FDA Releases Two Discussion Papers to Spur Conversation about Artificial Intelligence and Machine Learning in Drug Development and Manufacturing
By: Patrizia Cavazzoni, M.D., Director of the Center for Drug Evaluation and Research
Artificial intelligence (AI) and machine learning (ML) are no longer futuristic concepts; they are now part of how we live and work. The U.S. Food and Drug Administration uses the term AI to describe a branch of computer science, statistics, and engineering that uses algorithms or models to perform tasks and exhibit behaviors such as learning, making decisions, and making predictions. ML is a subset of AI that uses data and algorithms, without being explicitly programmed, to imitate how humans learn.
AI/ML’s growth in data volume and complexity, combined with cutting-edge computing power and methodological advancements, have the potential to transform how stakeholders develop, manufacture, use, and evaluate therapies. Ultimately, AI/ML can help bring safe, effective, and high-quality treatments to patients faster.
For example, AI/ML could be used to scan the medical literature for relevant findings and predict which individuals may respond better to treatments and which are more at risk for side effects. Conversational agents or chatbots, which are based on “generative” AI, have the potential to answer people’s questions about participating in clinical trials or reporting adverse events. Digital or computerized “twins” of patients can be used to model a medical intervention and provide biofeedback before patients receive the intervention.
The regulatory uses are real: In 2021, more than 100 drug and biologic applications submitted to the FDA included AI/ML components. These submissions spanned a range of therapeutic areas, and sponsors incorporated the technologies in different developmental stages.
As with other evolving fields of science and technology, there are challenges associated with AI/ML in drug development, such as ethical and security considerations like improper data sharing or cybersecurity risks. There are also concerns with using algorithms that have a degree of opacity, or algorithms that may have internal operations that are not visible to users or other interested parties. This can lead to amplification of errors or preexisting biases in the data. We aim to prevent and remedy discrimination — including algorithmic discrimination, which occurs when automated systems favor one category of people over other(s) — to advance equity when using AI/ML techniques. To address these concerns, the FDA has released a discussion paper, “Using Artificial Intelligence and Machine Learning in the Development of Drug and Biological Products.”
AI and ML in the Development of Drug and Biological Products
The discussion paper is a collaboration among the FDA’s Center for Drug Evaluation and Research, the Center for Biologics Evaluation and Research, and the Center for Devices and Radiological Health, including its Digital Health Center of Excellence. The paper aims to spur a discussion with interested parties in the medical products development community, such as pharmaceutical companies, ethicists, academia, patients and patient groups, and global counterpart regulatory and other authorities, on using AI/ML in drug and biologic development, and the development of medical devices to use with these treatments.
The paper includes an overview of the current and potential future uses for AI/ML in therapeutic development. It also discusses the possible concerns and risks associated with these innovations and ways to address them. For instance, the paper describes the importance of having human involvement, which will vary depending on how the technologies will be used. The paper also emphasizes adopting a risk-based approach to evaluate and manage AI/ML in facilitating innovations and protecting public health.
The paper characterizes certain risks, such as biases in data used to train ML algorithms, or inaccuracies and completeness of these data. In addition, the paper outlines the role of monitoring the performance of models to ensure they are reliable, relevant, and consistent over time.
There are also questions to consider, and a call for engagement and collaboration among the biomedical community. As a follow-up to the paper, we are planning a workshop to discuss how the community can work together to realize the potential of AI/ML for product development while being mindful of potential challenges. We look forward to hearing from experts on this important topic.
CDER’s Discussion Paper on the Framework for Regulatory Advanced Manufacturing Evaluation
To further address the use of AI in drug manufacturing, CDER issued another discussion paper, Artificial Intelligence in Drug Manufacturing, as part of the Framework for Regulatory Advanced Manufacturing Evaluation (FRAME) Initiative. AI technologies are important in drug manufacturing because they can enhance process controls, identify early warning signals, and prevent product losses. We are also planning a second workshop for stakeholders to discuss the questions in our AI in drug manufacturing discussion paper.
Our agency’s efforts in AI/ML extend beyond these initiatives. We consult product developers, engage patients, and promote regulatory science in this area, among other activities. 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. The FDA’s work also supports the Administration’s ongoing work to ensure technology improves the lives of the American people, while advancing a cohesive and comprehensive approach to AI-related risks and opportunities.