The NewbornTime project is about improved newborn care by using artificial intelligence (AI) for activity and event recognition in video from the time during and after birth.
The project is funded by NRC (project no. 320968, IKTPLUSS Collaborative and Knowledge-building Project), Fondation Idella and Helse Vest.
University of Stavanger (lead), Stavanger University Hospital (SUS), Laerdal Medical and bitYoga.
2 million – the number of newborn babies who could be saved each year if we end preventable newborn mortality.
Deprivation of oxygen to an infant during and after birth might lead to birth asphyxia, one of the leading causes of newborn deaths, cerebral palsy and other long-term damage. According to guidelines, a newborn in need of help to start breathing should be resuscitated immediately after birth. Resuscitation activities include stimulating, clearing airways, and perform bag-mask-ventilation. In Norway, approximately 10% of term infants need stimulation and around 3% need bag-mask ventilation.
NewbornTime will produce a timeline describing events and activities performed on a newborn. Accurate time of birth will be detected using AI models from thermal videos collected in the delivery room. Activity recognition will be performed using AI in the form of deep convolutional neural networks (CNN) on thermal and RGB video from the resuscitation. The system will be designed to recognize multiple time-overlapping activities. Care will be given to make the AI models robust, reliable, general, and adaptive to be able to use it at different hospitals and settings. The timelines will be used to evaluate compliance to guidelines and identify successful resuscitation activity patterns. It can further be useful in a de-briefing and quality improvement tool.
The project is a collaboration between University of Stavanger (UiS), Stavanger University Hospital (SUS), Laerdal Medical and BitYoga. UiS, SUS and Laerdal has long experience in collaborative research on newborn care. They have documented promising results on 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.
Information page for participants: In English and in Norwegian.
NewbornTime in the news
Approvals and recommendations
In this section you can find all communication with the regional ethical committee and Norwegian Centre for Research Data.
Communications and approvals from REK – Regional Ethical committee, REK nr. 22245
Communication and recommendations from NSD – Norwegian Centre for Research Data, NSD nr. 816989
We will push the research front in robust and adaptive Artificial Intelligence (AI) for activity recognition from video and thermal video analysis. We will develop automated systems useful for research, debriefing and feedback on newborn care around time of birth. NewbornTime means AI for safer births.
NewbornTime is making every resuscitation a learning event. We want to build a culture for continuous data-driven quality improvement.
This project will develop important, new technology to automate consent and data analysis. It will reduce the workload in the hospital and the new data will guide quality improvement. To make births safer.
BitYoga develops a Consent Management Platform for NewbornTime based on blockchain technology, reliable communication protocol and encryption, protecting user data in an absolutely secure manner.
Publications
Engan, Kjersti, Øyvind Meinich-Bache, Sara Brunner, Helge Myklebust, Chunming Rong, Jorge García-Torres, Hege L. Ersdal, Anders Johannessen, Hanne Markhus Pike, and Siren Rettedal. “Newborn Time - Improved Newborn Care Based on Video and Artificial Intelligence - Study Protocol.” BMC Digital Health 1, no. 1 (March 8, 2023): 10. https://doi.org/10.1186/s44247-023-00010-7.
Garcia-Torres, Jorge, Oyvind Meinich-Bache, Sara Brunner, Anders Johannessen, Siren Rettedal, and Kjersti Engan. “Towards Using Thermal Cameras in Birth Detection.” In 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (IVMSP), 1–5. Nafplio, Greece: IEEE, 2022. https://doi.org/10.1109/IVMSP54334.2022.9816177.
García-Torres, Jorge, Øyvind Meinich-Bache, Siren Irene Rettedal, Amalie Kibsgaard, Sara Brunner, and Kjersti Engan. “Comparative Analysis of Binary and Multiclass Activity Recognition in High-Quality Newborn Resuscitation Videos.” In Proceedings of the 5th Northern Lights Deep Learning Conference ({NLDL}), 59–66. PMLR, 2024. https://proceedings.mlr.press/v233/garcia-torres24a.html.
Information for employees at SUS affected by the collection of data
Do you have any questions about our collection of data? Here you will find presentations and information letters.
An invitation to an information and dialogue meeting was sent out to all employees at SUS who may be affected by the data collection in NewbornTime. The meeting was held on 24 January 2022.
Here you can see the video of the presentation that was held at the meeting.
University of Stavanger
Stavanger University Hospital (SUS)
Laerdal Medical
BitYoga
Department of Electrical Engineering and Computer Science
Department of Electrical Engineering and Computer Science
Department of Electrical Engineering and Computer Science
Health data in the cloud, secure data handling
Time and place: June 9th 2023, 8:30 am, at University of Stavanger (KE-E102).
8:30 Part 1 – public
Welcome and Stavanger AI Lab (SAIL) - Tom Ryen (15 min)
Project overview and legal basis – Kjersti Engan (25 min)
Building Trust in Healthcare with Privacy Techniques: Combining Blockchain, Federated Learning, and Homomorphic Encryption in the Cloud – Ferhat Özgur Catak (1 hour)
10:10-10:30 Coffee break
10:30 Part 2 – public
Save data collection, storage and handling (including DPA and ROS) – Anders Johannessen, Sara Brunner (40 min)
Thermal video data – what can it be used for and how, including showing samples – Jorge Garcia-Torres (20 min)
Helse Vest IKT: perspective on Health data in the cloud and secure data handling – Siri Hansen (50 min)
12:30-13:00: Lunch for extended project group + speakers
13:00-15:00 Part 3 – by invitation, in “Pauserommet” KE-E439
Hvordan jobber UiS med NewbornTime data for kunstig intelligens? – Øyvind Meinich-Bache, Jorge Garcia-Torres
Datainnsamling på SUS: Første leddet for kvalitetsdata – Siren Rettedal, Sissel Borén, Elise Lerang
Drøfte videre arbeidet med prosjektet – Kjersti Engan, all
Workshop on newborn resuscitation
University of Stavanger and Stavanger university hospital arranged a workshop Friday December 3rd.
Date: 3 December 2021
Location: University of Stavanger, Kjølv Egelands building (KE) Room E-102.
Program
10:00-10:05 Welcome
10:05-10:35 Hege Ersdal (SUS): Updated newborn resuscitation guidelines and Safer Births studies
10:35-10:50 Jørgen Linde (SUS): Research project in Tanzania – transfer value to newborn resuscitation in Norway
10:50-11:05 Discussion and small break
11:05-11:20 Siren Rettedal (SUS): Safer Births SUS – which knowledge gaps are we addressing and results so far
11:20-11:40 Joanna Haynes (SUS): Newborn simulation research at SUS – what did we learn from the studies?
11:40-11:50 Open discussion
11:50-12:30 Lunch (only for partners and presenters)
12:30-12:45 Kjersti Engan (UiS): NewbornTime – short about project and status
12:45-13:00 Chunming Rong (BitYoga): Digital consent solution and data security
13:00-13:15 Sara Brunner (Laerdal Med.): Semi-automatic data collection: how it all works
13:15-13:30 Helge Myklebust (Laerdal Med.): Experience gained using objective data from resuscitations
13:30-13:40 Siren Rettedal (SUS): Subproject funded: “NewbornTime Debrief and Simulation – Making Every Resuscitation a Learning Event”
13:40-14:10 Partners only (closed meeting); Planning ahead for NewbornTime: publications, abstracts, data collection etc.
14:10-15:00 Partners only (closed meeting); Open discussion