The use of large language models to enhance cancer clinical trial educational materials
This addresses the challenge of improving patient engagement in cancer clinical trials, though it is incremental as it applies existing LLMs to a new domain with human oversight still required.
This study tackled the problem of low cancer clinical trial recruitment by using GPT4 to generate patient-friendly educational content from informed consent forms, finding that the generated summaries were readable and comprehensive while multiple-choice questions showed high accuracy.
Cancer clinical trials often face challenges in recruitment and engagement due to a lack of participant-facing informational and educational resources. This study investigated the potential of Large Language Models (LLMs), specifically GPT4, in generating patient-friendly educational content from clinical trial informed consent forms. Using data from ClinicalTrials.gov, we employed zero-shot learning for creating trial summaries and one-shot learning for developing multiple-choice questions, evaluating their effectiveness through patient surveys and crowdsourced annotation. Results showed that GPT4-generated summaries were both readable and comprehensive, and may improve patients' understanding and interest in clinical trials. The multiple-choice questions demonstrated high accuracy and agreement with crowdsourced annotators. For both resource types, hallucinations were identified that require ongoing human oversight. The findings demonstrate the potential of LLMs "out-of-the-box" to support the generation of clinical trial education materials with minimal trial-specific engineering, but implementation with a human-in-the-loop is still needed to avoid misinformation risks.