High consistency between recommendations by a pulmonary specialist and ChatGPT for the management of a patient with non-resolving pneumonia

Abstract

The use of artificial intelligence in healthcare is rapidly growing, with great potential to assist medical professionals in diagnosis and treatment of complex medical conditions. In this case report, the recommendations of a pulmonary consultation are compared to the recommendations from a large language model (LLM), ChatGPT, in regards to a case of non-resolving pneumonia. The recommendations by ChatGPT were found to be consistent with the pulmonary consultation, and no recommendations given were inappropriate. As shown in this case report, early generations of LLM such as ChatGPT were able to provide appropriate recommendations for the management of a patient with a complex medical condition.