As recent studies highlight the need for a closer focus on maternal morbidity and mortality in the U.S., a new initiative at Brigham and Women’s Hospital is aimed at enhancing safety within a key area of childbirth risk: spinal anesthesia during C-section births.
In nearly three-quarters of patients who receive spinal anesthetic prior to C-section, the medication comes with an undesirable drop in blood pressure. A vasopressor medication is used to counteract the effect—producing a complex push-pull in which anesthesiologists work to maintain equilibrium with close monitoring and manual calculations. The consequences of too much aberration from this middle ground can be serious: nausea, vomiting, light-headedness, and in rare cases, stroke.
While recovering from her own C-section two years ago, Vesela Kovacheva, MD, PhD, of the Department of Anesthesiology, Perioperative and Pain Medicine, realized that technology could be applied to enhance accuracy—and improve birth safety—for patients. “The delivery of their baby is a very special time for our patients,” Dr. Kovacheva says. “Yet it’s also a very busy time for us as clinicians. We’re doing all of these things simultaneously while taking care of an anxious, awake patient and preparing for major abdominal surgery. In a couple of minutes, the math becomes too complex for any human to do, and we may under- or over-treat the patient.”
Before long, Dr. Kovacheva got to work on a software algorithm that can apply machine learning to more efficiently monitor and react to maternal blood pressure changes in real-time. The technology, under development by Dr. Kovacheva and colleagues, would compare patient data against a large database of similar scenarios to identify when medication needs to be adjusted, and alert an anesthesiologist when dose changes are necessary.
“The way machine learning works is that it utilizes previous patient records and ‘teaches’ itself what should be done, based on what we’ve done in the past,” she says. “Our hope is that this software will delegate a tedious, error-prone task to the machine so that I, as an anesthesiologist, could hold my patient’s hand, talk to them, and focus on other aspects of their care.”
Read more about Dr. Kovacheva’s research here.