Clinical Report: Assessment of AI-Generated Content on Acute Cholecystitis
Overview
This study evaluates the reliability and readability of AI-generated information on acute cholecystitis from ChatGPT®, Gemini®, and Perplexity® in English and Spanish.
Background
Acute cholecystitis is a common surgical condition and a leading cause of upper abdominal emergencies, primarily due to gallstones. The increasing use of AI language models for medical information necessitates an assessment of their reliability and clarity.
Data Highlights
No numerical data or trial data were provided in the source material.
Key Findings
The study assessed AI-generated responses from ChatGPT®, Gemini®, and Perplexity® regarding acute cholecystitis.
Responses were evaluated for reliability and readability in both English and Spanish.
The research adhered to STROBE guidelines and was approved by an ethics committee.
A total of 42 responses were generated based on seven standardized clinical questions.
The study highlights the variability in the quality of AI-generated medical information.
Clinical Implications
Healthcare professionals should critically evaluate AI-generated medical information before use in clinical practice. The findings suggest that while AI tools can provide information, their reliability and clarity may vary significantly.
Conclusion
The study underscores the importance of assessing the quality of AI-generated content in medical contexts, particularly for conditions like acute cholecystitis. Ongoing evaluation is necessary as AI tools continue to evolve.
by Mabel Lucero Olarte Jurado, Natalia Pimiento Blanco, María José Prieto Otero, Laura Sofía Rivera González, Miguel Enrique Ochoa Vera, Jaime Fernando Barajas, Cristian Orlando Porras Bueno
