Left to right: Marie Bradley, Anindita Saha, and Hussein Ezzeldin of the FDA (Credit: Joanne S. Eglovitch)
PHILADELPHIA – U.S. Food and Drug Administration (FDA) officials discussed strategies for integrating artificial intelligence (AI) and real-world evidence (RWE) to accelerate drug development during a panel discussion at the DIA Global Annual Meeting on Tuesday. Officials noted that the number of submissions utilizing both AI and RWE is increasing.
“We really want to advance AI and RWE as complementary tools to advance drug development,” said Marie Bradley, senior RWE advisor in the Office of Health Policy at the Center for Drug Evaluation and Research (CDER), during a panel discussion with other FDA officials.
“Where is the convergence point for how AI can enhance RWE?” Bradley asked her colleagues.
Commenting on the capabilities of AI, Hussein Ezzeldin, Senior Policy Advisor in the CDER Office of Health Policy, said: “What is AI good at? It’s good at finding patterns in data. This is an area where we’re seeing a lot of progress, where we can look at large amounts of data and extract specific features. Patient identification is another area where we can speed up patient enrollment. Signal identification could also be another area.” He added that AI is also good at phenotyping.
When asked to explain the limitations of AI, he said that AI models are “very good at finding patterns, but bad at finding rare events. Using AI to find rare events may not give you what you’re looking for.”
Officials also discussed the growth of AI and real-world data (RWD) programs at FDA. According to a recent report posted on the FDA’s website, the number of new drug applications (NDAs) and biologics license applications (BLAs) incorporating RWE increased from four in fiscal year 2023 to 10 in fiscal year 2025. This report was prepared under the Prescription Drug User Fee Act VII (PDUFA) agreement, under which FDA commits to reporting RWD application numbers to CDER and the Center for Biologics Evaluation and Research (CBER).
Mr. Bradley also noted that on September 23, 2025, FDA released a case study demonstrating how RWE has been utilized to support regulatory decisions at CDER and CBER since 2011. This includes instances where product approvals, label changes, and evaluations were deemed not to require regulatory action. An updated version was published on June 3, 2026, to include more recent examples and expand coverage to include the Center for Devices and Radiological Health (CDRH), reflecting the broader use of RWE across centers.
Anindita Saha, associate director of strategic initiatives for the Digital Health Center of Excellence within CDRH, said CDER and CBER received more than 1,000 submissions that incorporated AI elements, a significant increase from just one submission in 2016. The majority of these submissions are in the field of oncology, followed by gastroenterology, neurology, and psychiatry. Clinical trials use AI to set endpoints, select patients, and predict outcomes.
“There’s a lot of AI being used in non-clinical research, manufacturing and post-marketing,” Saha says.
Mr. Bradley asked Mr. Saha to discuss some of the comments received regarding the draft guidance on the use of AI in regulatory decision-making for drugs and biologics, published in January 2025.
“We heard loud and clear that industry wanted practical examples and practical use cases,” Saha said.
He was also asked by an audience member whether the FDA plans to release any information about the 1,000 applications that incorporate AI elements.
Saha said some of this information is confidential and proprietary and the agency cannot share all of it. However, she added, “We are still trying to figure out the best way to disseminate this information.”
