返回全部动态

Google 用智能手表传感器被动检测高血压迹象

原标题:Detecting signs of hypertension using wearable sensors

Google Research Blog一手来源研究质量 78

AI 摘要

Google Research 在 Nature 发表研究,提出 AI-PPG-ACC-HTN 多模态 AI 系统,利用智能手表的光电容积脉搏波(PPG)和加速度计(ACC)传感器被动检测高血压迹象,无需袖带校准。该系统采用自监督对比学习训练一维深度卷积网络,并在 196 名参与者的多中心前瞻性研究中以 24 小时动态血压监测为金标准验证,初筛灵敏度 65.8%、特异度 90.0%,确认性检测灵敏度 78.4%、特异度 90.9%,性能与传统袖带流程相当。相关发现已用于 Google Health 应用中的血压趋势 Health Guardian 功能。

以上摘要由 AI 生成,可能存在误差。事实请以原文为准。

正文节选

November 5, 2026 Paolo Di Achille, Staff Research Scientist, and Ming-Zher Poh, Senior Staff Research Scientist, Google Research We present a new AI system that leverages standard consumer smartwatch sensors to passively detect signs of high blood pressure. Hypertension (i.e., high blood pressure), often called the "silent killer”, affects over one billion people globally, yet more than half of adults with the condition are unaware they have it. Because it rarely presents with obvious symptoms,


发布时间:2026-11-06 00:01
抓取时间:2026-11-06 00:57
来源机构:Google Research
阅读原文research.google