Abstract Details

Title Development of Multimodal Automated Seizure Detection and Type Classification Using Synchronized Video-EEG Data

Topic Epilepsy/Clinical Neurophysiology (EEG)

Presentation(s) P2 - Poster Session 2 (11:45 AM-12:45 PM)

Poster/Presentation
Number 11-010

Objective To develop and validate a multimodal transformer network for automated seizure detection and seizure type classification on a large-scale multicenter datasets, using video-EEG data, addressing the critical need for efficient epilepsy diagnosis.

Background Visual seizure analysis by EEG specialists are time-consuming and labor-intensive. Deep learning based automated seizure recognition is significant for clinical practice. However, most researches with excellent seizure detection performance conducted on datasets less than 30 patients, offering limited coverage of seizure heterogeneity and between-patient variability. Seizure type classification studies face label scarcity, particularly for comprehensive focal seizure classification, and lack of external validation.

Design/Methods We included 820 patients, 5674 seizures from three epilepsy centers for model development and validation. Patient-wise splits and external center dataset were used for testing, to evaluate the robustness of model across individuals and centers. The model employed pretrained convolutional networks to extract features from EEG and video data. Transformer fuses these heterogeneous data modalities, enabling unified seizure analysis that addresses both detection and nine-class type classification (typical absence, atypical absence, epileptic spasm, myoclonic, tonic, temporal, frontal, centro-parietal and occipital seizures) tasks.

Results Validating on strict patient-wise split test set containing 151 patients, vEpiSzNet achieves robust seizure detection (AUROC 0.990, AUPRC 0.838). For seizure type classification, external 74 patients (583 seizures ) validation results showed 69.2% accuracy. Of the 74 patients, 44 patients were selected for clinician-machine comparison, resulting comparable performance on seizure classification between vEpiSzNet and EEG specialist (73.4% vs 73.7%). Machine showed dramatically reduced analysis time compared to clinician analysis (minutes versus hours). Video integration reduces false positives by 24.3% and improves frontal seizure classification by 38.4%. External validation across centers confirms generalizability (AUROC 0.923, AUPRC 0.607).

Conclusions

We developed vEpiSzNet, a multimodal pretrained Transformer that trained and validated on a large-scale multicenter datasets, shows excellent performance in seizure detection and classification achieving specialist-level accuracy.

Authors/Disclosures
Nan Lin, MD PRESENTER	Dr. Lin has nothing to disclose.
Ming Lu	Ming Lu has received personal compensation for serving as an employee of Eli Lilly and Company. Ming Lu has stock in Eli Lilly and Company.
Weifang Gao	Dr. Gao has nothing to disclose.
Heyagn Sun	Dr. Sun has nothing to disclose.
Katie Gao	An immediate family member of Ms. Gao has received personal compensation for serving as an employee of Otsuka Pharmaceutical.
Zi Liang, Jr., MD, no	Mr. Liang has nothing to disclose.
Thomas Li, PhD	Dr. Li has nothing to disclose.
Peng Hu	Mr. Hu has nothing to disclose.

��ɫ��

��ɫ��