What question did this study set out to answer?

This study evaluates how complete large language models are in generating informed consent information for clinical trials involving AYA patients with CNS tumors.

April 28, 2026Discover Public HealthOpen Access

Evaluating the completeness of large language model-generated clinical trial informed consent information for adolescent and young adult patients with central nervous system tumors

View Full Paper

Ask AI

Bookmark

Authors

CBCorey H. BaschWilliam Paterson University EJErin T. JacquesYork College, City University of New York EDErela DatuoweiColumbia University

Discussion

Member takes

Implication

Randomized trial evaluates completeness of informed consent in clinical trials for adolescents and young adults, suggesting areas for improvement.

Key Points

This study evaluates how complete large language models are in generating informed consent information for clinical trials involving AYA patients with CNS tumors.
Conducted a structured audit of five LLMs: ChatGPT 5.2, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini (Fast), and Perplexity.
Developed six standardized prompts based on FDA consent requirements (21 CFR § 50.25).
Scored the completeness of 25 LLM-generated informed consent responses across five cancer diagnoses using an FDA-aligned checklist.
Median consent completeness score was 33 (IQR: 31–34), ranging from 22 to 35, showing variability.
Completion scores were highest for eligibility and procedures domains (median 6, IQR 6–6).
Greater variability was seen in domains related to study purpose and practical details (median scores of 5).

Cite This Study

Basch et al. (2026) studied this question.

synapsesocial.com/papers/69f04e9b727298f751e72864 https://doi.org/10.1186/s12982-026-01963-6

View Full Paper

Ask AI

Bookmark

Implication

Randomized trial evaluates completeness of informed consent in clinical trials for adolescents and young adults, suggesting areas for improvement.

Evaluating the completeness of large language model-generated clinical trial informed consent information for adolescent and young adult patients with central nervous system tumors

Discussion

Member takes

Implication

Key Points

Cite This Study

Evaluating the completeness of large language model-generated clinical trial informed consent information for adolescent and young adult patients with central nervous system tumors

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider