Jakob Nikolas Kather: GPT-4 API to answer medical oncology questions based on guidelines

Jakob Nikolas Kather, Professor of Clinical Artificial Intelligence at Dresden University of Technology, made the following post on X:

“Finally out in NEJM AI, led by Dyke Ferber from Kather Lab: “GPT-4 for Information Retrieval and Comparison of Medical Oncology Guidelines”. We’ve developed a RAG pipeline using the GPT-4 API to answer medical oncology questions based on guidelines. Previous studies have claimed that “large language models (LLMs) are not suited for oncology” — but our data debunk these claims! Using RAG, LLMs are very good at medical decision-making in oncology — as we show in a quantitative evaluation. There is still room for improvement, but LLMs+RAG are the way to go.

• Paper link:
• Free-access link:”

Source: Jakob Nikolas Kather/X