- Artificial Intelligence Model Detects Parkinson’s From Breathing Patterns
- Artificial Intelligence Model Tracks Spread of Lyme Disease
The researchers tested the algorithm on data gathered from 66,586 delivery episodes, reviewing over 700 variables. Of the total cases examined, 21.68 percent resulted in unfavorable labor outcomes with a baseline labor risk score above 35 percent. The baseline labor risk score did not exceed 25 percent for those with favorable outcomes.
Researchers concluded that the calculation of labor risk score was applicable and accurate. They also noted secondary benefits of using the model, including lowering costs.
"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," said Bijan Borah, PhD, the Robert D. and Patricia E. Kern Scientific Director for Health Services and Outcomes Research at Mayo Clinic, in a press release.
Further, Mayo Clinic researchers plan on using the model within labor units as part of validation studies.
"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," says Abimbola Famuyide, MD, a Mayo Clinic OB-GYN and senior author of the study, in the press release.
Recently, clinicians have successfully deployed various risk prediction models to enhance patient care.
In June, a study published in the Journal of Medical Internet Research found that clinical risk prediction models successfully enhanced care for those suffering from sepsis, delirium, and acute kidney injury.
More research from March found that a risk prediction model successfully identified opioid misuse. Researchers also found this tool helpful in determining the appropriate level of opioids to prescribe to patients after an operation.
Another study published in January found that incorporating various factors, such as coronary 18F-NaF uptake on PET and quantitative coronary plaque characteristics on CT angiography, into an AI model allowed providers to better understand which patients may be at high risk for heart attack.
By 