Generative artificial intelligence in optimizing the quality of cancer care: potential, limitations, and future directions of development for Large Language Models. A narrative literature review

This literature review included scientific articles, published between 2022 and 2025, indexed in PubMed, Scopus, and Proquest. The article investigates the potential of generative artificial intelligence (GenAI), particularly Large Language Models (LLMs), to improve the quality of cancer care. LLMs have demonstrated effectiveness in patient education by simplifying complex medical terminology and tailoring content to the user’s level of understanding. LLMs also assist physicians in clinical decision-making by analyzing medical data and supporting adherence to the latest guidelines. However, expert oversight is still necessary due to the risk of error. For cancer prevention, LLMs promote healthy lifestyle adoption, participation in screening programs, and vaccination. They also play an important role in reducing inequities in access to information. Another key feature of LLMs is their ability to translate complex diagnostic reports into patient-friendly language. LLMs have also shown promise in counteracting cancer-related misinformation. However, the article identifies certain LLMs limitations, such as model hallucination, incomplete personalization, and unresolved legal liability concerns. The article emphasizes ethical dilemmas, particularly those related to patient autonomy and the risk of dehumanizing care. For future progress, the article emphasizes the need to integrate LLMs into e-health systems and to develop specialized models supported by interdisciplinary teams.