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, Ali Mir, Mona Ibrahim Ali, Raidah Al-Baradie, Norah Alaqili, Eman Mohammed Nassim Ali, Shahid Bashir · 2026

Read Deep learning architectures for EEG-based classification of Dravet syndrome: A comparative study of pre-trained and non-pretrained hybrid CNN-LSTM models by Sikandar Hussain, Soyiba Jawed, Ali Mir, Mona Ibrahim Ali, Raidah Al-Baradie, Norah Alaqili, Eman Mohammed Nassim Ali, Shahid Bashir (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0352991.txt.

Description

Sikandar Hussain led a team of eight authors on this 2026 study teaching computers to recognize Dravet syndrome from brain wave recordings. This rare childhood epilepsy is hard to spot, and few patient recordings exist. Using records from nine affected children plus healthy and other-epilepsy controls, they trained hybrid deep learning models and tested them one child at a time.

Models pre-trained on brain wave data classified children more steadily than models trained from nothing. Hussain calls the work a proof of concept, and says larger multi-center collections must test whether the method can help real diagnosis.

Catalog record

CREATORSikandar Hussain, Soyiba Jawed, Ali Mir, Mona Ibrahim Ali, Raidah Al-Baradie, Norah Alaqili, Eman Mohammed Nassim Ali, Shahid Bashir
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE53205
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0352991

Browse the full library · About the Tower of Babel