EUVIMEDEUVIMED entdecken
VergleichsstudieOpen Access · CC BY 4.0

Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models

Sikandar Hussain, Soyiba Jawed iD, Ali Mir, Mona Ibrahim Ali, Raidah Al-Baradie, Norah Alaqili, Eman Mohammed Nassim Ali, Shahid Bashir

PLOS One · 31.07.2026 · 21 (7) · e0352991

DOI: 10.1371/journal.pone.0352991 ↗

Kurz gefasst

Vergleichsstudie in der Zeitschrift PLOS One, online erschienen am 31.07.2026. Verfasst von Sikandar Hussain und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology(NUS…. Hauptthemen laut MEDLINE: Epilepsies, Myoclonic, Electroencephalography, Deep Learning. Die Arbeit nennt 49 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This study explores the potential of artificial intelligence (AI) using a hybrid deep learning Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) framework, for EEG-based classification and analysis of Dravet Syndrome (DS).

Method

The study cohort comprised nine pediatric patients with DS, confirmed through either a heterozygous pathogenic mutation in the SCN1A gene or a clinical diagnosis consistent with established diagnostic criteria. In addition, EEG recordings from age-matched healthy control subjects and pediatric patients with non-Dravet epilepsy (“abnormal” EEG) were included. Data on demographic information, seizure characteristics, developmental skills, cognitive functions, and genetic results were gathered from patient records. EEG recordings were analyzed using a subject-independent leave-one-subject-out validation strategy, spatial and temporal features by employing this model on preprocessed EEG data, effectively differentiating DS patients from Abnormal cases and healthy controls.

Result

Among the evaluated CNN-LSTM models, the pre-trained architecture achieved superior performance with improved stability across most subjects, with an overall accuracy of 85%, balanced accuracy of 85%, a macro-averaged F1-score of 0.85, and a macro-averaged ROC–AUC of 0.87, demonstrating stable performance for multi-class EEG classification of DS, Abnormal, and control subjects. The non-pretrained model showed reduced sensitivity and increased inter-class confusion, particularly for DS and Abnormal classes.

Conclusion

This study demonstrates that a pre-trained CNN-LSTM framework can support automated EEG-based classification of DS-related patterns as a proof-of-concept methodological approach, even in the context of limited subject availability. EEG-specific pretraining improves classification consistency and feature separability compared with training from scratch, highlighting the value of representation learning for rare epilepsy syndromes. Larger multi-center datasets and prospective validation will be required to assess robustness, generalizability, and clinical utility.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Epilepsies, MyoclonicElectroencephalographyDeep LearningHumansConvolutional Neural NetworksChildLong Short Term MemoryFemaleMaleChild, PreschoolNAV1.1 Voltage-Gated Sodium ChannelCase-Control Studies

Substanzen

NAV1.1 Voltage-Gated Sodium ChannelSCN1A protein, human

Autor:innen und Institutionen

  • Department of Computer and Software Engineering, College of Electrical and Mechanical Engineering, National University of Sciences and Technology(NUST), Islamabad, Pakistan.
  • Department of Pediatric Neurology, King Fahad Specialist Hospital, Dammam, Saudi Arabia.
  • Department of Adult Neurology, King Fahad Specialist Hospital, Dammam, Saudi Arabia.
  • Research Center, King Fahad Specialist Hospital Dammam, Dammam, Saudi Arabia.

ORCID-Profile: Soyiba Jawed

Zitieren

APA

Hussain, S., Jawed, S., Mir, A., Ibrahim Ali, M., Al-Baradie, R., Alaqili, N., Nassim Ali, E. M., & Bashir, S. (2026). Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models. PLOS One, 21(7), e0352991. https://doi.org/10.1371/journal.pone.0352991

Vancouver

Hussain S, Jawed S, Mir A, Ibrahim Ali M, Al-Baradie R, Alaqili N, et al. Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models. PLOS One. 2026;21(7):e0352991. doi:10.1371/journal.pone.0352991

BibTeX
@article{Hussain2026,
  author = {Hussain, Sikandar and Jawed, Soyiba and Mir, Ali and Ibrahim Ali, Mona and Al-Baradie, Raidah and Alaqili, Norah and Nassim Ali, Eman Mohammed and Bashir, Shahid},
  title = {Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {7},
  pages = {e0352991},
  doi = {10.1371/journal.pone.0352991}
}
Kostenlos starten →