Blog

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

Photo taken from Jakob Nikolas Kather/X

May 20, 2024, 13:46

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:”

Jakob Nikolas Kather

Source: Jakob Nikolas Kather/X

clinical AI Dresden University Dyke Ferber GPT-4 GPT-4 API information retrieval Jakob Nikolas Kather Kather Lab Large Language Models LLMs medical AI medical oncology NEJM AI oncology decision-making oncology guidelines oncology research quantitative evaluation RAG pipeline

Esophageal Cancer: Symptoms, Causes, Stages, Diagnosis & Treatment

Faster, Flexible and Affordable: Mikhail Groubman on Building a Global Legacy in Clinical Research in an Untapped Market

Invest in Health Policy: A Conversation with Professor Andreas Charalambous

FDA Approves Cosibelimab-ipdl for Treatment of Metastatic or Locally Advanced Cutaneous Squamous Cell Carcinoma

Dolph Lundgren’s Fight for Life: How He Survived Kidney Cancer After 9 Years of Battle

Special Coverage