FDA Releases Two Discussion Papers on Artificial Intelligence and Machine Learning in Drug Development and Manufacturing

On May 10, the FDA released two discussion papers on the use of artificial intelligence and machine learning (AI/ML) in drug development and manufacturing. In a statement introducing her paper, Patrizia Cavazzoni, M.D., Ph.D., director of the FDA’s Center for Drug Evaluation and Research, explored the potential of AI/ML to transform the way stakeholders develop, manufacture, use, and evaluate therapeutics. emphasized. “Ultimately, AI/ML will help us deliver safe, effective, and high-quality care to patients faster,” she wrote. “For example, AI/ML can be used to scan medical literature for relevant findings and predict which individuals will respond better to treatment and which are at higher risk of side effects. Conversational agents or chatbots based on “generative” AI could answer people’s questions about participating in clinical trials or reporting adverse events. Digital or computerized patient “twins” can be used to model medical interventions and provide biofeedback before patients undergo the intervention. ”

However, significant ethical and security challenges remain. The first paper, “Using Artificial Intelligence and Machine Learning in Drug and Biologics Development,” relates these concerns to algorithms that have some degree of opacity or that may have invisible internal operations. We are addressing the challenges of Errors and existing biases in the data can be amplified as they affect users and other stakeholders.

This discussion paper was produced as a collaborative effort of the FDA’s Center for Drug Evaluation and Research (CDER), the Center for Biologics Evaluation and Research, and the Center for Device and Radiation Health, which includes the Digital Health Center of Excellence. This is a collaborative effort with stakeholders in the medical product development community, including pharmaceutical companies, ethicists, academia, patients and patient advocacy groups, and corresponding regulatory and other authorities around the world to discuss AI/ML in drug and biologics development. It is intended to facilitate discussion about its use. Development of medical devices used for these treatments.

This paper contains an overview of the current and future uses of AI/ML in therapeutics development, discusses the concerns and risks that may be associated with these innovations and how to address them, and discusses the implications of AI It emphasizes taking a risk-based approach to assessing and managing /ML. ML fosters innovation and protects public health. As a follow-up to this paper, FDA is planning a workshop to discuss how the community can work together to realize the potential of AI/ML in product development.

Framework for Regulatory Advanced Manufacturing Assessment

To further address the use of AI in pharmaceutical manufacturing, CDER published a second discussion paper, Artificial Intelligence in Pharmaceutical Manufacturing, as part of the framework of the Regulatory Advanced Manufacturing Evaluation (FRAME) initiative. The agency plans his second workshop for stakeholders to discuss AI-related questions in drug manufacturing with discussion papers.

“Our institution’s AI/ML efforts extend beyond these efforts,” said Dr. Cavazzoni. “We consult with product developers, engage with patients, advance regulatory science in this area, and more. We want to encourage the safe development of these technologies to make them available quickly and reliably.”

Image: Dr. Patrizia Cavazzoni