FDA publishes discussion paper on AI/ML in drug development

The US Food and Drug Administration (FDA) has released a discussion paper on using artificial intelligence and machine learning in drug and biological product development.

FDA’s discussion paper follows another recently published discussion paper in March 2023 on incorporating artificial intelligence and advanced manufacturing techniques into the pharmaceutical manufacturing regulatory framework. (RELATED: AI in drug manufacturing: Stakeholders call for harmonization, further guidance, Regulatory Focus 9 May 2023)

“Artificial intelligence (AI) and machine learning (ML) are no longer futuristic concepts; they are now part of how we live and work,” Patrizia Cavazzoni, director of the Center for Drug Evaluation and Research (CDER), wrote in an FDA Voices article announcing the publication of both discussion papers.

Written by the agency’s three medical product centers, CDER, the Center for Biologics Evaluation and Research (CBER) and the Center for Devices and Radiological Health (CDRH), the paper is intended to engage pharmaceutical companies, ethicists, academia, patients and patient groups, and other international authorities interested in artificial intelligence and machine learning in drug and biologic development, as well as in developing medical devices.

The discussion paper covers both current and potential uses for AI and ML, including drug discovery, clinical and non-clinical research, postmarket safety surveillance, and advanced pharmaceutical marketing.

“Developers, manufacturers, regulators, academic groups, and other stakeholders are working to develop a shared understanding of where and how specific innovations, such as AI and ML, can best be used throughout the drug development process,” the agency wrote in the discussion paper. “FDA is publishing this discussion paper as part of a multifaceted approach to enhance mutual learning and to establish a dialogue with FDA stakeholders on this topic.”

FDA said it is important for stakeholders to understand how the agency is approaching AI and ML outside both discussion papers. “Our agency’s efforts in AI/ML extend beyond these initiatives,” Cavazzoni wrote. “We consult product developers, engage patients, and promote regulatory science in this area, among other activities,”

Concerns, risks of AI/ML

The paper raised concerns and risks with using the technology, describing the overarching standards and practices for use of AI and ML as well as the considerations for AI and ML in drug development. Central to those concerns is the importance of involving humans to the extent technology allows, adopting a risk-based approach in AI and ML, and using the technology to facilitate innovation while protecting public health, the agency noted.

Other concerns raised in FDA’s discussion paper are the risks of introducing bias in data or inaccurate/incomplete data used for ML algorithms, and monitoring AI and ML models for reliability, relevancy, and consistency.

“As a public health regulatory agency, we hope to encourage the safe development of these technologies that are poised to help Americans gain quicker and more reliable access to important treatments,” Cavazzoni wrote.

The agency explained that this discussion paper was intended as an initial communication and is asking for input from industry and other stakeholders on the opportunities and challenges using AI and ML in drug development and in medical devices developed to be used with drugs. A workshop is also being planned to discuss the potential as well as the challenges in using AI and ML for product development.

“We look forward to hearing from experts on this important topic,” Cavazzoni said.

Discussion paper

Federal Register notice

FDA publishes discussion paper on AI/ML in drug development

Related topics

Recommended content

Welcome to the new RAPS Digital Experience