• Politics
  • Diversity, equity and inclusion
  • Financial Decision Making
  • Telehealth
  • Patient Experience
  • Leadership
  • Point of Care Tools
  • Product Solutions
  • Management
  • Technology
  • Healthcare Transformation
  • Data + Technology
  • Safer Hospitals
  • Business
  • Providers in Practice
  • Mergers and Acquisitions
  • AI & Data Analytics
  • Cybersecurity
  • Interoperability & EHRs
  • Medical Devices
  • Pop Health Tech
  • Precision Medicine
  • Virtual Care
  • Health equity

Using AI to predict risks for pregnancy and delivery


Mayo Clinic researchers say artificial intelligence can help patients have better outcomes and could potentially lower costs for health systems.

Researchers from the Mayo Clinic have found that artificial intelligence can be used to help analyze if pregnant patients can have a safe delivery and avoid complications.

The researchers examined more than 700 health factors in more than 66,000 deliveries, according to a recent study published in PLOS ONE.

“Utilization of machine-learning–based algorithms may provide a dynamic, cumulative, and individualized model for prediction of outcomes of vaginal delivery and facilitation of intrapartum decision making,” the authors wrote.

Researchers said to their knowledge, this is the first time that researchers have attempted to apply machine learning algorithms to managing labor. The researchers described their work as the initial step, but a promising indicator, of the use in AI to help reduce pregnancy complications and maternal death.

Abimbola Famuyide, a gynecologic surgeon at the Mayo Clinic and the senior author of the study, said in a Mayo Clinic news release the study represents an important step in caring for pregnant patients and helping them to achieve the best outcomes.

"This is the first step to using algorithms in providing powerful guidance to physicians and midwives as they make critical decisions during the labor process," Famuyide said in the news release. "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 labor automatically recalculate the risk of adverse outcome.”

AI could help produce better outcomes for patients and save health systems money, said Bijan Borah, scientific director of health services and outcomes research in the Mayo Clinic's Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery.

"The AI algorithm’s ability to predict individualized risks during the labor process will not only help reduce adverse birth outcomes but it can also reduce healthcare costs associated with maternal morbidity in the U.S., which has been estimated to be over $30 billion," Borah said in the Mayo Clinic news release.

President Biden’s administration has focused on reducing maternal mortality. This week, the U.S. Department of Health and Human Services said it is investing $20 million to improve maternal and infant health.

The COVID-19 pandemic has had an impact on safety in delivery. Researchers have found an “alarming” rise in maternal death during delivery hospitalization and other pregnancy complications, according to a recent study 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 around the country.

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

Since it is tied to individual patients, the predictive score could guide providers to early interventions, or allow more time to transfer patients who don’t live close to a hospital to get better care.

“These models may provide an alternative to current practice, which endorses the use of labor charts,” the researchers wrote. “In contrast to labor charts, which set constant margins to safe labor course, machine-learning models promote individualization of clinical decisions using baseline and labor characteristics of each patient.”

The researchers examined more than 66,000 patients with a mean maternal age of about 27. More than a third of the patients were African-American, while nearly a third were white, and more than 1 in 5 were identified as Hispanic, and 4% were Asian/Pacific Islander.

The authors said the study’s results can’t be converted to a printed labor chart because of the complexity of the algorithms, but they said a digital application is being developed to allow for clinical use of this emerging tool.

Researchers said further study is necessary to utilize artificial intelligence in helping providers care for pregnant patients and identify risks.

Related Videos
Image credit: ©Shevchukandrey - stock.adobe.com
Image: Ron Southwick, Chief Healthcare Executive
Image credit: HIMSS
Related Content
© 2024 MJH Life Sciences

All rights reserved.