March 20 (Reuters) - A European Medicines Agency

committee, on Thursday, accepted the use of an artificial

intelligence (AI) tool called AIM-NASH in clinical trials to

help identify the severity of a type of fatty liver disease.

The condition, called metabolic dysfunction-associated

steatohepatitis, or MASH, is a difficult-to-treat disease that

affects around 1.5% to 6.5% of adults in the U.S., according to

the American Liver Foundation.

The AI-based AIM-NASH tool employs a machine learning

model trained on more than 100,000 annotations from 59

pathologists who assessed over 5,000 liver biopsies across nine

large clinical trials.

The EMA's human medicines committee (CHMP) said evidence

showed the AI tool can reliably determine disease activity from

biopsies with less variability than the current standard in

trials that rely on a consensus of three pathologists.

On that basis, the CHMP concluded, it can accept evidence

generated by the tool as scientifically valid, which will help

researchers obtain clearer evidence on the benefits of new

treatments in clinical trials.

Currently, Madrigal Pharmaceuticals' ( MDGL ), Rezdiffra is

the only U.S.-approved drug for MASH.

Drugmakers such as Novo Nordisk and Eli Lilly ( LLY )

are also conducting trials with their blockbuster GLP-1

treatments to treat patients with the liver disease.