FDA Qualifies First AI Drug Development Tool

The U.S. Food and Drug Administration (FDA) has approved the first artificial intelligence (AI) drug development tool for use in clinical trials.

AI Drug Development Tool for Use in "MASH" Clinical Trials

Metabolic dysfunction-associated steatohepatitis (MASH) can lead to cirrhosis, hepatic decompensation, liver cancer, the need for a liver transplant, or death. In current MASH clinical trials, multiple experts independently assess liver histology, a time-consuming process complicated by variable scoring. Thus, the new AI tool could standardize histologic assessments and reduce the time and resources needed for MASH drug development. The AI-Based Histologic Measurement of NASH (AIM-NASH) system uses AI algorithms to analyze liver biopsy images and provides scores according to the NASH Clinical Research Network (NASH CRN) scoring system. According to the FDA, the qualification was based on comprehensive validation studies demonstrating that AIM-NASH-assisted comparisons to expert consensus were similar to individual pathologists' comparisons to expert consensus. However, pathologists remain fully responsible for final interpretation, reviewing the whole slide image and AIM-NASH outputs before accepting or rejecting the AI-generated scores.

The AI tool is designed to assist pathologists and complement the consensus reading process currently used in MASH trials for endpoint evaluation (i.e., utilizing two pathologists and a tie-breaker, if needed). It should be integrated into the existing consensus reading process without replacing any pathologists or the tiebreaker currently used in MASH trials. Users should submit a plan describing how they will use the AIM-NASH system in their clinical trials as early as possible.

Learn more about FDA's Drug Development Tool Qualification Programs.