Objective:
To assess the effectiveness of chatbots in providing patient education about keratoconus compared to traditional resources, specifically the American Academy of Ophthalmology (AAO) website.
Key Findings:
- Bard scored significantly higher than ChatGPT-3.5, Copilot, and the AAO website in understandability and actionability (p < 0.001).
- Bard and ChatGPT outperformed the AAO website in the same metrics (p = 0.001).
- The AAO website had a higher Flesch Reading Ease score compared to Bard (p = 0.017).
Interpretation:
Chatbots can provide accurate and understandable information for keratoconus patients, potentially serving as a valuable educational resource under clinician supervision, which is crucial for ensuring the quality of information.
Limitations:
- The study's sample size and scope may limit the generalizability of the findings, as a larger and more diverse sample could yield different results.
- Responses from chatbots may vary based on updates and training data, affecting consistency.
Conclusion:
Chatbots show promise in enhancing patient education for keratoconus, potentially alleviating the educational burden on healthcare providers.
This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.