Evaluating GPT-4’s ability to generate informed consent material for genetic testing

Abstract The informed consent (IC) process is essential in genetic testing, yet IC materials are often difficult to read and understand, influencing patients’ decision-making. Large language models may improve the accessibility and clarity of these materials. We used GPT-4 to generate IC materials for Non-Invasive Prenatal Testing (NIPT) and hereditary breast and ovarian cancer testing (BRCA) in English, German, Italian, and Greek, using zero-shot prompting and retrieval-augmented generation. Healthcare providers evaluated GPT-4-generated and human-generated materials using a previously published framework. GPT-4 performed well on structured components, such as explaining the purpose and benefits of testing, but struggled with nuanced ethical and contextual content. Respondents overall preferred human-written materials, underscoring limitations in current GPT-4-generated material for health communication in the genetic testing context. GPT-4’s performance in German, Italian and Greek was generally weaker than in English, highlighting potential language-specific challenges in GPT-4-generated IC content.