SMARTPHONE-BASED BLOOD PRESSURE MEASUREMENTS VALIDATION USING THE AAMI/ESH/ISO UNIVERSAL PROTOCOL: RESULTS FROM THE FIRST FORTY PATIENTS. (April 2021)

• Record Type: Journal Article
• Authors: Wuerzner, Gregoire; Degott, Jean; Hofmann, Gregory; Proença, Martin; Bonnier, Guillaume; Lemkaddem, Alia; Lemay, Mathieu; Schorer, Raoul; Christen, Urvan; Knebel, Jean -Francois; Brenet, Fanny; Eliott, Jones; Wuerzner, Arlène; Burnier, Michel; Schoettker, Patrick
• Is Part Of: Journal of hypertension. Volume 39(2021)e-Supplement 1
• Publication Date: 2021-04
• Subjects: Hypertension -- Periodicals; Hypertension -- Periodicals; 616.132005
• DOI: 10.1097/01.hjh.0000745788.35493.c0
• Languages: English
• ISSNs: 1473-5598

Abstract

Abstract: Objective: Hypertension is a preventable disease but only half of the affected population is aware of it. Digital health approaches, in particular mobile health diagnostics, have been shown to be effective and scalable for chronic disease detection and management. Smartphones are widely available and have the potential to be used as a "cuffless" blood pressure (BP) measuring devices. Using a smartphone-based pulse wave analysis algorithm (oBPMâ) trained with invasive blood pressure measurements, the objective was to assess the performance and accuracy of the oBPMâ in an outpatient setting. Design and method: We collected optical signals from patient's fingertip via a smartphone in an outpatient setting. After an initial calibration, smartphone optical BP were generated and compared to simultaneous acquired auscultatory systolic (SBP), diastolic (DBP) and mean (MBP) blood pressure in an initial set of participants in accordance with the AAMI/ESH/ISO universal consensus for the validation of BP measuring devices. Results: Signals acquired from 40 patients (range of age 21–78 years) generated 140 smartphone BP measurements. The prevalence of low, normal or elevated systolic blood pressure (SBP) was respectively 12.9%, 70.00% and 17.1 %. The prevalence of low, normal or elevated diastolic blood pressure (DBP) was respectively 25.0%, 61.4% and 13.6%. The mean difference in BP and its standard deviation between the optical vs. reference value were -0.7 ± 7·7 mmHg for the SBP, -0·4 ± 4·5 mm Hg for DBP and -0·6 ± 5·2 mmHg for mean blood pressure. These results were within the range of the ISO standards. Conclusions: These results demonstrate that BP can be measured with accuracy after an initial calibration using a smartphone and newly developed algorithm. If the accuracy of these smartphone-based measurements can be confirmed in various subtypes of population, it may become an important tool to detect and manage hypertension in various settings, in particular low income countries, where the availability of smartphones is high but access to health care is scarce.