Evaluating LLM-Generated Informed Consent: FDA-Aligned Audit Framework for AYA CNS Cancer Clinical Trials

Fuente: Zenodo
Saved in:
Bibliographic Details
Main Authors: Basch, Corey, Jacques, Erin
Format: Recurso digital
Published: Zenodo 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901749131902976
author Basch, Corey
Jacques, Erin
author_facet Basch, Corey
Jacques, Erin
contents This repository contains complete materials for replicating a structured audit of large language model (LLM) responses to informed consent questions about clinical trials for adolescent and young adult (AYA) patients with central nervous system (CNS) tumors. The study evaluates how completely publicly available AI tools cover FDA-mandated informed consent elements. Includes standardized prompts, FDA-aligned evaluation checklist, scored response data, data collection protocol, and analysis code. Key finding: AI-generated informed consent responses showed substantial variability in completeness (median score: 33/35; range: 22-35), with no response achieving full coverage of all FDA-aligned consent elements.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_18294186
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Evaluating LLM-Generated Informed Consent: FDA-Aligned Audit Framework for AYA CNS Cancer Clinical Trials
Basch, Corey
Jacques, Erin
artificial intelligence
large language models
informed consent
clinical trials
health communication
patient safety
FDA regulation
adolescent and young adult
cancer
central nervous system tumors
AI evaluation
health information quality
This repository contains complete materials for replicating a structured audit of large language model (LLM) responses to informed consent questions about clinical trials for adolescent and young adult (AYA) patients with central nervous system (CNS) tumors. The study evaluates how completely publicly available AI tools cover FDA-mandated informed consent elements. Includes standardized prompts, FDA-aligned evaluation checklist, scored response data, data collection protocol, and analysis code. Key finding: AI-generated informed consent responses showed substantial variability in completeness (median score: 33/35; range: 22-35), with no response achieving full coverage of all FDA-aligned consent elements.
title Evaluating LLM-Generated Informed Consent: FDA-Aligned Audit Framework for AYA CNS Cancer Clinical Trials
topic artificial intelligence
large language models
informed consent
clinical trials
health communication
patient safety
FDA regulation
adolescent and young adult
cancer
central nervous system tumors
AI evaluation
health information quality
url https://doi.org/10.5281/zenodo.18294186