UPMC uses AI to accelerate testing of coronavirus treatments

• Chris Potter/WESA
  BioRecent Stories

  

  Nearly three decades after leaving home for college, Chris Potter now lives four miles from the house he grew up in -- a testament either to the charm of the South Hills or to a simple lack of ambition. In the intervening years, Potter held a variety of jobs, including asbestos abatement engineer and ice-cream truck driver. He has also worked for a number of local media outlets, only some of which then went out of business. After serving as the editor of Pittsburgh City Paper for a decade, he covered politics and government at the Pittsburgh Post-Gazette. He has won some awards during the course of his quarter-century journalistic career, but then even a blind squirrel sometimes digs up an acorn.

 Julio Cortez / AP Photo

FILE- In this July 10, 2018, file photo bottles of medicine ride on a belt at a mail-in pharmacy warehouse in Florence, N.J.

There is no shortage of potential treatments for the coronavirus—the real shortage is the time to figure out which ones work best. But UPMC says it plans to use artificial intelligence to accelerate the timetable for winnowing out approaches that don’t work. And among the first drugs to be tested will be anti-malarial medication hydroxychloroquine, which President Donald Trump has touted in press conferences.

Researchers call the approach REMAP, for Randomized, Embedded, Multi-factorial, Adaptive Platform. It was devised a half-decade ago, and it allows researchers to pursue a number of potential treatments at the same time, using fewer patients than standalone clinical trials. The treatments are tested side-by-side, with the AI directing more patients to those that show the most promise, though a process called “reinforcement learning.”

In a statement, UPMC and the University of Pittsburgh’s School of Medicine call this a “learning by doing” approach, and says it ensures that doctors “are always betting on the winning horse in the moment, and poorly performing options are quickly discontinued.”

“This allows us to always rapidly identify which treatment works best, while keeping the number of patients needed … low,” said Derek Angus, who participated in a worldwide development of the approach, and who is professor and chair of the Pitt’s Department of Critical Care Medicine. “It also means we get the best treatment to the most patients right out of the gate.”

Researchers are set to discuss the approach further at a Thursday-morning press conference. But in the statement, UPMC says it will join its research – which it is billing as the UPMC-REMAP-COVID19 trial – to similar efforts elsewhere in North America, Europe, and Australia and New Zealand. The effort is backed by governments and other institutions, as well as UPMC Enterprises, which provides venture capital to health care entrepreneurs.

For its part, UPMC plans to use the approach across its 40 hospitals, starting with several proposed coronavirus treatments – including steroids and hydroxychloroquine. Drugs can be tried in various dosages and combinations – a process which UPMC likens to a chef comparing how diners respond to various meals. New drugs that come online can be added to the test as time goes on.

One-eighth of the patients in the trials will be given placebos at the outset, though UPMC says that “within weeks,” only 1 percent of participants will be receiving placebos.

UPMC boasts that its research will be augmented by its electronic-health record system – a platform that Angus says helps build a “one-stop shop” that allows any patient to join the trial.

Using artificial intelligence in medical testing is not a new idea. The randomized control trials which have been the baseline research tool for decades, are time-consuming, and have only a 10 percent success rate at producing an approved medication. But the coronavirus — for which there is no immunity, no treatment, and no vaccine — has given new impetus to the drive to find a faster approch.

“In a pandemic, doctors will not have the time to debate the pros and cons of every possible clinical trial,” Angus said in the statement. “This is an unprecedented pandemic and we need an unprecedented response.”

The Purple Buck Newsletter

Get insights into WITF’s newsroom and an invitation to join in the pursuit of trustworthy journalism.

Hidden

Groups

News

CAPTCHA

Email(Required)

Phone

This field is for validation purposes and should be left unchanged.