Assessment of Large Language Models for Enhancing Diabetologist-Developed Personalized Treatment Plans in Complex Type 2 Diabetes
Michelle Wang, Madhumita Sushil, Christopher Y. K. Williams, Brenda Y. Miao, Sarah Kim, Umesh B. Masharani, Gregory Ku, Victoria C. Hsiao, Aloukika Shah, Suneil K. Koliwad, Atul Janardhan Butte · Clinical Diabetes · 2025
Treatment decisions for type 2 diabetes are complex and multifactorial. This study evaluated the utility of OpenAI's generative pre-trained transformer-4 (GPT-4) large language model in enhancing treatment plans for people with diabetes. The authors assessed GPT-4's ability to extract and critically evaluate diabetologist-developed treatment plans from patients' clinical notes. GPT-4 accurately discerned personalized treatment goals but performed suboptimally when identifying plans that could be further improved and personalized. However, 40% of GPT-4's reasoning and explanations were still considered helpful by experienced academic diabetologists, suggesting a potential broad benefit to less expert physicians, such as those in primary care settings.