EEG-Based Prognostic Prediction in Moderate Traumatic Brain Injury: A Hybrid BiLSTM-AdaBoost Approach

An electroencephalography (EEG)-based prognostic model for moderate traumatic brain injury (moTBI) overcomes the limitations of traditional clinical assessment. Although machine learning (ML) algorithms promise better results, existing frameworks often struggle to capture the complex temporal patterns in EEG data, resulting in poor prediction accuracy. This study addresses this gap by presenting a novel hybrid deep learning (DL) architecture of a prediction model that uses resting-state EEG data as input. This architecture synergistically combines bidirectional long short-term memory (BiLSTM) with adaptive boosting (AdaBoost), which enables accurate discrimination between poor and good prognosis of moTBI. The BiLSTM component extracts complex features from the EEG signals, while AdaBoost serves as a classifier discriminator, replacing the conventional softmax function to optimize performance. Experimental results show that the BiLSTM-AdaBoost model achieves impressive under the curve (AUC) performance of 99.51 ± 1.36% and 98.91 ± 2.47% for preprocessed and 98.91 ± 2.47% for unprocessed EEG sequences. Notably, the model outperforms conventional DL architectures and other hybrid models, showing improvements of up to 14.14% over DL-only models and 24.51% over traditional ML approaches. This innovative architecture of the BiLSTM-AdaBoost model represents a significant advance in EEG-based decision support systems for moTBI and rapid assessment of a potentially overlooked poor prognosis.