Three of the four most popular artificial intelligence (AI) search tools correctly identified home blood pressure monitors that met validated clinical standards only 63% to 83% of the time, according to preliminary research presented at the American Heart Association's Hypertension Scientific Sessions 2026. The study, conducted in Canada between April and May 2026, tested 324 home blood pressure monitors—145 validated and 179 not validated—using Google Gemini, Microsoft Copilot, ChatGPT, and Perplexity. Google Gemini performed best, answering correctly 86% to 91% of the time, but still provided incorrect responses about 10% to 15% of the time.
High blood pressure affects more than 125 million adults in the U.S., about 47%, according to the American Heart Association's 2026 Heart Disease and Stroke Statistics Update. Only about 1 in 4 of those adults have their blood pressure within the target range of less than 120/80 mm Hg. The 2025 American Heart Association Guideline for the Prevention, Detection, Evaluation, and Management of High Blood Pressure in Adults recommends using a validated home blood pressure monitor, which can be confirmed by visiting www.validatebp.org or validatebp.org.
"We found that most AI tools performed only slightly better than if you had flipped a coin for each question," said Anna Soriano, M.D., a third-year internal medicine resident at the University of Montreal and the study's presenting author. "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."
All four AI tools were less accurate at identifying validated monitors compared to unvalidated ones. When researchers retested devices with mixed results on different days or computers, the AI tools often produced different answers. "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.
Keith C. Ferdinand, M.D., FAHA, an American Heart Association volunteer expert and vice chair of the Association's 2025 High Blood Pressure Guideline, emphasized 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. In addition, home blood pressure devices need to be both validated and accurate."
The findings underscore the importance of verifying device validation through independent registries rather than relying on AI tools. The study's limitations include potential changes as AI technology improves and the inability to fully prevent language model training despite using private browsing sessions. The research will be presented at 5:30 p.m. on Thursday, October 8, 2026, and the abstracts will be published in the Hypertension Scientific Sessions 2026 Supplement of the Hypertension journal on November 17, 2026.
