AI for Regulatory Affairs: Balancing Accuracy, Interpretability, and Computational Cost in Medical Device Classification
This addresses the need for automated classification in regulatory affairs to improve market access and patient safety, but it appears incremental as it focuses on evaluating existing methods without introducing new ones.
The study tackled the problem of classifying medical devices for regulatory affairs by evaluating various AI models, including traditional ML, deep learning, and large language models, on a dataset of device descriptions, but no concrete results or numbers were provided.
Regulatory affairs, which sits at the intersection of medicine and law, can benefit significantly from AI-enabled automation. Classification task is the initial step in which manufacturers position their products to regulatory authorities, and it plays a critical role in determining market access, regulatory scrutiny, and ultimately, patient safety. In this study, we investigate a broad range of AI models -- including traditional machine learning (ML) algorithms, deep learning architectures, and large language models -- using a regulatory dataset of medical device descriptions. We evaluate each model along three key dimensions: accuracy, interpretability, and computational cost.