European Medicines Agency Qualifies Unlearn’s AI-powered Method for Running Smaller, Faster Clinical Trials

PROCOVA procedure outlines a clear regulatory-qualified framework for implementing AI-generated prognostic digital twins in clinical trials

SAN FRANCISCO--()--Unlearn®, the only artificial intelligence (AI) company developing prognostic digital twins to run smaller, faster clinical trials, today announced that the European Medicines Agency (EMA) has released its final favorable qualification opinion providing a regulatory framework for the application of the company’s TwinRCT™ solution in Phase 2 and 3 clinical trials. The three-step PROCOVA™ procedure (patent-pending) is the foundation for TwinRCTs and describes how to use patient-specific prognostic scores derived from digital twins to reduce clinical trial sizes while controlling Type-1 error rates. This qualification opinion represents the first time a regulatory body has formally supported a machine learning-based method for reducing sample size in pivotal trials.

Unlearn was founded to pioneer AI to eliminate trial and error in medicine. Today, their TwinRCT solution reduces control arm sizes by up to 35%, giving more trial patients the opportunity to receive the experimental treatment. TwinRCTs significantly shorten timelines, helping to speed new lifesaving therapies to patients.

“Since our founding, our team has focused on reshaping the future of medicine with digital twin technology. The EMA’s adoption of our novel PROCOVA procedure using digital twins is a historic milestone on the path toward achieving that ultimate goal,” said Charles Fisher, Ph.D., founder and CEO of Unlearn. “PROCOVA is a key part of our mission to innovate in regulatory-acceptable ways. With Unlearn’s guidance, our partners now have a framework that enables them to confidently implement TwinRCTs in alignment with the EMA’s rigorous standards.”

In their final opinion, the EMA stated that the Committee for Medicinal Products for Human Use (CHMP) “qualifies PROCOVA” and that “the proposed procedures could enable increases in power and/or decreases in sample size in phase 2 and 3 clinical trials with continuous outcomes.” The EMA’s validation of Unlearn’s cutting-edge technology signifies broader regulatory acceptance of AI in clinical development. Unlearn will continue to work with regulators while advancing machine learning to chart more efficient and patient-centric clinical pathways in the future.

For more information on the final EMA qualification opinion, please visit Unlearn’s website to download a summary and a step-by-step guide for the practical application of PROCOVA.

About Unlearn

Founded in 2017, Unlearn brings together a world-class team of experts across pharma, physics, machine learning, and business who share a vision of pioneering AI to eliminate trial and error in medicine. Unlearn.AI is the only company creating TwinRCTs, which combine AI, prognostic digital twins, and novel statistical methods to run clinical trials requiring fewer patients in the control arm. Unlearn’s technology is used by leading global pharmaceutical companies, including Merck KGaA, Darmstadt, Germany, and has been published in conference abstracts and scientific journals, including Scientific Reports - Nature and The International Journal of Biostatistics. The European Medicines Agency (EMA) qualifies Unlearn’s PROCOVA™ procedure, which provides the regulatory framework for the application of the TwinRCTs to Phase 2 and 3 clinical trials. For more information, please visit or follow @UnlearnAI on Twitter, @unlearn-ai on LinkedIn.


Colin Sanford