FDA explores the potential of AI to streamline drug safety reviews
Our machine-learning prototype will help the Food and Drug Administration's Center for Drug Evaluation and Research explore the use of advanced technologies for efficient and timely review of drug products for the U.S. market.
The Division of Medication Error Prevention and Analysis (DMEPA) within the FDA's Center for Drug Evaluation and Research reviews pre-market and post-market drug labeling to minimize the risk of medication errors. Working with their team, we are developing a machine-learning prototype that uses models, algorithms, and machine vision to streamline and minimize inefficiencies in the drug labeling review process.
The FDA’s drug labeling review process is both extensive and time sensitive. Typically, each medication error reviewer performs 25 to 50 drug pre-market reviews per year, analyzing things like a label’s font size and its ability to accurately meet regulations and standards. The goal of such a detailed review process is to ensure a drug product is safe and effective and prevent accidents—misinterpreted labels can lead to adverse reactions or even accidental death.
The review process, which includes back-and-forth communication between reviewers and drug manufacturers, is often manual and, at times, may be subjective by individual reviewers. The FDA sought a way to use cutting-edge technology to expedite and streamline the user experience (UX) for medication error drug labeling reviewers, ultimately benefiting all healthcare consumers.
We are collaborating with FDA reviewers to build out a machine learning prototype known as the Computerized Labeling Assessment Tool (CLAT). CLAT is designed to use algorithms and machine vision to read drug labels and pinpoint specific items for review. We train our machine-learning models on thousands of images to ensure sensitivity and accuracy. Simultaneously, we tap into the expertise of our data scientists to utilize cutting edge algorithms and tune them to the problem at hand.
In addition, our data experts continue to develop process recommendations for the FDA, including standardized images to represent how a particular drug should be used—a standard ear image for drugs targeting ear-related issues, for example. The FDA is in the process of rolling out these standardized images, which is meant to improve efficiency for reviewers.
Where we are now
As work to optimize the impact of CLAT advances in 2023 and beyond, the FDA continues to explore how this machine-learning prototype could be used in other review processes. While our work on the prototype project is currently focused on the technical side, the goal is to eventually develop a friendly, approachable experience for front-end users.