Mayo Clinic researchers have used artificial intelligence (AI) algorithms to analyse how changes in women who are in labour can help identify whether a successful vaginal delivery will occur with good outcomes for mom and baby.

“This is the first step to using algorithms in providing powerful guidance to physicians and midwives as they make critical decisions during the labour process,” said Abimbola Famuyide, a Mayo Clinic ob-gyn and senior author of the study. “Once validated with further research, we believe the algorithm will work in real time, meaning every input of new data during an expectant woman’s labour automatically recalculate the risk of adverse outcome. This may help reduce the rate of caesarean delivery, and maternal and neonatal complications.”

Women in labour understand the importance of periodic cervical examinations to gauge the progress of labour. This is an essential step, as it helps obstetricians predict the likelihood of a vaginal delivery in a specified period of time. The problem is that cervical dilation in labour varies from person to person, and many important factors can determine the course of labour.

In the study, researchers used data from the Eunice Kennedy Shriver National Institute of Child Health & Human Development’s multi-centre Consortium on Safe Labor database to create the prediction model. They examined more than 700 clinical and obstetric factors in 66,586 deliveries from the time of admission and during labour progression.

The risk-prediction model consisted of data known at the time of admission in labour, including patient baseline characteristics, the patient’s most recent clinical assessment, as well as cumulative labour progress from admission. The researchers explain that the models may provide an alternative to conventional labour charts and promote individualisation of clinical decisions using baseline and labour characteristics of each patient.

“It is very individualised to the person in labour,” said Famuyide. He added that this would be a powerful tool for midwives and physicians remotely as it would allow time for transfers of patients to occur from rural or remote settings to the appropriate level of care.

This study was conducted in collaboration with scientists from the Mayo Clinic Robert D and Patricia E Kern Center for the Science of Health Care Delivery. The findings were published in Plos One.

“The AI algorithm’s ability to predict individualised risks during the labour process will not only help reduce adverse birth outcomes but it can also reduce healthcare costs associated with maternal morbidity in the USA, which has been estimated to be over $30bn,” said Bijan Borah, Robert D and Patricia E Kern scientific director for health services and outcomes research.

Validation studies are ongoing to assess the outcomes of these models after they were implemented in labour units.