US FDA Approves AIM-NASH, First AI Tool for Liver Disease Trials

The US Food and Drug Administration has approved AIM-NASH, the world’s first AI-based tool designed to support liver disease drug trials. The technology aims to make biopsy interpretation for metabolic dysfunction-associated steatohepatitis (MASH) faster, more consistent and more reliable for clinical research.

AI Innovation for Liver Biopsy Assessment

AIM-NASH analyses digital images of liver biopsy samples and scores key markers of liver injury. These include steatosis, hepatocellular ballooning, lobular inflammation and fibrosis stage. By providing quantified, standardised scoring, the tool helps pathologists streamline assessments that are traditionally time-consuming and subject to variability.

How AIM-NASH Supports Clinical Trials

In current MASH trials, multiple experts independently review each biopsy, often leading to delays and inconsistent scoring. AIM-NASH reduces this bottleneck by producing rapid AI-generated scores aligned with the NASH Clinical Research Network system. Human oversight remains central, as pathologists review full-slide images alongside AI outputs before confirming results.

Why Accurate MASH Diagnosis Matters

MASH is a progressive form of fatty liver disease characterised by excess fat, inflammation and scarring. If untreated, it may advance to cirrhosis, liver failure or cancer. Improving diagnostic accuracy and consistency is therefore crucial for evaluating new therapies and accelerating drug development pipelines.

Exam Oriented Facts

• AIM-NASH is the first FDA-approved AI tool for liver disease drug trials.
• It evaluates steatosis, inflammation and fibrosis from digital biopsy images.
• It follows the NASH Clinical Research Network scoring system.
• Pathologists retain final authority over AI-assisted biopsy interpretations.

Transforming Drug Research With AI Integration

The FDA notes that AIM-NASH may significantly cut the time and resources needed for MASH drug development. By standardising histologic assessments and reducing inter-observer variability, the tool represents a major step toward integrating AI into clinical research workflows and improving patient outcomes.