Video-based detection of cessation of breathing in pre-term infants using machine learning
2026-07-06 • Machine Learning
Machine Learning
AI summaryⓘ
The authors studied how cameras can help monitor breathing in premature babies, who often stop breathing because their lungs are not fully developed. They used video to track chest movements and combined this with other usual sensor data. Their camera-only method could detect breathing stops fairly well, and when combined with traditional methods, detection improved significantly. This shows that video can add useful information and could make monitoring babies' breathing safer and more reliable without needing sticky sensors.
pre-term infantsapnoearespiratory monitoringnon-contact videoimpedance pneumographyECG-derived respirationPPG respiratory envelopemachine learningresidual networkneonatal intensive care unit
Authors
Dineo Serame, Lionel Tarassenko, Mauricio Villarroel
Abstract
Pre-term infants are susceptible to potentially harmful apnoea-related cessations of breathing due to immature respiratory control. However, reliable respiratory monitoring in the neonatal intensive care unit (NICU) remains challenging because motion artefacts, sensor displacement, and skin fragility can compromise contact-based measurements. Non-contact video monitoring offers a complementary approach that does not depend on adhesive sensors while providing additional respiratory information. We investigated whether camera-based signals can detect apnoea-related cessation of breathing (COBE) and provide complementary information to routinely acquired physiological signals. Using video and clinical recordings from 30 pre-term infants, respiratory motion was extracted from dynamically tracked torso regions to generate camera-derived time-series signals. Camera-only models were trained using residual network (ResNet) architectures, while hybrid models combined video-derived signals with impedance pneumography (IP), ECG-derived respiration (EDR), and the PPG-derived respiratory envelope. Camera-only models achieved a balanced accuracy of 76.9%, demonstrating the feasibility of non-contact COBE detection. Combining video-derived features with IP improved balanced accuracy to 90.6%, outperforming either modality alone and indicating that video provides respiratory information beyond standard physiological signals. These findings show that video-derived signals contain clinically relevant respiratory features and enhance COBE detection when combined with conventional physiological signals. This supports non-contact video as a complementary modality for automated COBE detection and highlights its potential to improve the robustness of neonatal respiratory monitoring.