The Center for Drug Evaluation and Research, the FDA’s key drug review arm, has announced the start of a review of a new AI‑based Drug Development Tool. The AI model is designed to predict drug‑induced liver injury – one of the main causes of clinical trial failures. Current methods do not reliably assess this risk in humans.
The tool is a digital, AI‑driven liver model that predicts whether a new drug will cause liver harm. It assesses the hepatotoxicity risk of new molecules by comparing their chemical structures with those of known drugs with established safety profiles. The model does not fully replace existing methods but complements them and aids decision‑making in early development stages.
The FDA noted that the tool could potentially improve early safety assessments, reduce reliance on animal testing, and support more informed decisions before human clinical trials begin.
“Emerging technologies show incredible promise in improving and streamlining the drug development process, with the ultimate goal of enhancing patient care,” said Michael Davis, acting director of CDER.
The AI‑developed digital liver model has been accepted into the agency’s ISTAND pilot programme (Innovative Science and Technology Approaches for New Drugs).
Approval of the letter of intent is the first step in a multi‑stage qualification process. If successful, drug manufacturers will be able to use the tool in their marketing applications. The drug development tool qualification programme works with experts to help create application‑specific solutions.
