A patient-independent hybrid generative-discriminative framework for seizure detection achieved a mean accuracy of 0.9964, mean specificity of 0.9967, and 4.71 false alarms per hour.
Does a patient-independent hybrid generative-discriminative framework improve automated seizure detection in long-term scalp EEG?
A patient-independent hybrid generative-discriminative framework demonstrated high accuracy and specificity for automated seizure detection in long-term scalp EEG, effectively handling severe class imbalance.
Automated seizure detection from long-term scalp electroencephalography (EEG) remains challenging because seizure windows are sparse, channel configurations vary across patients, and clinically useful systems must maintain strict control of false alarms. This study presents a patient-independent hybrid generative-discriminative framework evaluated on the CHB-MIT cohort under leave-one-patient-out cross-validation. In each outer fold, one patient was reserved exclusively for final testing, whereas channel harmonization, representation learning, feature refinement, model training, and operating-point calibration were performed using only the remaining patients. A fold-specific convolutional \ (\) -variational autoencoder (\ (= 1. 0\) ) was trained on interictal windows from the training patients only. For each window, latent statistics and reconstruction error were combined with handcrafted seizure-sensitive descriptors, followed by train-only sanitization and supervised feature selection. Candidate boosted-tree classifiers, namely LightGBM, CatBoost, and XGBoost, were trained within the training pool, and operating parameters were selected on validation data only. Final performance was then computed on the held-out patient using window-level metrics with record-wise temporal postprocessing. Across the 24 held-out evaluation cases, corresponding to 23 distinct individuals in the public CHB-MIT release, the framework achieved mean accuracy of 0. 9964, mean balanced accuracy of 0. 9411, mean specificity of 0. 9967, and mean false alarms per hour of 4. 7154. Across seizure-positive held-out cases, the mean sensitivity, F1-score, ROC-AUC, and average precision were 0. 5505, 0. 3543, 0. 9496, and 0. 2990, respectively. These findings show that leakage-safe hybrid representation learning can support seizure detection while explicitly handling heterogeneous channels, severe class imbalance, and false-alarm control in long-term scalp EEG.
Farooq et al. (Mon,) conducted a other in Epilepsy (Seizures) (n=23). Patient-independent hybrid generative-discriminative modeling was evaluated on Mean accuracy across all 24 held-out evaluation cases. A patient-independent hybrid generative-discriminative framework for seizure detection achieved a mean accuracy of 0.9964, mean specificity of 0.9967, and 4.71 false alarms per hour.