A systematic review of artificial intelligence techniques based on electroencephalography analysis in the diagnosis...

In recent years, Artificial Intelligence (AI), with a specific emphasis on attention mechanisms instead of conventional Deep Learning (DL) or Machine Learning (ML), has demonstrated significant applicability across diverse medical domains. This paper redirects its focus from general brain mapping techniques to specifically investigate the impact of AI in the field of epilepsy diagnosis, concentrating exclusively on Electroencephalography (EEG) data. While earlier studies have predominantly centered on the automatic identification and prediction of seizures using EEG records, an emerging body of research delves into the potential of AI techniques to enhance the analysis of EEG data. This systematic review offers a comprehensive overview, commencing with a concise theoretical exposition on Artificial Neural Networks (ANNs) and attention mechanisms. Subsequent sections explore the applications of AI in EEG analysis for epilepsy, covering aspects such as diagnosis, lateralization, automated lesion detection, presurgical evaluation, and the prediction of postsurgical outcomes. The discussion not only highlights the promising aspects of AI in refining clinical practices but also underscores its potential in tailoring individualized treatments for epilepsy, considering it as a network disorder. The paper concludes by addressing limitations, challenges, and proposing future directions for the application of AI in epilepsy research. While acknowledging the transformative potential of this approach, it emphasizes the necessity for greater multicenter collaboration to amass high-quality data and ensure the open accessibility of developed codes and tools. Moreover, the application of AI models in Computer-Aided Diagnosis (CAD) has exhibited significant promise in enhancing the accuracy and efficiency of epilepsy and seizure diagnosis. This integration of advanced technologies contributes to the development of robust tools for clinical decision-making and underscores the potential for AI-driven solutions in neurological healthcare.