Large language models (LLMs) have demonstrated high levels of performance in clinical information extraction compared to rule-based systems and traditional machine-learning approaches, offering scalability, contextualization, and easier deployment. However, most studies rely on proprietary models with privacy concerns and high costs, limiting accessibility. We aim to evaluate 14 publicly available open-source LLMs for extracting clinically relevant findings from free-text echocardiogram reports and examine the feasibility of their implementation in information [...]
Author(s): Chi, Jonathan, Rouphail, Yazan, Hillis, Ethan, Ma, Ningning, Nguyen, An, Wang, Jane, Hofford, Mackenzie, Gupta, Aditi, Lyons, Patrick G, Wilcox, Adam, Lai, Albert M, Payne, Philip R O, Kollef, Marin H, Dreisbach, Caitlin, Michelson, Andrew P
DOI: 10.1093/jamiaopen/ooaf092