The machine learning algorithms — a type of device known as Software as a Medical Device (SaMD), where the software is the device rather than a mechanical device — analyze patterns of changes for women in labor.
“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,” senior author Dr. Abimbola Famuyide said in a 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. This may help reduce the rate of cesarean delivery, and maternal and neonatal complications.”
The researchers examined more than 700 clinical and obstetric factors in 66,586 deliveries from the time of admission and during labor progression, they said in a study published in PLOS ONE. The data included patient baseline characteristics, the patient’s most recent clinical assessment and cumulative labor progress from admission.
“It is very individualized to the person in labor,” Famuyide said.
The risk-prediction models could provide an alternative to conventional labor charts and promote individualization of clinical decisions using baseline and labor characteristics of each patient. They could also give patients in rural or remote settings more warning time to transfer somewhere with a higher level of care.
The models have been implemented in labor units, with validation studies currently assessing the outcomes.