New Delhi, Jan 30 A new artificial intelligence-based model on Thursday has shown previously unidentified combinations of risk factors linked to serious negative pregnancy outcomes, including stillbirth.
A team of US researchers including from the Universities of Utah and Brown conducted an AI-based analysis of almost 10,000 pregnancies in the country.
It included information on social and physical characteristics ranging from pregnant people’s level of social support to their blood pressure, medical history, and foetal weight, as well as the outcome of each pregnancy.
There may be up to a 10-fold difference in risk for infants who are currently treated identically under clinical guidelines, revealed the results, published in the journal BMC Pregnancy and Childbirth.
Foetal sex, presence or absence of pre-existing diabetes and the presence or absence of a foetal anomaly such as a heart defect could determine the risk.
The AI model helped identify a “really unexpected” combination of factors that revealed higher risk, said Nathan Blue, from Utah’s Department of Obstetrics and Gynecology.
The model can progress toward making “more personalised risk assessment and pregnancy care”, he added.
The findings showed that female babies could be at higher risk than males if the mother has pre-existing diabetes. Usually, female foetuses are at slightly lower risk for complications than male foetuses -- a small but well-established effect.
“The AI model detected something that could be used to inform risk that not even the really flexible, experienced clinician brain was recognising,” Blue said.
The researchers were especially interested in developing better risk estimates for foetuses in the bottom 10 per cent for weight, but not the bottom 3 per cent.
These babies are small enough to be concerning, but large enough that they are usually perfectly healthy.
While current clinical guidelines advise intensive medical monitoring for all such pregnancies, the team found that within this foetal weight class, the risk of an unhealthy pregnancy outcome varied widely.
Disclaimer: This post has been auto-published from an agency feed without any modifications to the text and has not been reviewed by an editor