About 3-8% of newborns need time-critical resuscitation. NewbornTime will create a timeline of events during resuscitation, using AI to detect the exact time of birth from thermal videos in the delivery room. It will employ deep convolutional neural networks (CNN) for activity recognition from thermal and visual videos, capable of identifying overlapping activities. The AI models will be designed to be robust and adaptable for various hospitals. These timelines will help assess guideline compliance, recognize effective resuscitation patterns, and serve as a tool for debriefing and quality improvement.
Goal
Improve newborn resuscitation based on video and artificial intelligence.
Project collaboration
The project is a collaboration between the University of Stavanger (UiS), Stavanger University Hospital (SUS), Laerdal Medical and BitYoga. UiS, SUS and Laerdal have long experience in collaborative research on newborn care. They have documented promising results in detecting activities using resuscitation videos from a hospital in Tanzania. In NewbornTime the data collection will be performed at SUS. BitYoga and Laerdal will ensure smart GDPR-compliant data contracts and data platforms. UiS will develop site-adaptive AI methods for activity recognition in video. The project has been recommended by Sikt – Norwegian Agency for Shared Services in Education and Research, formerly known as NSD (number 816989).