OBJECTIVE: This study aims to investigate the accuracy of a contactless BP monitor software app for classifying the full range of clinically relevant BPs as hypertensive or nonhypertensive and to evaluate its accuracy for measuring the pulse rate (PR) and BP of people with BPs relevant to stage-1 hypertension.
METHODS: The software app, known commercially as Lifelight, was investigated following the data collection and data analysis methodology outlined in International Organization for Standardization (ISO) 81060-2:2018/AMD 1:2020 \"Non-invasive Sphygmomanometers-Part 2: Clinical investigation of automated measurement type.\" This validation study was conducted by the independent laboratory Element Materials Technology Boulder (formerly Clinimark). The study generated data from 85 people aged 18-85 years with a wide-ranging distribution of BPs specified in ISO 81060-2:2018/AMD 1:2020. At least 20% were required to have Fitzpatrick scale skin tones of 5 or 6 (ie, dark skin tones). The accuracy of the app\'s BP measurements was assessed by comparing its BP measurements with measurements made by dual-observer manual auscultation using the same-arm sequential method specified in ISO 81060-2:2018/AMD 1:2020. The accuracy of the app\'s PR measurements was assessed by comparing its measurements with concurrent electroencephalography-derived heart rate values.
RESULTS: The app measured PR with an accuracy root-mean-square of 1.3 beats per minute and mean absolute error of 1.1 (SD 0.8) beats per minute. The sensitivity and specificity with which it determined that BPs exceeded the in-clinic systolic threshold for hypertension diagnosis were 70.1% and 71.7%, respectively. These rates are consistent with those reported for conventional BP monitors in a literature review by The National Institute for Health and Care Excellence. The app\'s mean error for measuring BP in the range of normotension and stage-1 hypertension (ie, 65/85, 76% of participants) was 6.5 (SD 12.9) mm Hg for systolic BP and 0.4 (SD 10.6) mm Hg for diastolic BP. Mean absolute error was 11.3 (SD 10.0) mm Hg and 8.6 (SD 6.8) mm Hg, respectively.
CONCLUSIONS: A calibration-free, software-only medical device was independently tested against ISO 81060-2:2018/AMD 1:2020. The safety and performance demonstrated in this study suggest that this technique could be a potential solution for rapid and scalable screening and management of hypertension.
目的:本研究旨在研究非接触式BP监测软件应用程序的准确性,用于将所有临床相关BP分类为高血压或非高血压,并评估其测量脉搏率的准确性(PR)和与1期高血压相关的BP患者的BP。
方法:软件应用程序,商业上被称为Lifelight,根据国际标准化组织(ISO)81060-2:2018/AMD1:2020中概述的数据收集和数据分析方法进行了研究。“非侵入性血压计-第2部分:自动测量类型的临床研究。“这项验证研究是由独立实验室ElementMaterialsTechnologyBoulder(以前的Clinimark)进行的。该研究从85名年龄在18-85岁之间的人中收集了数据,这些人的BP分布广泛,在ISO81060-2:2018/AMD1:2020中。至少需要20%的Fitzpatrick音阶肤色为5或6(即,深色肤色)。通过将其BP测量值与使用ISO81060-2:2018/AMD1:2020中指定的同臂顺序方法通过双观察者手动听诊进行的测量值进行比较来评估应用程序的BP测量值的准确性。通过将其测量值与并发脑电图得出的心率值进行比较来评估应用的PR测量值的准确性。
结果:该应用程序以每分钟1.3次搏动的精度均方根和每分钟1.1(SD0.8)次搏动的平均绝对误差测量PR。确定BPs超过临床收缩压阈值诊断高血压的敏感性和特异性分别为70.1%和71.7%。分别。这些比率与美国国家健康与护理卓越研究所的文献综述中报道的常规BP监测仪的比率一致。在正常血压和1期高血压范围内测量BP的应用程序平均误差(即,65/85,76%的参与者)收缩压为6.5(SD12.9)mmHg,舒张压为0.4(SD10.6)mmHg。平均绝对误差为11.3(SD10.0)mmHg和8.6(SD6.8)mmHg,分别。
结论:无需校准,纯软件医疗设备根据ISO81060-2:2018/AMD1:2020进行了独立测试。这项研究中证明的安全性和性能表明,该技术可能是快速,可扩展的高血压筛查和管理的潜在解决方案。