Qualitatively Assessing ChatGPT Responses to Frequently Asked Questions Regarding Sexually Transmitted Diseases

Area of Science:

• Artificial Intelligence in Healthcare
• Public Health Informatics
• Natural Language Processing

Background:

• Large language models like ChatGPT are increasingly used in healthcare.
• Understanding ChatGPT's accuracy for public health inquiries is limited.
• This study evaluates ChatGPT's responses to common sexually transmitted disease (STD) questions.

Purpose of the Study:

• To assess the accuracy, clarity, and appropriateness of ChatGPT's answers to frequently asked questions about STDs.
• To determine the potential of AI as a tool for public health education regarding STDs.

Main Methods:

• Ten common STD questions were sourced from 25 government websites.
• ChatGPT provided responses to these questions.
• Responses were graded on a 4-point scale for accuracy, clarity, and appropriateness using evidence-based criteria.

Main Results:

• Four out of ten responses were rated excellent, needing no clarification.
• Six responses required minimal clarification.
• All responses appropriately advised consulting a healthcare professional; none were unsatisfactory.

Conclusions:

• ChatGPT demonstrates potential as a supplementary tool for patient education on STDs.
• Further research is needed to integrate AI into public health strategies for STD-related concerns.