Federated learning improves infant movement analysis with uncertainty measure
Uncertainty-Aware Federated Learning for Infant Movement Analysis
Machine LearningArtificial IntelligenceComputer Vision and Pattern Recognition
Summary
Identifying early signs of brain development problems in babies can be done by watching how they move, which is usually hard and needs expert eyes. The authors created a way for computers at different hospitals to learn from baby movement data without sharing it all in one place, protecting privacy. They also found a way for the computer models to know which hospitals have more reliable data and give those more influence. Their tests show this approach works nearly as well as having all data in one spot and better than each hospital learning alone.
What this means in practice
- •For hospital data teams: Coordinate infant movement models across multiple hospitals without sharing sensitive data for early brain disorder detection.
- •For medical device software developers: Develop baby movement analysis tools that integrate federated learning and uncertainty to improve automated assessments.$Commercial implications: Enables creation of privacy-preserving clinical AI products for infant neurological screening devices sold to healthcare providers.
Authors
Edmond S. L. Ho
Abstract
Infant movement analysis provides valuable biomarkers for the early identification of neurodevelopmental disorders. Recent advances in deep learning have enabled automated analysis of infant movements from video-derived skeletal representations, achieving performance comparable to expert assessment for tasks such as General Movement Assessment (GMA). However, most existing approaches rely on centralized training, requiring data from multiple institutions to be collected and stored at a single site. Such assumptions are often impractical in clinical settings due to privacy, governance, and data-sharing constraints. To address these challenges, we present, to the best of our knowledge, the first federated learning framework for automated infant movement analysis and General Movement Assessment using skeletal motion data. As a clinically relevant use case, the proposed framework is evaluated on fidgety movement classification. To quantify model confidence, Monte Carlo (MC) Dropout is employed to estimate predictive uncertainty during inference. Building upon this, we propose an Uncertainty-Aware Federated Averaging (UA-FedAvg) strategy that incorporates predictive entropy derived from MC-Dropout into the federated aggregation process, enabling client contributions to be adjusted according to their predictive uncertainty. Experiments were conducted using a cross-subject evaluation protocol under a three-client federated learning setting. Results demonstrate that federated learning substantially improves classification performance compared with independently trained local models while achieving performance approaching that of centralized training. Furthermore, UA-FedAvg and its variant incorporating validation loss generally outperform conventional FedAvg across the evaluated data-split configurations.