To help newborns in the neonatal intensive care unit who have trouble breathing, researchers at the University of Wisconsin-Madison School of Medicine and Public Health are developing an artificial intelligence-based “digital mentor” to train doctors.
Neonatal babies, a reference to those who are born too soon, can have issues breathing because their lungs are underdeveloped.
To improve their breathing, a high-risk intubation, where a doctor places a breathing tube in a baby’s windpipe so a machine can help them breathe, is often needed.
Since the intubation process is difficult, the school looked for a new technology to improve the process.
“We realized we had a clinical problem: How can we teach this skill as safely and quickly as possible?” Dr. Ryan McAdams, professor of pediatrics at the UW medical school, said in a statement. “We turned to our colleagues on campus with expertise in deep learning and AI to help leverage new technology to develop a solution.”
The project used video laryngoscopies to collect data and develop technology to help doctors safely place the tubes.
The technology does not replace physicians who perform the procedure, it simply aids medical professionals, especially in understaffed rural hospitals.
“We compare this to a backup camera on a car,” McAdams said. “It provides visual cues to improve situational awareness by circling and highlighting key areas, but the technology does not replace the person performing the task.
“Instead, it serves as a strong helper or a good coach for a learner,” he said. “This feedback can be helpful for experienced clinicians as well.”
