Generative AI costs in large healthcare systems, an example in revenue cycle.

Application of large language models in healthcare continues to expand, specifically for medical free-text classification tasks. While foundation models like those from ChatGPT show potential, alternative models demonstrate superior accuracy and lower costs. This study underscores significant challenges, including computational costs and model reliability. Amidst rising healthcare expenditures and AI's perceived potential to reduce costs, a combination of local and commercial models might offer balanced solutions for healthcare systems.