ChatGPT, Enhanced with Clinical Practice Guidelines, is a Superior Decision Support Tool

Abstract

AbstractChatGPT has gained remarkable traction since its inception in November 2022. However, it faces limitations in generating inaccurate responses, ignoring existing guidelines, and lacking reasoning when applied in clinical settings. This study introduces ChatGPT-CARE, a tool that integrates clinical practice guidelines with ChatGPT, focusing on COVID-19 outpatient treatment decisions. By employing in-context learning, chain-of-thought prompting, and few-shots learning, ChatGPT-CARE enhances original ChatGPT’s clinical decision support and reasoning capabilities. The tool was evaluated using three categories of various descriptions of patients seeking COVID-19 treatment, and two physicians specialized in pulmonary disease and critical care assessed the responses for accuracy, hallucination, and clarity. The results indicate that ChatGPT-CARE, particularly the GPT-4 version, offers higher accuracy and clarity compared to the original ChatGPT. Despite some limitations, such as occasional hallucinations, ChatGPT-CARE represents a significant advancement in AI-driven clinical decision support, with potential applications beyond COVID-19 treatment.