Uncertainty-Aware Federated Learning for Infant Movement Analysis

2026-09-25

AI Summary

This study addresses the data silo problem in infant motion analysis caused by privacy constraints by proposing the first skeleton-based federated learning framework. Methodologically, it employs deep learning to process video-derived skeletal data and utilizes Monte Carlo Dropout to quantify predictive uncertainty. Furthermore, an uncertainty-aware federated averaging strategy (UA-FedAvg) is introduced, which dynamically adjusts client aggregation weights based on estimated predictive entropy, enabling multi-institutional collaborative training without centralized data storage. Experimental results demonstrate that the proposed framework significantly outperforms isolated local models and achieves performance comparable to centralized training. Additionally, UA-FedAvg consistently surpasses the conventional FedAvg algorithm across various data partitioning schemes, highlighting its robustness and effectiveness for privacy-preserving infant motion analysis.

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.

Problem

• Infant Movement Analysis
• Federated Learning
• General Movement Assessment
• Data Privacy
• Uncertainty Estimation

Innovation

• Federated Learning
• Uncertainty-Aware Aggregation
• Monte Carlo Dropout
• Infant Movement Analysis
• General Movement Assessment