Coronavirus: UPMC To Fast-Track Multiple Treatment Approaches

PITTSBURGH, PA - Pittsburgh's largest health care provider on Thursday launched a "learning while doing" clinical trial that will fast-track multiple COVID-19 treatment approaches at dozens of hospitals.

Developed by University of Pittsburgh School of Medicine researchers, the trial will occur throughout UPMC's 40-hospital system and include different treatment combinations. They will include the anti-malarial drug hydroxychloroquine, steroids and medications called immunomodulators that alter the responsiveness of the immune system.

Researchers believe this approach, detailed in a study published Thursday in the Annals of the American Thoracic Society, should help doctors decide between quickly adopting new therapies and waiting until they are tested in longer clinical trials.

“We must throw out old ways of thinking and fuse clinical care and clinical research into one extremely efficient system,” said Dr. Derek Angus, professor and chair of Pitt's Department of Critical Care Medicine. “This is an unprecedented pandemic and we need an unprecedented response.”

Don't miss local and statewide news about coronavirus developments and precautions. Sign up for Patch news alerts and daily newsletters.

Angus said the clinical trial model relies on a type of artificial intelligence known as reinforcement learning to help identify the best, evidence-backed therapy for COVID-19 much faster than using the traditional scientific approach. This method allows researchers to rapidly test multiple treatment approaches simultaneously, at a lower cost and with fewer patients than traditional clinical trials.

All trial participants will receive the current standard of care, and most also will receive one, two or three of the experimental treatment options. This means that, at launch, only 12.5 percent of participants will be strictly assigned to the placebo arm of the trial and, within weeks, researchers
expect that about 99 percent of patients will be receiving one or more active therapies specifically targeting COVID-19.

If one of the treatments shows early signs of performing better than the others, patients will be automatically enrolled more often into that treatment option. Poorly performing options will be e
quickly discontinued.

“This allows us to always rapidly identify which treatment works best, while keeping the number of patients needed to achieve statistical significance low,” Angus said.. “It also means we get the best treatment to the most patients right out of the gate.”