Large language models in cancer: potentials, risks, and safeguards

Abstract

This review examines the use of large language models (LLMs) in cancer, analysing articles sourced from PubMed, Embase, and Ovid Medline, published between 2017 and 2024. Our search strategy included terms related to LLMs, cancer research, risks, safeguards, and ethical issues, focusing on studies that utilized text-based data. 59 articles were included in the review, categorized into 3 segments: quantitative studies on LLMs, chatbot-focused studies, and qualitative discussions on LLMs on cancer. Quantitative studies highlight LLMs' advanced capabilities in natural language processing (NLP), while chatbot-focused articles demonstrate their potential in clinical support and data management. Qualitative research underscores the broader implications of LLMs, including the risks and ethical considerations. Our findings suggest that LLMs, notably ChatGPT, have potential in data analysis, patient interaction, and personalized treatment in cancer care. However, the review identifies critical risks, including data biases and ethical challenges. We emphasize the need for regulatory oversight, targeted model development, and continuous evaluation. In conclusion, integrating LLMs in cancer research offers promising prospects but necessitates a balanced approach focusing on accuracy, ethical integrity, and data privacy. This review underscores the need for further study, encouraging responsible exploration and application of artificial intelligence in oncology.

Keywords: ChatGPT; artificial intelligence; cancer; chatbots; large language models; natural language processing; potentials; risks; safeguards.

Figure 1.

Literature review process for LLMs in oncology. Flowchart depicting the article selection process for our review on LLMs in oncology. Initially, 1167 articles were identified through a database search. Each article was manually assessed by title and abstract for relevance to the review scope. Articles were classified as “aligned with scope of the review”, “not aligned with scope of the review”, or “uncertain”. For articles marked as “uncertain”, a full-text review was conducted to determine their relevance to our study. Finally, our process led us to a final selection of 59 relevant articles aligned with the scope of the review. LLMs = large language models.