SinTransNet: an EEG-based deep learning framework for infantile epileptic spasms syndrome detection
Junyuan Feng, Zhenzhen Liu, Linlin Shen, Xiaoling Luo, Yan Chen, Lin Li, Tian Zhang · 2026
Read SinTransNet: an EEG-based deep learning framework for infantile epileptic spasms syndrome detection by Junyuan Feng, Zhenzhen Liu, Linlin Shen, Xiaoling Luo, Yan Chen, Lin Li, Tian Zhang (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/PMC13548594.txt.
Description
Junyuan Feng and colleagues present a deep learning system that reads brainwave recordings to detect infantile epileptic spasms syndrome, in a 2026 methods paper. This severe infant epilepsy shows chaotic brainwave patterns, and reading the traces by eye is slow and error-prone, delaying treatment. Their system, SinTransNet, splits each recording into five frequency bands, extracts features with wave-shaped convolutional filters, and lets a transformer weigh relationships across bands.
Testing used 129 recordings containing close to two thousand spasm events from the team's own collection. The system reached average accuracy near eighty-six percent, catching about four fifths of true cases while keeping false alarms low. The authors argue that automated reading of this kind could speed diagnosis in pediatric neurology wards, giving infants a better chance at early treatment before developmental harm accumulates.
Catalog record
| CREATOR | Junyuan Feng, Zhenzhen Liu, Linlin Shen, Xiaoling Luo, Yan Chen, Lin Li, Tian Zhang |
|---|---|
| YEAR | 2026 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 67833 |
| LICENSE | https://creativecommons.org/licenses/by/4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |