FDA authorizes use of 1st AI tool to speed MASH clinical trials
U.S. OK follows similar authorization in Europe
The U.S. Food and Drug Administration (FDA) has authorized the use of the first artificial intelligence (AI) drug-development tool for use in clinical trials of metabolic dysfunction-associated steatohepatitis (MASH), a severe form of fatty liver disease.
The agency qualified PathAI‘s tool, dubbed AIM-MASH, to help pathologists analyze liver biopsies. PATH-AI said the tool “offers a more efficient, standardized, and reproducible approach” to scoring liver biopsy components used for clinical trial enrollment and monitoring responses to therapies.
The FDA said the authorization is the first of its type for an AI tool. AIM-MASH “could help standardize [liver biopsy] assessment and reduce the time and resources needed for MASH drug development,” the agency said in a press release.
The FDA’s decision follows a similar authorization from the European Medicines Agency (EMA).
AI could ‘transform pathology’
“We’re proud to have worked collaboratively with FDA, EMA, industry partners and advisors to achieve the first FDA and EMA qualification of an AI-based biomarker via their biomarker qualification programs,” Andy Beck, MD, PhD, co-founder and CEO of PathAI, said in a company press release. “Dual recognition from U.S. and EU regulators underscores our commitment to rigorous validation and responsible deployment of AI to transform pathology and improve patient outcomes.”
Metabolic dysfunction-associated steatotic liver disease (MASLD) is characterized by the buildup of excessive fat in the liver in people who have underlying metabolic issues, such as high blood pressure or diabetes. In severe cases, the condition can progress to MASH, where the accumulation of liver fat leads to liver inflammation and scarring. This can set the stage for life-threatening complications such as liver cancer.
Researchers in MASH clinical trials typically collect biopsies (small samples of liver tissue) at the beginning and end of a study to assess molecular-level changes in liver fat, inflammation, and scarring. Currently, human experts examine the slides, but these analyses are time-consuming and prone to human error.
The AIM-MASH tool is designed to allow one person to do a job typically handled by several people. PathAI says extensive testing has shown that the AI tool can measure disease-relevant changes, such as liver fat and scarring, with accuracy on par with or superior to that of expert pathologists.
AIM-MASH’s qualification for MASH clinical trials by the FDA and EMA essentially confirms that the tool can be used to support regulatory applications, including those seeking approval for new medicines. As long as drug developers use the tool within specific parameters outlined by the agencies, developers don’t have to provide further documentation to support the validity of AIM-MASH.
“Dual qualification by the EMA and the FDA gives sponsors a regulator approved path to use AI-assisted histology for Phases 2 and 3 MASH clinical trial enrollment and endpoint assessment,” said Naim Alkhouri, MD, medical director of research at the Clinical Research Institute of Ohio and director of the institute’s fatty liver program. “For MASH trials worldwide, that means greater consistency, reproducibility, and confidence in histologic endpoints.”
About the Author
