FDA Pilots AI for Near Real-Time Clinical Trial Monitoring

The U.S. Food and Drug Administration is testing the use of artificial intelligence and data science tools in real-time clinical trials as part of an effort to accelerate the development of new drug therapies.

According to the agency, traditional clinical development can be slowed by data and procedural bottlenecks that delay how quickly key trial findings reach regulators. The FDA said two proof-of-concept projects involving AstraZeneca and Amgen have already achieved successful initiation as part of the initiative.

AstraZeneca is conducting a Phase 2 multi-site clinical trial called Traverse involving patients with untreated mantle cell lymphoma. The study includes participation from the University of Texas MD Anderson Cancer Center and the University of Pennsylvania.

Amgen is conducting a Phase 1b trial called Stream-SCLC involving patients with limited-stage small cell lung carcinoma. Final site selection for the study remains in process.

The FDA said it met with sponsors from both companies to establish criteria for reporting key data signals, including efficacy outcomes and safety concerns, during the course of the trials.

The agency plans to expand the two proof-of-concept efforts into a broader pilot program. In a request for information, the FDA sought public input on how AI-enabled technologies could improve the efficiency, speed, and quality of decision-making in early-phase clinical trials.

The request for information asks stakeholders to provide feedback on pilot program design and implementation, evaluation metrics, success criteria, infrastructure requirements, and the types of clinical trials that may benefit most from the use of AI technologies. The FDA also requested comments on how a pilot program could accommodate participants with varying levels of AI capability.

The agency stated that most clinical development currently occurs in separate phases conducted under distinct protocols and studies, which can create pauses between phases and slow product development timelines.

The FDA did not disclose which AI or data science technologies are being used in the AstraZeneca and Amgen proof-of-concept projects.

The agency said it intends to release final selection criteria for the wider pilot program in July and complete pilot selections in August.

Some experts said the FDA’s adoption of AI in the clinical trial process represents a potentially important step in modernizing trial oversight and review processes. Areas identified as potential applications for AI tools include adverse-event signal detection, protocol-deviation monitoring, document review, and pattern recognition across large clinical data submissions.

The FDA indicated that its long-term objective is to move toward real-time, continuous clinical trials across multiple phases of drug development, with FDA scientists able to review safety signals and endpoints as studies progress.