Researchers have developed a machine learning model capable of detecting cessation of breathing in pre-term infants using non-contact video monitoring. The camera-only models achieved a balanced accuracy of 76.9%, demonstrating the feasibility of this approach. When combined with impedance pneumography, the hybrid model improved detection accuracy to 90.6%, surpassing either modality alone and indicating the value of video-derived respiratory information. AI
IMPACT This research demonstrates the potential for AI-powered video analysis to enhance critical infant monitoring, potentially improving patient outcomes and reducing reliance on contact-based sensors.
RANK_REASON The cluster contains an academic paper detailing a new machine learning model and its performance on a specific task.
- cessation of breathing
- Dineo Serame
- impedance pneumography
- machine learning
- PPG-derived respiratory envelope
- pre-term infants
- residual neural network
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
