A new type of clinical trial developed at UPMC aims to split the difference between quickly adopting potential COVID-19 therapies and waiting for traditional clinical trials to finish.

Using artificial intelligence, the trial will be an “adaptive platform trial,” allowing doctors to move between combinations of drugs — including the anti-malarial drug hydroxychloroquine, steroids and immunomodulators — based on care data from patients worldwide.

“The trial design uses a machine-learning model that incorporates data from patients enrolled across the world to continuously learn which therapies and combinations of therapies are performing best,” researcher Scott Berry said in a news release. “Last week, the Chief Medical Officer of the United Kingdom's National Health Service urged every hospital in the country to participate in this trial. As more institutions join, the model learns faster.”

The testing platform will be implemented at all 40 UPMC hospitals, including at Passavant-Cranberry, and patients with COVID-19 will have the choice of whether to opt-in to the trial or not.

Only about one-eighth of patients enrolled in the trial will be on a placebo when treatment starts. But weeks in, the researchers expect nearly all patients will be on an active drug, according to Dr. Derek Angus, professor and chairman of the University of Pittsburgh's Department of Critical Care Medicine.

While most clinical trials are not widely implemented at point-of-care sites, Angus said, the “learning-while-doing” approach is necessary in the time of the coronavirus pandemic.

“We must throw out old ways of thinking and fuse clinical care and clinical research into one extremely efficient system,” he said. “This is an unprecedented pandemic and we need an unprecedented response.”

The trial also extends beyond UPMC's network, including patients in North America, Europe, Australia and New Zealand.

Because it takes an approach of learning-while-doing, more patients will be enrolled into a treatment option if that drug or combination of drugs shows promise in treatment. Likewise, poorly performing treatments will be 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.”