Comprehensive Evaluation of AI Consent Forms in Otolaryngologic Surgery.
Lay readers said AI-generated surgical consent forms adequately explained risks, benefits, and alternatives
Comprehensive Evaluation of AI Consent Forms in Otolaryngologic Surgery.
Surgical consent documents are frequently written at reading levels exceeding average health literacy.
This study evaluated the clarity, clinical accuracy, and acceptability of consent forms generated by GPT-4 and Claude for common otolaryngologic procedures.
A cross-sectional cohort of 300 English-speaking adults (15 raters per form) evaluated perceived clarity and signing comfort on 5-point Likert scales, and perceived trust using a binary (Yes/No) item, and completed eight binary quality assessments.
Mean lay ratings for clarity across AI-generated forms were high overall.
However, when analyzed at the form level, differences between models were not statistically significant for clarity (mean difference 0.04; t (9) = -0.80; p = 0.44) or signing comfort (mean difference 0.13, t (9) = -1.68, p = 0.13).
Mean Flesch-Kincaid Grade Level was lower for AI-generated forms compared to official templates.
Although prompts targeted a 6th-8th grade reading level, achieved readability scores were slightly higher (8.8-9.4).
In a non-clinical evaluation, AI-generated consent forms were perceived as clear and clinically complete, with model-specific trade-offs between perceived clarity and clinical detail.
These perception-based findings-reflecting participant ratings of clarity, perceived trust, and willingness to sign rather than objective comprehension-are hypothesis-generating, and prospective clinical and legal validation in more representative patient populations is required.