Started in March 2016, the Digi-NewB project aims to develop a new generation monitoring system in neonatology. This system is developed thanks to big data techniques and artificial intelligence to extract key information from multi-sources data (cardiac frequency, respiration, movements thanks to video analysis, cries, clinical signes). Using such an approach is expected to bring clear benefits for clinicians and patients, thanks to an early detection of sepsis and an improvement of the clinical follow up and of the patient’s maturation.
After almost three years since the start, the project is showing first promising results: 400 newborns were monitored in the 6 University hospitals including physiological signals (heart rate, respiratory rate, etc.), clinical annotations and video and sound recordings. These data were analysed with continuously improved processing tools aiming at a quicker and more efficient real-time data analysis to be applied in the future system. Such algorithms are included in a prototype demonstration being currently developed. This prototype delivers a full interface enabling the visualization of the sepsis risk and its evolution, the contributing features and their evolution.
The system development is based on a participatory approach, by including care staff (on usability and user requirements analysis and group interviews) and parents (by taking part to the clinical study, to group interviews, and to the project Advisory board through the national association SOS Prema).
The Digi-NewB prototype aims to be used as a medical decision support system, contributing to personalized medicine also called precision medicine, enabled by artificial intelligence and computers increased calculation power. By this approach, project partners aim to achieve improved early sepsis diagnosis and thus a reduction in sepsis-related morbidity and mortality in neonatology services.
Digi-NewB is led by the French Western network of University Hospitals HUGO and in particular by Pr. Pladys from Rennes Hospital and Pr. Carrault from Rennes 1 University, and is based on a strong cooperation of paediatricians from the HUGOPEREN network. The project includes the participation of 4 Universities, 6 Hospital Universities, and 2 SMEs: Rennes 1 University (Image and signal processing laboratory, FR), Tampere University (FI), Galway University (IE), Porto University (INESC TEC, PT), Rennes, Angers, Brest, Tours, Nantes and Poitiers Hospital Universities, Voxygen SME (FR) and Syncrophi SME (IE).
Digi-NewB will launch a first demonstration in Spring 2019 and will publish its final results in February 2020, leading to a wider-scale clinical study after 2020.