The preprint “Using ChatGPT to Improve the Readability of Surgical Consent Forms” is an innovative exploration into the application of AI research to enhance the comprehensibility of surgical consent forms. The researchers implemented an AI model, ChatGPT, to simplify the language of these critical documents to a 13-year-old reading level, aiming to make them more accessible.
The study undertook two distinct tasks: first, the simplification of 15 existing consent forms, and second, the creation of 5 new ones. These revised and newly generated forms were evaluated by surgical staff and a medico-legal expert through a combination of qualitative and quantitative methods. However, a significant drawback of the study is the lack of patient involvement, a key stakeholder group in this context.
Nonetheless, the paper presents a compelling use case for AI in health care communication. It elicits anticipation of how health organisations might leverage such AI advancements to tackle health inequalities, especially among people with disabilities. Given that one in four individuals living in England are disabled, the potential impact of such initiatives could be substantial in making health care more accessible and understandable to all.
~
As Sanome continues to run Patient-Public Involvement workshops and translate our innovative technology, it is crucial that we are mindful of simplifying and translating the scientific and technical language for accessibility and health literacy for all.
From the Paper:
Background:
Despite the importance of informed consent in healthcare, the readability and specificity of consent forms often impedes patients’ comprehension. Health literacy is linked to patient outcomes, making it essential to address these issues. 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.
Methods:
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.
Results:
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.
Conclusions:
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. Ensuring AI technologies are safely incorporated into clinical practice is crucial to reach a wide range of patients, including the most vulnerable.
Read the pre-print here [as of, 28 June 2023]: https://www.medrxiv.org/content/10.1101/2023.05.06.23289615v1
