The FDA has qualified the first AI-based drug development tool to support metabolic dysfunction-associated steatohepatitis clinical trials.
The cloud-based tool, AI-Based Histologic Measurement of NASH (AIM-NASH), is designed to assist pathologists in assessing liver biopsy images, according to a Dec. 8 news release. It evaluates disease activity by scoring steatosis, hepatocellular ballooning, lobular inflammation and fibrosis according to the NASH Clinical Research Network scoring system.
AIM-NASH uses AI to analyze digital images of liver tissue, but human pathologists remain responsible for interpreting the results. They review the entire slide and AIM-NASH output before accepting or rejecting the scores.
The FDA said AIM-NASH could help standardize histologic scoring and reduce the time and resources required for drug development, a process often hindered by variability and the need for multiple expert reviewers.
Qualification was supported by studies showing AI-assisted assessments were comparable to expert consensus, with agreement levels similar to those seen between individual pathologists and consensus scores.
