Because AI-powered search tools are now integrated into all online platforms, people increasingly ask them quick health questions — including whether a home blood pressure monitor has been validated and meets clinical standards.

What did the researchers find?

The study tested four widely used AI chatbots on their ability to determine whether specific home blood pressure monitors had been validated. Key results include:

• Accuracy varied significantly depending on the tool used, with Google Gemini scoring highest at 86–91% correct.
• ChatGPT, Copilot and Perplexity answered correctly only 63–83% of the time.
• All four tools were less accurate at identifying validated monitors than unvalidated ones.
• When researchers retested the same tools with the same questions — on a different day or from a different computer — the AI tools often produced a different answer for devices with mixed results.

The researchers also tested lesser-known home monitors, which appear on the same official registries as popular models. The team could not determine exactly why the AI tools struggled with devices that had already passed validation testing.

"It is surprising, and almost counterintuitive, that AI tools had so much difficulty specifically identifying validated devices, since those devices are the ones with clear listings on official registries," Soriano said. "In many cases, the AI tools found the blood pressure monitor was listed within an official website; however, it seems AI was not able to interpret being listed on the registry as proof of validation."

What are the risks of wrong answers?

Inaccurate AI responses could carry real health consequences. "People may unknowingly think a device is validated based on the AI tool's inaccurate responses. Using that device may result in inaccurate blood pressure readings, which could lead to an inappropriate diagnosis or treatment decisions," Soriano said.

Keith C. Ferdinand, M.D., FAHA, an American Heart Association volunteer expert and vice chair of the association's 2025 High Blood Pressure Guideline, urged caution. "The potential shortcomings of AI demonstrated by this study's results should remind clinicians and the public that the use of AI for clinical decision-making requires caution," said Ferdinand, who was not involved in the study and holds the Gerald S. Berenson Endowed Chair in Preventative Cardiology at Tulane University School of Medicine in New Orleans.

Ferdinand also emphasized that AI itself remains promising in medicine. "Artificial intelligence holds great promise to help support clinicians in areas such as cardiac imaging, electrocardiography, mobile devices and other tools," he said.

"In addition, home blood pressure devices need to be both validated and accurate. With the proper technique and regular monitoring, readings from home BP devices are a valuable component of integrated, individual treatment plans that can improve patient care and outcomes," Ferdinand added.

What are the study's limitations?

The findings are preliminary, come from a conference presentation rather than a peer-reviewed publication, and may change quickly. The authors note that results will likely shift as AI technology continues to improve.

To prevent each tool from learning from previous test searches, the researchers used private internet browsing sessions. They acknowledge, however, that this technique could not fully prevent the AI tools' language models from training on their queries.