Equation-level parameterized fusion reformulation improved epileptic seizure detection accuracy from 77.56% to 99.99% with an F1-score of 99.98% and AUC of 100% compared to baseline fusion in 120 clinically diagnosed epilepsy patients.
Does an equation-level multimodal fusion reformulation improve epileptic seizure detection accuracy compared to baseline models in patients with epilepsy?
An equation-level multimodal fusion reformulation integrating EEG, ECG, EMG, and ACC signals significantly improves the accuracy of machine learning and deep learning models for epileptic seizure detection.
Effect estimate: Accuracy improvement from 77.56% to 99.99%, F1-score from 75.32% to 99.98%, AUC from 79.77% to 100% after equation-level fusion reformulation across models
Absolute Event Rate: 99.99% vs 77.56%
Epileptic seizure detection remains challenging due to noise, inter-subject variability, and the poor generalization ability of unimodal learning models. To address these limitations, this study proposes an equation-level multimodal fusion reformulation for epileptic seizure detection that integrates EEG, ECG, EMG, and ACC signals using adaptive parameterized fusion and interaction control. The framework introduces four interpretable parameters: a fusion exponent ( ρ ), an interaction weight ( δ ), a stabilization factor λ , and a synergy amplifier η , which jointly regulate modality contribution, nonlinear cross-modal interaction, numerical stability, and synergistic enhancement within a unified mathematical formulation applicable to both traditional and deep learning models. The study is conducted on a multimodal dataset comprising recordings from 120 clinically diagnosed epilepsy patients, including 60 patients from Tamale Teaching Hospital and 60 from publicly available datasets. Signals were sampled at 512 Hz and segmented into 2-second windows with 50% overlap, yielding approximately 1,024,000 labeled samples. A formal Data Quality Assurance (DQA) model and a Novel Cosine Similarity (NCS) index were employed to assess signal reliability and cross-source alignment prior to fusion. Twelve machine learning and deep learning classifiers were evaluated using a strict patient-wise data split to prevent data leakage. Experimental results demonstrate consistent performance improvements across all models following equation-level reformulation. Traditional machine learning models improved from baseline accuracies of approximately 55–67% to 82–92%, while deep learning models improved from 70–82% to 89–97.9%, with the Transformer-based model achieving the highest performance. These results confirm that equation-level multimodal fusion provides a generalizable, interpretable, and computationally efficient approach for robust epileptic seizure detection.
Khalid et al. (Fri,) conducted a other in Clinically diagnosed epilepsy patients with synchronized EEG, ECG, EMG, and ACC recordings (n=120). Equation-level parameterized multimodal fusion reformulation with adaptive parameters (fusion exponent ρ, interaction weight δ, stabilization factor λ, synergy amplifier η) applied to machine learning and deep learning seizure detection models vs. Baseline unmodified machine learning and deep learning models using multimodal data fusion was evaluated on Epileptic seizure detection performance measured by accuracy, F1-score, and AUC (Accuracy improvement from 77.56% to 99.99%, F1-score from 75.32% to 99.98%, AUC from 79.77% to 100% after equation-level fusion reformulation across models). Equation-level parameterized fusion reformulation improved epileptic seizure detection accuracy from 77.56% to 99.99% with an F1-score of 99.98% and AUC of 100% compared to baseline fusion in 120 clinically diagnosed epilepsy patients.