NUST Institutions Library Catalogue

Neurological disorders pose major global health challenge, affecting an estimated one
billion individuals worldwide. According to the World Health Organization (WHO), these
neurological disorders contribute to approximately six million deaths annually,
representing a significant burden. Early and accurate identification of brain pathological
features in electroencephalogram (EEG) recordings is important for the diagnosis and
management of these disorders. However, manual interpretation of EEG recordings is not
only time-consuming but also requires expertise. This problem is compounded by the
scarcity of trained neurologists in the healthcare sector, especially in low- and middleincome countries. These limitations emphasize the necessity for automated diagnostic
processes. With the advancement of machine learning algorithms, have sparked significant
interest in automating the process of early diagnoses using EEGs. Therefore, this paper
presents a novel deep learning model consisting of distinct path, Hybrid-CNNTransformer, for the automatic detection of abnormal raw EEG data. Through multiple
ablation studies, we demonstrated the effectiveness of all parts of proposed model. The
performance of our proposed model was evaluated using NMT Scalp EEG Dataset and
achieved a high classification accuracy of 87.77%, which outperforms the original baseline
model and other research studies. Moreover, we demonstrated the generalization of our
proposed model by evaluating it on another independent dataset, TUH abnormal EEG
Corpus V.2.0.0. (TUAB), without any hyperparameter tuning or adjustment. Furthermore,
a Explainable AI (XAI) analysis confirmed that the model's decision-making process is not
only transparent but also neurologically plausible.