FDA sees rapid uptick in drug and biologic submissions with AI/ML components

BOSTON – Hao Zhu, director of the Division of Pharmacometrics in the US Food and Drug Administration’s (FDA) Center for Drug Evaluation and Research (CDER) said the number of drug applications incorporating artificial intelligence (AI) and machine learning (ML) elements have “increased drastically in the past five years.” In 2022, he said the agency received 170 submissions containing these elements.

In 2018, Zhu said that only three submissions contained AI/ML components. Zhu made these remarks at the DIA Global Annual Meeting on 27 June.

These tools are used to support enriching the design of the study, identifying patients for the study, identifying patient risk, selecting and optimizing dosing, assessing endpoints and biomarkers, predicting drug toxicity, or for drug discovery or repurposing.

Such AI tools were to support the emergency use authorization (EUA) for Anakinra, a drug used to treat hospitalized COVID-19 patients, where a machine learning model was used to select patients in clinical trials, Zhu said. He noted that two machine learning models were used to derive the score-based rule for patient selection.

He told the group that “FDA supports and encourages the appropriate use of innovative tools, such as AI/ML, to streamline new drug development.”

An article published in June 2022 in the journal Clinical Pharmacology & Therapeutics, entitled “Landscape Analysis of the Application of Artificial Intelligence and Machine Learning in Regulatory Submissions for Drug Development From 2016 to 2021,” examined drug and biologic regulatory submissions from 2016 to 2021 and searched in submissions for key terms such as “machine learning” or “artificial intelligence.”

The analysis found that in 2021, the agency received 132 applications containing AI and ML elements for new drugs and biologics. Of the total, most or 27% were in the oncology space, followed by 15% in psychiatry and 12% in gastroenterology.

Most of these AI/MI elements were most frequently used in the clinical phase, followed by the nonclinical, postmarketing and drug discovery and repurposing stages.

FDA is interested in gauging public comment on how the agency should use AI/ML to help inform the regulatory landscape in this area, and earlier this year the agency solicited feedback on two discussion papers on the use of AI/ML in drug development and manufacturing. (RELATED: FDA publishes discussion paper on AI/ML in drug development, Regulatory Focus 12 May 2023; FDA seeks feedback on artificial intelligence in drug manufacturing, Regulatory Focus 1 March 2023)

Zhu told Focus that “CDER will carefully review and analyze the comments, and based on the feedback received we plan to develop public workshops, white papers and guidance documents to provide regulatory clarity as needed.”

DIA meeting

FDA sees rapid uptick in drug and biologic submissions with AI/ML components

Related topics

Recommended content

Welcome to the new RAPS Digital Experience