Is ChatGPT able to interpret arterial blood gas analysis?A comparative cross-sectional study

Background: This study aimed to evaluate the performance of ChatGPT in interpreting arterial blood gas results and compare it to the performance of physicians with varying levels of experience. Methods: In this comparative and cross-sectional study, 30 selected clinical cases encompassing simple and mixed acid-base disorders, respiratory abnormalities, and electrolyte disturbances, were analyzed by ChatGPT and 45 anesthesiology physicians who were divided into three groups: specialists, experienced residents, and inexperienced residents. Participants assessed arterial blood gases across five domains, including acid-base diagnosis, respiratory evaluation, fluid and electrolyte disturbance, other abnormalities, and treatment planning. Both ChatGPT and participant responses were scored by two experienced anesthesiology academicians based on a 5-point Likert scale. The overall score was calculated as the sum of the scores from the five individual subdomains. Results: The overall scores of ChatGPT and the physicians were similar (21.75, 21.97). ChatGPT demonstrated high accuracy in diagnosing primary acid-base disorders and providing treatment recommendations, though slight variability was observed in mixed disorders. A strong correlation was observed between ChatGPT’s scores and those of physicians (r = 0.912, p < 0.001). Conclusions: ChatGPT demonstrated a performance comparable to that of physicians, suggesting that it could assist in the decision-making processes of healthcare professionals and contribute to workload reduction.