The use of generative AI across medtech is increasing, including applications for patient care, medical research, and education. In this new study, we compare six leading large language models (LLMs) against human experts on core regulatory tasks to evaluate strengths and weaknesses.
Here are the exercises we put LLMs through:
Strategic advice on the AI Act: Read the EU Artificial Intelligence Act and analyze its impact on medtech companies.
Classifying medical devices: Review software applications and determine which are medical devices based on intended uses.
Summarizing technical documents: Read and provide an executive summary of various technical documents and justify the conclusions using data provided within the documents.
Read the study findings to see how the LLMs performed compared to humans, including where they fell short and the potential benefits. How will GenAI fit into your regulatory organization?
About this email: You are receiving this message as part of your complimentary newsletter subscription to MedTech Dive. If you no longer wish to receive the daily newsletter, you can switch to a weekly subscription or unsubscribe. See our full privacy policy. MedTech Dive is a product of TechTarget, Inc. and its subsidiaries, 275 Grove St. Newton, MA, 02466
