跳到正文
原文
Medical Xpress·· 2026-10-08AI 评分40

研究称主流AI搜索工具在家用血压计验证查询上回答不可靠

Leading AI search tools give unreliable answers about home blood pressure monitor validation, research finds

AI 导读

一项在2026年美国心脏协会高血压科学大会上展示的初步研究发现,四款主流AI搜索工具准确识别符合临床验证标准的家用血压计的比例仅为63%至83%。其中Google Gemini表现最好,正确率最高达91%,但仍低于对未验证设备的识别准确率,且同一问题在不同日期或设备上的回答往往不一致。

正文
home blood pressure monitor
Credit: Unsplash/CC0 Public Domain

Three of four leading artificial intelligence (AI) search tools accurately identified home blood pressure monitors that met validated clinical standards only 63–83% of the time, according to preliminary research being presented at the American Heart Association's Hypertension Scientific Sessions 2026, held in Arlington, Virginia, Oct. 7–11.

High blood pressure is the No. 1 risk factor for cardiovascular disease, affecting 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 mm Hg/80 mm Hg.

The 2025 American Heart Association Guideline for the Prevention, Detection, Evaluation, and Management of High Blood Pressure in Adults recommends that people use a home blood pressure monitoring device that has been validated for accuracy. People can talk with their clinician and visit a website for more information.

Now that AI-powered search tools are integrated into all online platforms, people are increasingly asking AI tools for quick answers to health questions, including whether home health devices such as blood pressure monitors have been validated and meet clinical standards.

A home blood pressure monitor is considered validated when independent, third-party testing has proven it gives consistently accurate blood pressure readings, and there are three primary registries that list these devices. In this analysis, researchers found AI-powered chatbots were not reliable at making this determination.

"We found that most AI tools performed only slightly better than if you had flipped a coin for each question. Even Google Gemini, which performed best, was often wrong and couldn't find information that is easily located," 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," she added.

Key findings of the study

  • Researchers found that accuracy in identifying whether a home blood pressure monitor meets clinical standards varied significantly depending on the AI-powered tool used.
  • Google Gemini scored the highest—answering correctly 86% to 91% of the time depending on how the questions were phrased.
  • Correct responses from ChatGPT, Copilot and Perplexity ranged from only about 63% to 83%.
  • All four AI tools were less accurate at identifying validated BP monitors than unvalidated monitors.
  • When researchers retested the AI tools' responses for devices that had mixed accuracy results, asking the same AI tool the same questions—on a different day or from a different computer—the AI tools often produced a different answer.

Researchers also tested a wide range of devices, including lesser-known home blood pressure monitors, though researchers noted these still appear on the same official registries as more popular ones. The authors could not determine exactly why AI tools struggled with identifying 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."

"Artificial intelligence holds great promise to help support clinicians in areas such as cardiac imaging, electrocardiography, mobile devices and other tools," 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.

"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. 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, who was not involved in this study, is the Gerald S. Berenson Endowed Chair in Preventative Cardiology and professor of medicine at Tulane University School of Medicine in New Orleans.

A limitation of the study is that these results are likely to change as AI technology continues to improve with time. In addition, to limit each tool's ability to learn from previous test searches, scientists used private internet browsing sessions; however, this technique could not fully prevent language model training of the AI tools.

Who's behind this story?

Sadie Harley

Sadie Harley

BSc Life Sciences & Ecology. Microbiology lab background with pharmaceutical news experience in oil, gas, and renewable industries. Full profile →

Robert Egan

Robert Egan

Bachelor's in mathematical biology, Master's in creative writing. Well-traveled with unique perspectives on science and language. Full profile →

Citation: Leading AI search tools give unreliable answers about home blood pressure monitor validation, research finds (2026, October 8) retrieved 8 October 2026 from https://medicalxpress.com/news/2026-10-ai-tools-unreliable-home-blood.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

来源:Medical Xpress · medicalxpress.com