EU Medicines Agency assesses first AI diagnosis as "scientifically valid"
For the first time, the European Medicines Agency has recognized AI software for the diagnosis of fatty liver hepatitis as scientifically valid.
Photomicrograph of hepatosteatosis showing an accumulation of fat in liver cells, known as fatty liver disease.
(Image: Kateryna Kon/Shutterstock.com)
The Committee for Medicinal Products for Human Use (CHMP) of the European Medicines Agency (EMA) has issued its first Qualification Opinion on an AI-based tool. The tool, called AIM-NASH (Artificial Intelligence-Based Measurement of Non-alcoholic Steatohepatitis Histology) from Boston-based Path AI, supports pathologists in analyzing liver biopsy scans to assess histology in a qualified manner. It is designed to help determine the severity of a disease in which fat accumulates in the liver and causes inflammation, irritation and scarring over time.
Metabolic dysfunction-associated steatohepatitis (MASH) is associated with obesity, type 2 diabetes, high blood pressure, abnormal cholesterol and abdominal fat, according to the EMA. If left untreated, it can lead to advanced liver disease.
The AIM-NASH tool aims to improve the reliability and efficiency of clinical trials for new MASH treatments and is specifically designed for NASH/MASH clinical research. The CHMP had stated that findings obtained with this tool would be recognized as scientifically valid in future applications. A study on the process behind AIM-NASH has also been published in Nature.
Videos by heise
According to the EMA, new MASH treatments are often tested based on liver biopsies, in which small pieces of liver tissue are removed. These biopsies are intended to prove the effectiveness of new, experimental drugs. According to the EMA, AIM-NASH uses a machine-learning process that has been trained on more than 100,000 annotations from 59 pathologists who have assessed over 5,000 liver biopsies in nine large clinical trials. The EMA is coordinating all its AI activities according to a multi-year AI work plan to ensure that AI is used safely and responsibly in the European medicines network.
(mack)
