This systematic review examines the clinical and surgical applications of large language models (LLMs), particularly focusing on their potential benefits and limitations in healthcare. The review, conducted by a team from the Mayo Clinic, searched six databases and identified 34 articles published in 2023 that met the eligibility criteria. These articles covered a wide range of medical specialties, including various surgical subspecialties. The review highlights that LLMs can enhance healthcare delivery by assisting in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. In surgical settings, LLMs can aid in documentation, surgical planning, and intraoperative guidance. However, the review also emphasizes several limitations and concerns, such as accuracy, biases, and patient privacy. Addressing these issues is crucial for the responsible use of LLMs. The authors conclude that while LLMs have the potential to improve healthcare, they should be viewed as complementary tools rather than replacements for healthcare professionals. Future research should focus on enhancing accuracy, reducing biases, expanding applications, integrating LLMs with healthcare systems, and addressing ethical concerns. The review provides a comprehensive overview of the current state and future directions of LLMs in healthcare, emphasizing the need for further development and validation to ensure their reliable use.This systematic review examines the clinical and surgical applications of large language models (LLMs), particularly focusing on their potential benefits and limitations in healthcare. The review, conducted by a team from the Mayo Clinic, searched six databases and identified 34 articles published in 2023 that met the eligibility criteria. These articles covered a wide range of medical specialties, including various surgical subspecialties. The review highlights that LLMs can enhance healthcare delivery by assisting in diagnosis, treatment guidance, patient triage, physician knowledge augmentation, and administrative tasks. In surgical settings, LLMs can aid in documentation, surgical planning, and intraoperative guidance. However, the review also emphasizes several limitations and concerns, such as accuracy, biases, and patient privacy. Addressing these issues is crucial for the responsible use of LLMs. The authors conclude that while LLMs have the potential to improve healthcare, they should be viewed as complementary tools rather than replacements for healthcare professionals. Future research should focus on enhancing accuracy, reducing biases, expanding applications, integrating LLMs with healthcare systems, and addressing ethical concerns. The review provides a comprehensive overview of the current state and future directions of LLMs in healthcare, emphasizing the need for further development and validation to ensure their reliable use.