Summary: A new study explores the potential of AI assistants, such as ChatGPT, in providing accurate and actionable responses to public health questions.
The study evaluated ChatGPT’s ability to address a range of common health queries and found that it provided evidence-based responses to 91% of the questions. However, only 22% of the responses included referrals to specific resources, indicating room for improvement in connecting users with appropriate help.
Key Facts:
- ChatGPT, an AI assistant, was tested on 23 public health questions across categories like addiction, interpersonal violence, mental health, and physical health.
- The study revealed that ChatGPT mirrored subject matter expert support in its responses, often aligning with evidence-based guidelines for various health concerns.
- While ChatGPT demonstrated knowledge in answering questions, there is a need for better integration of specific resource referrals to ensure users can access the necessary support and expert guidance.
Source: UCSD