By Soham NandiReviewed by Frances BriggsJul 1 2025
Researchers have developed an AI model to detect epileptic spasms in children using smartphone and social media videos. It could offer a fast and accessible diagnostic tool for the rare neurological disorder.

Image Credit: vasara/Shutterstock.com
Infantile epileptic spasms syndrome (IESS) is a serious condition affecting approximately one in 2000 to 2500 infants. Early detection is essential for patient outcomes, but symptoms of IESS are easily mistaken for everyday movements in children. This difficulty in detection can lead to delayed diagnosis and poorer outcomes.
Smartphone videos have been recognized as a good way to identify seizures, but a lack of specialist availability often limits their use. Previous attempts at creating AI to recognize seizures have been limited by the quantity of training data they could access, which is particularly true for rare disorders like IESS.
Researchers at the Universitätsmedizin Berlin have turned to social media as an unconventional but rich data source to mitigate this. Their study, published in Nature, compiled 991 confirmed IES events from 141 videos and trained a vision transformer AI model to recognize seizure patterns.
Supplementing this with clinical data, the AI model achieved impressive accuracy, demonstrating its potential as a scalable tool for early diagnosis.
Conducting The Study
The dataset was compiled from YouTube videos uploaded before 2022. Videos were carefully selected to include only children under the age of two showing clearly visible seizures, and a neurologist verified each case. The clips were divided into five-second segments labeled as seizure or non-seizure, with additional footage of healthy infants included to balance the training set.
Three separate datasets were used to validate the model: newer social media clips, control videos of typical infant behavior, and clinical video-EEG recordings. Videos were standardized to 30 frames per second and 224×224 resolution, with augmentations like rotation and flipping applied. A pretrained Hiera Vision Transformer model, originally built for action recognition, was fine-tuned using low-rank adaptation (LoRA) for binary classification.
The tool's performance was evaluated using standard metrics, area under the curve (AUC), sensitivity, specificity, accuracy, and false alarm rate (FAR), with five-fold cross-validation. Given the subject's sensitivity, researchers ensured that ethical procedures were followed, including privacy protections and consent waivers for retrospective data.
Download your PDF copy now!
What the Study Showed
The results of the study were striking. The AI model achieved an AUC of 0.96, with 82 % sensitivity and 90 % specificity on the training set. External testing on smartphone videos from 26 infants showed even stronger results (AUC 0.98, 89 % sensitivity, 100 % specificity), with a FAR of just 0.75 %.
The model's FAR rose slightly in clinical settings when using video-EEG data from 21 seizure-free infants. This rise of 3.4 % was largely due to lower image quality and obstructions like EEG caps. Still, it maintained strong accuracy (AUC 0.98, 80 % sensitivity), highlighting the importance of video clarity for real-world use.
This research reveals a promising path for earlier, more accessible diagnosis of IESS. By using social media videos, the AI model addressed the challenges of data scarcity and specialist shortages. It has the potential to accelerate time-to-diagnosis and improve outcomes. However, further prospective clinical trials are needed to fully assess its effectiveness in everyday medical settings.
Journal Reference
Miron, G., Halimeh, M., Tietze, S., Holtkamp, M., & Meisel, C. (2025). Detection of epileptic spasms using foundational AI and smartphone videos. Npj Digital Medicine, 8(1). DOI:10.1038/s41746-025-01773-1
https://www.nature.com/articles/s41746-025-01773-1
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.