Inside STAT: At Mayo Clinic, AI engineers face an ‘acid test’ 

MACHINE LEARNING ENGINEER ZACHI ATTAI OBSERVES A PACEMAKER SURGERY AT MAYO CLINIC. (SARAH STACKE FOR STAT)

Artificial intelligence has yielded plenty of headline-grabbing papers, but the technology’s application in health care is still facing its true test: ensuring improved real-world outcomes for patients. At the Mayo Clinic in Rochester, Minn., meeting the challenge takes the form of inviting 33-year old software engineer Zachi Attia into the cardiac operating rooms. Attia has no medical training or surgical experience, but by working alongside physicians, he can see patients with diverse backgrounds and complex medical issues. “[B]ecause I’m here, I can go to physicians with examples from the data and ask, ‘What do you think is happening here, or what is going on there?’ And then I can improve the algorithm,” Attia tells STAT’s Casey Ross. Read more about Mayo's efforts here in the first article in a yearlong series exploring the use of AI in health care, a project partly funded by a grant from the Commonwealth Fund.