Large Language Models Are Reshaping Patient Data Management and Clinical Practice in Nuclear Medicine.

The review synthesizes recent research on large language models (LLMs) in nuclear medicine and theranostics. It explores the potential of LLMs in this specialized field for patient data management, clinical decision support, and education. Key challenges include hallucinations, limited domain knowledge, and privacy concerns. The paper emphasizes the need for validation and domain adaptation to improve the potential of LLMs in these medical domains.