Good AI Practice in Drug Development

The US FDA CDER and CBER together with the European Medicines Agency (EMA) have developed guiding principles that industry and product developers should consider when using artificial intelligence (AI) to advance drug and biological product development.

The use of AI in drug development has the potential to transform the way drugs are developed and evaluated, ultimately improving health care. AI technologies are anticipated to help promote innovation, reduce time-to-market, strengthen regulatory excellence and pharmacovigilance, and decrease reliance on animal testing by improving the prediction of toxicity and efficacy in humans. The FDA recently approved the first AI tool for use in clinical trials.

"To fully realize the potential of AI while ensuring reliability of the information to ensure patient safety and regulatory excellence, it is essential to establish guiding principles that address the unique challenges and considerations of AI applications in drug development", the FDA says.

The principles are tailored to the drug development cycle and emphasize the importance of, for example,

• Human-Centric by Design
• Risk-based Approach
• Multidisciplinary Expertise
• Data Governance and Documentation
• Model Design and Development Practices
• Life Cycle Management

The "Guiding Principles of Good AI Practice in Drug Development" are available as pdf for download here.