Using AI to analyse ultrasound scans lets parents pinpoint exact due date of babies, study claims

By MEIKE LEONARD, HEALTH REPORTER
Published: | Updated:
Using artificial intelligence to analyse ultrasound scans could give parents the exact day their child will be born with 95 per cent accuracy, a study has claimed.
Doctors currently estimate a foetus's due date by adding 40 weeks to the first day of the mother's last menstrual period.
This rough calculation is known as Naegele's rule and assumes the woman has a 28-day menstrual cycle and ovulates on day 14, which, for many, is not true.
In the UK, just four per cent of babies are born on their due date.
But a group of US researchers say using AI to analyse ultrasounds could predict a child's date of birth with 95 per cent accuracy.
Using a software developed and trained using more than two million ultrasound images from women who gave birth at the University of Kentucky from 2017 to 2020, the scientists measured how well AI could estimate whether a baby would be carried to term or not.
The program, called Ultrasound AI, was able to predict whether a baby would be born early with 72 per cent accuracy, without relying on external information such as maternal history or clinical measurements.
It was 95 per cent accurate in predicting the due date of babies carried to full term, and 92 per cent accurate for all births combined.
Using artificial intelligence to analyse ultrasound scans could give parents the exact day their child will be born with 95 per cent accuracy, a study has claimed
'AI is reaching into the womb and helping us forecast the timing of birth, which we believe will lead to better prediction to help mothers across the world and provide a greater understanding of why the smallest babies are born too soon,' said Dr John O'Brien, director of maternal-foetal medicine at the University of Kentucky.
'AI will eventually provide greater insights into how to target and prevent adverse pregnancy outcomes
'This work is an important first step in the start of a powerful advance in technology for the field of obstetrics.'
Preterm birth is currently the leading cause of neonatal mortality in the world, and one in every 12 babies is born prematurely.
It comes after the UK Government last year announced a plan to reduce the number of preterm births from 8 per cent to 6 per cent.
Daily Mail