Using AI to predict pregnancy and childbirth risks

Mayo Clinic researchers say artificial intelligence can help patients achieve better outcomes and could potentially reduce costs for healthcare systems.

Researchers from the Mayo Clinic have found that artificial intelligence can be used to help analyze whether pregnant patients can give birth safely and avoid complications.

Researchers looked at more than 700 health factors in more than 66,000 deliveries, according to a recent study published in PLOS ONE.

“Using machine learning-based algorithms can provide a dynamic, cumulative, and individualized model for predicting vaginal birth outcomes and facilitating intrapartum decision-making,” the authors wrote.

The researchers said that to their knowledge, this is the first time that researchers have attempted to apply machine learning algorithms to work management. The researchers described their work as the first step, but a promising indicator, of using AI to help reduce pregnancy complications and maternal mortality.

Abimbola Famuyide, gynecological surgeon at Mayo Clinic and lead author of the study, said in a Mayo Clinic press release that the study represents an important step in caring for pregnant patients and helping them achieve the best results.

“This is the first step towards using algorithms to provide powerful guidance to doctors and midwives when making critical decisions during the labor process,” Famuyide said in the press release. . “Once validated by further research, we believe the algorithm will work in real time, meaning that each new data entry during a pregnant woman’s labor automatically recalculates the risk of an adverse outcome.”

AI could help produce better outcomes for patients and save healthcare systems money, said Bijan Borah, scientific director of health services and outcomes research at the Robert D. Center and Patricia E. Kern of the Mayo Clinic for the science of health care delivery.

“The ability of the AI ​​algorithm to predict individualized risks during the labor process will not only help reduce adverse birth outcomes, but it may also reduce healthcare costs associated with maternal morbidity in the United States. , which have been estimated at more than $30 billion,” Borah said in the Mayo Clinic press release.

President Biden’s administration has focused on reducing maternal mortality. This week, the US Department of Health and Human Services announced that it is investing $20 million to improve maternal and child health.

The COVID-19 pandemic has had an impact on the security of deliveries. Researchers have found an “alarming” increase in maternal mortality during childbirth hospitalization and other pregnancy complications, according to a recent study published in Jama Network Open.

In the AI ​​study, Mayo Clinic researchers analyzed data from the Eunice Kennedy Shriver National Institute of Child Health and Human Development. They used data from the Consortium on Safe Labor, a large database of pregnancy and labor characteristics from 12 medical centers across the country.

The researchers developed a “work risk score” for their analysis. Based on machine learning, the Labor Risk Score is designed to provide more individual insights and serve as an alternative to traditional labor graphs currently used by providers.

Since it’s tied to individual patients, the predictive score could guide providers toward early interventions or allow more time to refer patients who don’t live near a hospital for better care.

“These models may provide an alternative to current practice, which endorses the use of workboards,” the researchers wrote. “Unlike workflow charts, which set constant margins for safe workflow, machine learning models promote the individualization of clinical decisions using each patient’s baseline and workflow characteristics.”

The researchers examined more than 66,000 patients with an average maternal age of around 27 years. More than a third of patients were African American, while almost a third were white, and more than 1 in 5 identified as Hispanic and 4% were Asian/Pacific Islander.

The authors said the study results could not be converted into a printed worksheet due to the complexity of the algorithms, but they said a digital application was being developed to enable clinical use of this emerging tool.

The researchers said further study is needed to use artificial intelligence to help providers care for pregnant patients and identify risks.

About Stephen Ewing

Check Also

Providence’s $712 million expansion project to bring 2 satellite health centers to San Clemente, RMV

SUPPORT THIS INDEPENDENT JOURNALISMThe article you are about to read comes from our journalists doing …