Millions of people are now using AI chatbots every week to navigate health questions.
While many say the technology has proved useful, it can generate hallucinations and make mistakes — some of which have had serious consequences.
How you prompt a chatbot matters, said Dr. Adam Rodman, an internist and director of AI programs for the Carl J. Shapiro Institute for Education and Research at Beth Israel Deaconess Medical Center. He uses a traffic-light style system to help guide patients.
Rodman emphasized these guidelines are not set in stone and reflect the current capabilities of large language models, such as ChatGPT, Claude, and Gemini. He said his guidance will likely change as models improve and become more deeply integrated into the health system.
Several companies now offer health-specific AI agents, but it’s important to understand privacy policies before uploading personal medical information.
Here’s how Rodman recommends using — and not using — chatbots if you have health questions.
Allyson Chiu can be reached at allyson.chiu@globe.com. Follow her on X @_allysonchiu.