Comprehensive Evaluation of AI Consent Forms in Otolaryngologic Surgery
8 affiliations
- 1City St. Georges University London School of Medicine, Program Delivered by University of Nicosia at the Chaim Sheba Medical Center Ramat Gan Israel
- 2City St. Georges University London School of Medicine, Program Delivered by University of Nicosia Ramat Gan Israel
- 3Touro College of Osteopathic Medicine Montana USA
- 4New York Institute of Technology College Of Osteopathic Medicine USA
- 5Washington University in St. Louis St. Louis Missouri USA
- 6Department of Otolaryngology Sheba Medical Center Ramat Gan Israel
- 7Department of Otolaryngology‐Head and Neck Surgery Houston Methodist Hospital Houston USA
- 8Division of Otolaryngology‐Head and Neck Surgery Children's National Hospital Washington District of Columbia Washington District of Columbia USA
Abstract
Introduction Surgical consent documents are frequently written at reading levels exceeding average health literacy. Large language models (LLMs) may offer a scalable approach to generating clearer, procedure‐specific consent forms. This study evaluated the clarity, clinical accuracy, and acceptability of consent forms generated by GPT‐4 and Claude for common otolaryngologic procedures. Methods Twenty AI‐generated consent forms (10 GPT‐4.0, 10 Claude‐2.1) were produced using standardized prompts. In a survey‐based, non‐clinical setting, five board‐certified otolaryngologists independently rated each form for medical accuracy, readability, comprehensibility, legal/ethical sufficiency, and usability using a 4‐point scale. 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. A blinded subgroup (n = 10) compared AI‐generated and official national health system templates across five Likert domains. Readability was assessed using Flesch–Kincaid Grade Level (FKGL). Results Mean lay ratings for clarity across AI‐generated forms were high overall. Claude demonstrated numerically higher scores than GPT‐4 for clarity (4.72 vs. 4.68), perceived trust (reported as proportions), and signing comfort (4.40 vs. 4.27). 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). Across binary domains, ≥ 95% of participants affirmed adequate explanation of risks, benefits, and alternatives. Experts rated GPT‐4 more accurate than Claude (2.2 vs. 1.5, p = 0.034). 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). Conclusions 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.
Related
- The role of information and consent forms in patients’ decision-making regarding participation in oncology clinical trials
- Reproductive Privacy Risk Disclosure in US Clinical Trial Informed Consent Forms After the Dobbs Decision
- Effect of video-assisted informed consent on preoperative anxiety in patients undergoing laparoscopic gastrointestinal cancer surgery: a randomized controlled trial
- Robotic-assisted beating heart surgery: a comprehensive review
- Artificial Intelligence Applications in Laser-Assisted Refractive Surgery—A Comprehensive Review
BibTeX
@article{hack2026comprehensive,
title = {{Comprehensive Evaluation of AI Consent Forms in Otolaryngologic Surgery}},
author = {Sholem Hack and Rebecca Attal and Armin Farzad and Lilia Ann Crew and Shmuel Silverstein and Jacob E. Karni and Nir Livneh and Shibli Alsleibi and Naseem Saleh and Ben Gvili and David Yogev and Eric Remer and Eran E. Alon and Gil Siegal and Masayoshi Takashima and Habib G. Zalzal},
journal = {World Journal of Otorhinolaryngology-Head and Neck Surgery},
year = {2026},
month = oct,
doi = {10.1002/wjo2.70118},
url = {https://doi.org/10.1002/wjo2.70118},
note = {CC BY},
}
RIS
TY - JOUR
TI - Comprehensive Evaluation of AI Consent Forms in Otolaryngologic Surgery
AU - Sholem Hack
AU - Rebecca Attal
AU - Armin Farzad
AU - Lilia Ann Crew
AU - Shmuel Silverstein
AU - Jacob E. Karni
AU - Nir Livneh
AU - Shibli Alsleibi
AU - Naseem Saleh
AU - Ben Gvili
AU - David Yogev
AU - Eric Remer
AU - Eran E. Alon
AU - Gil Siegal
AU - Masayoshi Takashima
AU - Habib G. Zalzal
PY - 2026
DA - 2026/10/23
JO - World Journal of Otorhinolaryngology-Head and Neck Surgery
DO - 10.1002/wjo2.70118
UR - https://doi.org/10.1002/wjo2.70118
AB - Introduction Surgical consent documents are frequently written at reading levels exceeding average health literacy. Large language models (LLMs) may offer a scalable approach to generating clearer, procedure‐specific consent forms. This study evaluated the clarity, clinical accuracy, and acceptability of consent forms generated by GPT‐4 and Claude for common otolaryngologic procedures. Methods Twenty AI‐generated consent forms (10 GPT‐4.0, 10 Claude‐2.1) were produced using standardized prompts. In a survey‐based, non‐clinical setting, five board‐certified otolaryngologists independently rated each form for medical accuracy, readability, comprehensibility, legal/ethical sufficiency, and usability using a 4‐point scale. 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. A blinded subgroup (n = 10) compared AI‐generated and official national health system templates across five Likert domains. Readability was assessed using Flesch–Kincaid Grade Level (FKGL). Results Mean lay ratings for clarity across AI‐generated forms were high overall. Claude demonstrated numerically higher scores than GPT‐4 for clarity (4.72 vs. 4.68), perceived trust (reported as proportions), and signing comfort (4.40 vs. 4.27). 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). Across binary domains, ≥ 95% of participants affirmed adequate explanation of risks, benefits, and alternatives. Experts rated GPT‐4 more accurate than Claude (2.2 vs. 1.5, p = 0.034). 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). Conclusions 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.
SN - 2589-1081
SN - 2095-8811
ER -