A European Medicines Agency committee has approved the use of an artificial intelligence tool called AIM-NASH in clinical trials to assess the severity of a fatty liver disease known as metabolic dysfunction-associated steatohepatitis (MASH). This challenging condition affects approximately 1.5% to 6.5% of adults in the U.S., according to the American Liver Foundation.
The AIM-NASH tool utilizes a machine learning model developed from over 100,000 annotations provided by 59 pathologists, who evaluated more than 5,000 liver biopsies across nine large clinical trials. The EMA's human medicines committee (CHMP) noted that the AI tool can reliably determine disease activity from biopsies with less variability than the current standard, which depends on a consensus among three pathologists.
Based on this evidence, the CHMP has deemed the results generated by AIM-NASH as scientifically valid, thereby aiding researchers in obtaining clearer evidence regarding the efficacy of new treatments in clinical trials.
Currently, Madrigal Pharmaceuticals' Rezdiffra is the only drug approved in the U.S. for MASH. Other pharmaceutical companies, including Novo Nordisk and Eli Lilly, are also conducting trials for their popular GLP-1 treatments aimed at addressing this liver disease.