‘They would have been dead’: Hospitals using AI to save lives - Newsweek

While artificial intelligence is often associated with automating administrative work, health care leaders at Newsweek’s AI Health Summit in New York City described how the technology is being used on the clinical front lines to identify serious conditions earlier and give clinicians more time to intervene.

When Tampa General Hospital first deployed AI, it prioritized clinical applications over streamlining back-office tasks, according to John Couris, president and CEO of the Florida Health Sciences Center, which runs the hospital. “I instructed the organization, you will deploy AI first in the clinical environment, period,” he told Newsweek.

For Couris, putting clinical applications first meant focusing AI on areas where it could affect quality, safety and patient outcomes. One of Tampa General’s early applications was with patients afflicted with sepsis and septicemia, which Couris stressed is the, “leading cause of death in our country and arguably in most countries."

“We have saved over 1,000 lives,” Couris said. “These are mothers and fathers and aunts and uncles and grandparents that are home, living. With their families and living their lives, who otherwise would have been dead if it wasn't for the deployment of AI.”

He stressed that the result was not the work of AI alone, crediting doctors, nurses, pharmacists and scientists with helping turn the technology’s insights into better patient outcomes.

Couris said AI gave clinicians greater visibility into septicemia, helping them move from chasing it to predicting whether a patient might become septic. “It has been an absolute game changer,” he said.

The hospital executive explained that the current 48-hour mortality rate at its academic medical center is below 5%. He said the comparable rate in the U.S. is somewhere between 15% and 18%, while some hospitals have mortality rates as high as 30%.

At Sanford Health, AI is also being used to identify disease risk earlier. Sanford's Chief Transformation Officer Tommy Ibrahim said the organization embedded the technology into its electronic medical records.

“We've been able to double the amount of screening that we do for chronic kidney diseases,” Ibrahim said. “And we have tripled the diagnosis rate as well.

“That’s real impact and real quality of care that we're bringing to our communities. And intervening earlier and actually saving people from developing progression of chronic kidney disease and ultimately going on dialysis.”

Ibrahim also described a colorectal cancer case in rural North Dakota in which an algorithm identified hidden risk factors in a patient who otherwise would not have been screened. The patient was referred for a colonoscopy, where doctors detected precancerous lesions and were able to act quickly.

Sanford is also seeing administrative gains, with automation of billing and payment tasks projected to save 100,000 hours this year – equivalent to about 50 full-time employees, Ibrahim said.

He stressed that does not mean job cuts but instead AI frees employees to focus on other work.

At Mount Sinai Health System, CEO Dr Brendan Carr said AI can help newborns at risk of intracranial bleeding.

“Neonates are much more likely to have intracranial bleeds,” he said, explaining that the condition can be difficult to detect because early signs may involve, “some sort of small little twitch or little hemiparalysis.”

But, he said, “if you have a baby on camera, you can see it sooner. And if you can see it sooner, you can intervene quicker.”