General movements (GMs) are spontaneous, coordinated body movements in infants that offer valuable insights into the developing nervous system. Assessed through the Prechtl GM Assessment (GMA), GMs are reliable predictors for neurodevelopmental disorders. However, GMA requires specifically trained clinicians, who are limited in number. To scale up newborn screening, there is a need for an algorithm that can automatically classify GMs from infant video recordings. This data poses challenges, including variability in recording length, device type, and setting, with each video coarsely annotated for overall movement quality. In this work, we introduce a tool for extracting features from these recordings and explore various machine learning techniques for automated GM classification.
@article{arxiv.2411.09821,
title = {Towards Scalable Newborn Screening: Automated General Movement Assessment in Uncontrolled Settings},
author = {Daphné Chopard and Sonia Laguna and Kieran Chin-Cheong and Annika Dietz and Anna Badura and Sven Wellmann and Julia E. Vogt},
journal= {arXiv preprint arXiv:2411.09821},
year = {2025}
}
Comments
Paper at Proceedings of Machine Learning Research 298 1 22, 2025 Machine Learning for Healthcare. Iterations of previous versions accepted as oral and best paper award at ICLR 2025 Workshop on AI for Children and at the Findings track of the Machine Learning for Health (ML4H) symposium 2024