JMIR Publications

ABSTRACT

Background:

Electroencephalography (EEG) is widely used in medicine as a technique for the assessment of several brain-related pathologies. However, the interpretation of EEG signals is a strenuous task that requires the expertise of trained neurologists and has relatively low inter-rater agreement.

Objective:

To address this problem by using artificial intelligence methods to automate EEG interpretation and compare the performance of different modeling approaches.

Methods:

A gradient boosting–based model, inspired by the work of Albaqami et al., was implemented and compared to deep learning–based models using convolutional neural networks to classify images generated from raw EEG signals. The models were trained and tested on pediatric EEGs acquired at the University Hospital in Essen.

Results:

The deep learning model demonstrated superior sensitivity (78.3%) and F1-score (80.0%) compared to the gradient boosting model (sensitivity: 68.1%, F1-score: 76.4%), indicating improved detection of abnormal EEGs. However, the gradient boosting approach achieved higher specificity (93.7% vs. 89.6%), suggesting a stronger ability to recognize normal EEGs. Overall, both methods yielded promising results, with classification accuracies reaching up to 85%.

Conclusions:

Both approaches show potential for automated EEG interpretation. Future improvements, including larger and more diverse datasets, refined deep learning architectures, and integration of explainable AI techniques, could further enhance performance.