Researchers have developed VideoPulse, a novel system designed to estimate neonatal heart rate and peripheral capillary oxygen saturation (SpO2) using non-contact video recordings. This approach is particularly beneficial for neonates, as it avoids the need for adhesive probes that can cause skin irritation and increase infection risks. The system utilizes a 3D CNN backbone and achieves promising results on the NBHR neonatal dataset, with MAE of 2.97 bpm for heart rate and 1.69 percent for SpO2. Furthermore, VideoPulse demonstrates effectiveness in cross-dataset evaluations, indicating its potential for low-cost, non-invasive monitoring in neonatal intensive care units. AI
IMPACT Enables non-invasive, low-cost monitoring of neonatal vital signs, potentially improving care in NICUs.
RANK_REASON The cluster contains an academic paper detailing a new method and dataset for vital sign estimation. [lever_c_demoted from research: ic=1 ai=1.0]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →