Bridging the literacy gap for surgical consents: an AI-human expert collaborative approach
Open accessPublished version of a preprint
The DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Despite the importance of informed consent in healthcare, the readability and specificity of consent forms often impede patients’ comprehension. This study investigates the use of GPT-4 to simplify surgical consent forms and introduces an AI-human expert collaborative approach to validate content appropriateness. Consent forms from multiple institutions were assessed for readability and simplified using GPT-4, with pre- and post-simplification readability metrics compared using nonparametric tests. Independent reviews by medical authors and a malpractice defense attorney were conducted. Finally, GPT-4’s potential for generating de novo procedure-specific consent forms was assessed, with forms evaluated using a validated 8-item rubric and expert subspecialty surgeon review. Analysis of 15 academic medical centers’ consent forms revealed significant reductions in average reading time, word rarity, and passive sentence frequency (all P < 0.05) following GPT-4-faciliated simplification. Readability improved from an average college freshman to an 8th-grade level ( P = 0.004), matching the average American’s reading level. Medical and legal sufficiency consistency was confirmed. GPT-4 generated procedure-specific consent forms for five varied surgical procedures at an average 6th-grade reading level. These forms received perfect scores on a standardized consent form rubric and withstood scrutiny upon expert subspeciality surgeon review. This study demonstrates the first AI-human expert collaboration to enhance surgical consent forms, significantly improving readability without sacrificing clinical detail. Our framework could be extended to other patient communication materials, emphasizing clear communication and mitigating disparities related to health literacy barriers.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine
Lee, P., Bubeck, S., & Petro, J. (2023) · New England Journal of Medicine · doi:10.1056/nejmsr2214184 · Cited by 1,738
Understanding and Responding to Health Literacy as a Social Determinant of Health
Nutbeam, D., & Lloyd, J. E. (2021) · Annual Review of Public Health · doi:10.1146/annurev-publhealth-090419-102529 · Cited by 1,178
New technologies, new disparities: The intersection of electronic health and digital health literacy
Smith, B., & Magnani, J. W. (2019) · International Journal of Cardiology · doi:10.1016/j.ijcard.2019.05.066 · Cited by 446
Adams, L. C., Truhn, D., Busch, F., Kader, A., Niehues, S. M., Makowski, M. R., & Bressem, K. K. (2023) · Radiology · doi:10.1148/radiol.230725 · Cited by 339 · cited 1×
“Newly-developed arti fi cial intelligence systems, speci fi cally in the form of large language models (LLMs), have shown promise in their ability to summarize, adjust, and re-formulate text in a manner that could be highly relevant to this task 9,10 .”
Research works printed but not linked: 21
- Paasche-Orlow, M. K., Taylor, H. A. & Brancati, F. L. Readability standards for informed-consent forms as compared with actual readability. N. Engl. J. Med. 348, 721–726 (2003). · DOI · Paper page
- Sand, K., Eik-Nes, N. L. & Loge, J. H. Readability of informed consent documents (1987–2007) for clinical trials: a linguistic analysis. J. Empir. Res. Hum. Res. Ethics 7, 67–78 (2012). · DOI
- Bothun, L. S., Feeder, S. E. & Poland, G. A. Readability of participant informed consent forms and informational documents: from phase 3 COVID-19 vaccine clinical trials in the United States. Mayo Clin. Proc. 96, 2095–2101 (2021). · DOI
- Grundner, T. M. On the readability of surgical consent forms. N. Engl. J. Med. 302, 900–902 (1980). · DOI · Paper page
- Amezcua, L., Rivera, V. M., Vazquez, T. C., Baezconde-Garbanati, L. & Langer-Gould, A. Health disparities, inequities, and social determinants of health in multiple sclerosis and related disorders in the US: a review. JAMA Neurol. 78, 1515–1524 (2021). · DOI · Paper page
- Kessels, R. P. Patients’ memory for medical information. J. R. Soc. Med. 96, 219–222 (2003).
- Yee, L. M. et al. Association of health literacy among nulliparous individuals and maternal and neonatal outcomes. JAMA Netw. Open 4, e2122576 (2021). · DOI
- Spatz, E. S. et al. An instrument for assessing the quality of informed consent documents for elective procedures: development and testing. BMJ Open 10, e033297 (2020). · DOI
- Eltorai, A. E. et al. Readability of invasive procedure consent forms. Clin. Transl. Sci. 8, 830–833 (2015). · DOI
- Gordon, E. J. et al. Are informed consent forms for organ transplantation and donation too difficult to read? Clin. Transplant. 26, 275–283 (2012). · DOI
- Hannabass, K. & Lee, J. Readability analysis of otolaryngology consent documents on the iMed consent platform. Mil. Med. 188, 780–785 (2023). · DOI
- Yusefi, A. R. et al. Health literacy and health promoting behaviors among inpatient women during COVID-19 pandemic. BMC Womens Health 22, 77 (2022). · DOI
- Glaser, J. et al. Interventions to improve patient comprehension in informed consent for medical and surgical procedures: an updated systematic review. Med. Decis. Making 40, 119–143 (2020). · DOI · Paper page
- Rivera Perla, K. M. et al. Predicting access to postoperative treatment after glioblastoma resection: an analysis of neighborhood-level disadvantage using the Area Deprivation Index (ADI). J. Neurooncol. 158, 349–357 (2022). · DOI
- Ammanuel, S. G., Edwards, C. S., Alhadi, R. & Hervey-Jumper, S. L. Readability of online neuro-oncology-related patient education materials from tertiary-care academic centers. World Neurosurg. 134, e1108–e1114 (2020). · doi:10.1016/j.wneu.2019.11.109
- Hansberry, D. R. et al. Analysis of the readability of patient education materials from surgical subspecialties. Laryngoscope 124, 405–412 (2014). · DOI
- Goss, R. M. Investigations of doctors by General Medical Council. The procedure for consent still leaves much to be desired. BMJ 321, 111 (2000). · doi:10.1136/bmj.321.7253.111
- Ozhan, M. O. et al. Do the patients read the informed consent? Balkan Med. J. 31, 132–136 (2014). · doi:10.5152/balkanmedj.2014.13212
- Ntonti, P. et al. A systematic review of reading tests. Int. J. Ophthalmol. 16, 121–127 (2023). · doi:10.18240/ijo.2023.01.18
- Sarica, S. & Luo, J. Stopwords in technical language processing. PLoS One 16, e0254937 (2021). · DOI · Paper page
- Spatz, E. S. et al. Quality of informed consent documents among U.S. hospitals: a cross-sectional study. BMJ Open 10, e033299 (2020). · doi:10.1136/bmjopen-2019-033299
Cited by
Large language models in patient education: a scoping review of applications in medicine
Aydin, S., Karabacak, M., Vlachos, V., & Margetis, K. (2024) · Frontiers in Medicine · doi:10.3389/fmed.2024.1477898 · Cited by 288
Artificial intelligence in surgery
Varghese, C., Harrison, E. M., O’Grady, G., & Topol, E. J. (2024) · Nature Medicine · doi:10.1038/s41591-024-02970-3 · Cited by 287
Resnik, D. B., & Hosseini, M. (2025) · AI and Ethics · doi:10.1007/s43681-024-00493-8 · Cited by 228
“• Writing and editing scientific papers, grant proposals, consent forms, and institutional review board applications [3, 53, 54, 82, 163].”
Assessing the research landscape and clinical utility of large language models: a scoping review
Park, Y.-J., Pillai, A., Deng, J., Guo, E., Gupta, M., Paget, M., & Naugler, C. (2024) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-024-02459-6 · Cited by 187
“Reported benefits of using LLMs like ChatGPT for communication with patients included providing quick, readable (i.e. approximately 8th-grade level, according to Ali et al. [26]), and often-times accurate instructions and analysis of test results to patients and their providers [23–28].”
BackgroundMethodThe quality and safety of using generative AI to produce patient-centred discharge instructions
Stanceski, K., Zhong, S., Zhang, X., Khadra, S., Tracy, M., Koria, L., Lo, S., Naganathan, V., Kim, J., Dunn, A. G., et al. (2024) · npj Digital Medicine · doi:10.1038/s41746-024-01336-w · Cited by 45
Metadata
- Authors
- Ali, R., Connolly, I. D., Tang, O. Y., Mirza, F. N., Johnston, B., Abdulrazeq, H. F., Lim, R. K., Galamaga, P. F., Libby, T. J., Sodha, N. R., Groff, M. W., Gokaslan, Z. L., Telfeian, A. E., Shin, J. H., Asaad, W. F., Zou, J., & Doberstein, C. E.
- Venue
- npj Digital Medicine
- Published
- 2024-03-08
- Volume
- 7
- Issue
- 1
- Pages
- 63-63
- ISSN
- 2398-6352 (ISSN-L)
- OpenAlex
- W4392598276
- Cited by
- 78
- References
- 4
- FWCI
- 6.09
- Type
- journal article
- Language
- en
- Update notices
- correction (2024-04-12)
- Open access
- gold
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Bridging the literacy gap for surgical consents: an AI-human expert collaborative approach. https://app.cochat.ai/papers/10.1038/s41746-024-01039-2
- The paper
- Ali, R., Connolly, I. D., Tang, O. Y., Mirza, F. N., Johnston, B., Abdulrazeq, H. F., Lim, R. K., Galamaga, P. F., Libby, T. J., Sodha, N. R., Groff, M. W., Gokaslan, Z. L., Telfeian, A. E., Shin, J. H., Asaad, W. F., Zou, J., & Doberstein, C. E. (2024). Bridging the literacy gap for surgical consents: an AI-human expert collaborative approach. npj Digital Medicine. https://doi.org/10.1038/s41746-024-01039-2
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.