1]. Therefore, Non-Epileptic Events (NEEs) may be due to different organic or non-organic disorders. The diagnosis of Non-Epileptic Attack Disorder (NEAD) involves both exclusion of organic causes of NEEs and elucidation of positive phenomena of this entity [2]. The distinct entity of NEAD does not allude to any specific Manuscript received February 4, 2006. S. Papavlasopoulos, post-graduate, Department of Archives and Library Science, Ionian University. Palaia Anaktora PO Box 96 49100 Corfu Greece (e-mail: sozon@ionio.gr). M. Poulos, Phd, Adjunct Teacher Department of Archives and Library Science, Ionian University. Palaia Anaktora PO Box 96 49100 Corfu Greece (e-mail: mpoulos@ionio.gr http://www.ionio.gr/~mpoulos). G. Bokos, Full Professor, Department of Archives and Library Science, Ionian University. Palaia Anaktora PO Box 96 49100 Corfu Greece (e-mail: gbokos@ionio.gr http://www.ionio.gr/~gbokos ). A. Evangelou, Department of Exp. Physiology, School of Medicine, University of Ioannina. University Campus of Ioannina 45110 Greece (e-mail: evagel@uoi.gr ). psychological mechanism and this term includes a variety of synonyms like Pseudo Epileptic Seizure (PES), psychogenic seizure, pseudo seizure, hysterical seizure, hystero-epilepsy and functional seizure. The subject has recently attained renewed interest as intensive monitoring has diagnosed many cases of refractory seizures (20% or more) as non-epileptic seizures [3]. In the case of Epileptic events, the condition where the brain itself is the cause of periodic spells, the classic diagnostic approach has always been to perform an EEG and search for epileptiform "spikes" or "spike and waves" which may signify epilepsy [4, 5]. Electroencephalography remains a major complex technique in differentiating epilepsy and non-epileptic attacks like NEAD, syncope, narcolepsy, cataplexy, sleep disorders, etc. Proper clinical history and observation of an attack may not be sufficient for diagnosis and, therefore, ictal and postictal EEG, 24 hours ambulatory EEG and video EEG can be of immense help for the purpose. Long term monitoring (LTM) for epilepsy is the technological advancement to improve the yield of EEG data in differentiating Epileptic Seizure (ES) from Non- Epileptic Seizure (NES). LTM includes radio telemetry, cable telemetry and cassette recorders [6]. Suggestion and induction techniques along with simultaneous continuous video-EEG monitoring have been used to differentiate between EE and NEE. These include iv saline infusion, alcohol patch technique and hypnosis and NEEs could be induced in 77- 82% cases [7, 8]. Ideally, an EEG is performed during an actual clinical or "ictal" event during which time runs of epileptiform discharges would be expected. However, ictal events may be few and far between. In practice most epileptics demonstrate epileptiform activity even in-between seizures (interictally). The human eye is the "gold standard" for recognizing epileptiform activity and to distinguish it from artifactual signals and from EEG activity that may mimic epileptiform activity but is benign ("normal variants"). However the unaided human eye cannot efficiently distinguish the specific details of interictal epileptic activity that are valuable regarding a final epileptic diagnosis [4, 5]. Our study [9], a diagnostic testing method used to discriminate between interictal epileptic EEG and non- epileptic pathological EEG events, this method based purely on signal processing and describes an algorithm which is Classification Control for Discrimination between Interictal Epileptic and Non – Epileptic Pathological EEG Events Sozon H. Papavlasopoulos, Marios S. Poulos, George D. Bokos, and Angelos M. Evangelou I International Journal of Biomedical Sciences Volume 1 Number 1 34