Speaker
Fatima N. Mirza, MD, MPH
Chief Resident
Department of Dermatology
Warren Alpert Medical School of Brown University
Keywords
Artificial Intelligence; ChatGPT; Informed Consent
Key Points
- Artificial Intelligence (AI), when implemented thoughtfully in clinical settings, can lead to meaningful results for patients.
- Medicine has long fallen short of the ideal of informed consent, in part due to the limited readability of informed consent forms; as of 2020, 54% of Americans were estimated to read below the sixth-grade reading level. This has implications for patient understanding and quality of care.
- Using ChatGPT-4, the research team took LifeSpan Healthcare System’s (LHS) surgical consent form from a 12.6 Flesch-Kincaid reading level to a 6.7. After hospital leadership reviewed the revised form and the research team had addressed concerns around biases, approvals, and future needs, the revised form was deployed across LHS.
- This real-world implementation demonstrated the potential for AI to make meaningful improvements to patient care and communication. As a proof-of-concept, it sparked the interest of other health systems.
- To investigate the clinical implications of consent form readability, the research team analyzed 798 federally funded clinical trials providing accessible informed consent forms. A 16% increase in the dropout rate was associated with each additional Flesch-Kincaid grade-level increase in the language.
- The observed association between consent form complexity and participant dropout rate could be attributed to misaligned expectations; erosion of trust; participant surprise and dissatisfaction; and reduced engagement. This highlights the importance of clear, accessible communication throughout the entire trial process, not just enrollment.
- Improved readability of consent forms is crucial for the design and implementation of clinical trials, potentially leading to more inclusive, efficient, and impactful clinical research.
Discussion Themes
Medical malpractice attorneys were part of the cohort that reviewed the simplified consent forms. They shared that when these cases go to court, a jury will often review the informed consent document. In these cases, it can more protective to have documentation that people can understand.
There is the potential for tailored chatbots that could personalize the consent process for patients, but expert oversight would be crucial. AI models can “hallucinate,” saying something incorrect with absolute certainty. Dr. Mirza indicated that the field isn’t ready for those bespoke consents; centralized documents, as least for the time being, are the way to go.
AI is going to be integrated into our healthcare system. It’s important for clinicians, researchers, and people who really care about patients, as well as the patients themselves, to have a seat at the table discussing these early models.