AI and EHR Could Expedite Matching Patients with Clinical Trials
According to a survey by UPMC's Center for Connected Medicine (CCM), most healthcare executives believe that artificial intelligence (AI) could help identify and recruit patients for clinical trials, reducing the current time and expense required.
In a survey published earlier this year, among 58 payer and provider senior executives, nearly two-thirds (64 percent) of respondents said the most time-consuming hurdle for launching clinical trials is finding suitable patients. In 61 percent of survey respondents, using AI to quickly scan medical records to find eligible patients was seen as “playing a critical role.”
"Clinical trials are an important part of providing life-changing care to our patients. However, it can be a significant challenge to match patients to studies," said Oscar Marroquin, M.D., chief healthcare and data analytics officer at UPMC, and a founding partner of the CCM. "I'm excited by the potential for AI to help medical centers do a better job of finding and recruiting trial participants."
The CCM report cited a 2020 study in the Journal of Medical Internet Research, which found that “80 percent of trials don't meet initial enrollment targets of timelines, with delays resulting in lost revenues of as much as $8 million a day for drug development companies.” The report also pointed out that the use of AI in patient matching and recruitment will allow organizations to participate in more trials in the future.
Marroquin said CCM has "already seen the benefits of using natural language processing to harness and analyze the vast quantities of unstructured data in healthcare to better understand the conditions of our patients. Applying these techniques for clinical trial matching would be an advantage for health systems, industry and patients."
Looking ahead, the CCM report also identified “disease management and prediction as the top use for AI at health systems.” Over the next two years, survey respondents said their AI investments will be “aimed primarily around operational optimization.”
