Performance of Retrieval-Augmented Large Language Models to Recommend Head and Neck Cancer Clinical Trials.

Hung, Tony K W; Kuperman, Gilad J; Sherman, Eric J; Ho, Alan L; Weng, Chunhua; Pfister, David G; Mao, Jun J

The research letter published in the Journal of Medical Internet Research by Hung et al. discusses the development and evaluation of a retrieval-augmented large language model (LLM) to recommend clinical trials for head and neck cancer patients. The study utilized real-world patient cases to assess the performance of the LLM, achieving moderate precision and recall rates. The findings suggest that the retrieval-augmented LLM outperformed its baseline and could potentially enhance clinical trial participation in oncology practice. The study acknowledges limitations such as sample size and institutional focus, highlighting the need for further research to optimize LLMs for clinical decision support.

LANGUAGE models; ARTIFICIAL intelligence; CLINICAL decision support systems; EPIDERMAL growth factor receptors; SALIVARY gland cancer

Journal of Medical Internet Research, 2024, Vol 26, p1

1439-4456

Academic Journal

10.2196/60695