FDA Issues Comprehensive Guidance on the Use of AI Models for Regulatory Decision-Making in Drug Development

The FDA's latest guidance on artificial intelligence (AI) models in regulatory decision-making for drug development introduces a risk-based credibility assessment framework to ensure the reliability of AI outputs. This framework tailors oversight levels, performance criteria, and risk mitigation strategies to the AI model's context of use (COU) and associated risks. Sponsors are encouraged to engage early with the FDA to align their AI applications with regulatory expectations, focusing on safety, effectiveness, and quality. While the guidance excludes AI applications in drug discovery and operational efficiencies not impacting patient safety, it highlights the importance of detailed documentation and planning for credible AI model deployment in regulatory processes.