PROMETHEUS
Research type
Research Study
Full title
PROMETHEUS: Prospective tRial of Machine lEarning To Help fEtal Ultrasound Scanning
IRAS ID
292223
Contact name
Reza Razavi
Contact email
Sponsor organisation
King's College London
ISRCTN Number
ISRCTN65824874
Duration of Study in the UK
1 years, 0 months, 0 days
Research summary
Congenital heart disease (CHD) is the most common medical problem affecting unborn babies. We know that if we diagnose these babies before birth, they are more likely to survive after birth and less likely to suffer other medical problems. Unfortunately, in the UK only around half of babies with CHD are diagnosed before birth. This is because the ultrasound scans are difficult to perform, and there is a shortage of people able to do these scans. Some areas of the UK have much lower rates of detection of CHD before birth than others.
This project aims to investigate whether a sophisticated type of computer programme known as Artificial Intelligence (AI) can help us identify heart conditions in babies, before birth. We want to find out if AI can help the people doing these scans, by assisting them and telling them when the baby has CHD.
We will ask pregnant women to volunteer for our study, both those who have a baby with a healthy heart and those with a baby with CHD. The women will be recruited from the fetal cardiology clinic at Evelina London Children’s Hospital. We will test how our AI systems work in ‘real life’ by scanning these volunteers using AI and without (so each volunteer will be scanned twice, taking around 1 hour in total). These scans will be in addition to the usual clinical scans, and will take place between 18+0 and 27+6 weeks’ gestation. The people doing the scan will not know which babies have CHD beforehand. We will measure if the AI assistance improves the rate of detection of CHD. These research scans will take place in the Clinical Research Facility at St Thomas’ Hospital.
REC name
London - Dulwich Research Ethics Committee
REC reference
22/LO/0163
Date of REC Opinion
13 Apr 2022
REC opinion
Further Information Favourable Opinion