A novel smartphone app for blood pressure measurement: a proof-of-concept study against an arterial catheter

Hofmann, Gregory; Proença, Martin; Degott, Jean; Bonnier, Guillaume; Lemkaddem, Alia; Lemay, Mathieu; Schorer, Raoul; Christen, Urvan; Knebel, J-F; Schoettker, Patrick

doi:10.1007/s10877-022-00886-2

Cited by 7 publications

(5 citation statements)

References 44 publications

(49 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The second dataset is from a study at the Lausanne University Hospital (CHUV, Lausanne, Switzerland) in collaboration with the Geneva University Hospital (HUG, Geneva, Switzerland) [9] approved by the local ethics committee (CER-VD no. 2018-01656; NCT03875248 at ClinicalTrials.gov).…”

Section: Datasetsmentioning

confidence: 99%

Generalization Capability of a Neural Network for Blood Pressure Estimation from Photoplethysmography

Aguet¹,

Zaen²,

Proença³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

Photoplethysmography (PPG) is one of the most promising alternatives for non-invasive and cuffless blood pressure (BP) monitoring. In recent years, several machine learning approaches have been considered for this task: either feature engineering-based to map PPGderived features into BP values or feature learning-based with an automated feature extraction process. The generalization capability, namely the ability of a model to adapt to unseen data, is an important aspect of such datadriven models due to the heterogeneity of PPG waveforms. However, in published studies, this point is generally omitted. Therefore, we propose to assess the generalization capability of a feature learning model built to estimate BP from PPG signals by comparing the model accuracy (bias) and precision (standard deviation of the error) on two datasets with different recording protocols. On unseen subjects from the training dataset, the proposed model achieved mean and standard deviation errors of -0.88±10.29 mmHg for systolic BP (SBP) and -0.60±5.76 mmHg for diastolic BP (DBP). Whereas, on the other dataset, the same metrics were 1.13±12.86 mmHg for SBP and -0.44±6.99 mmHg for DBP. Taken together, these results show that a feature learning model can extract feature representation that are generalizable over different populations and different PPG sensors.

show abstract

Section: Datasetsmentioning

confidence: 99%

Generalization Capability of a Neural Network for Blood Pressure Estimation from Photoplethysmography

Aguet¹,

Zaen²,

Proença³

et al. 2022

Computing in Cardiology Conference (CinC)

View full text Add to dashboard Cite

show abstract

“…This BP estimation technique was subsequently migrated onto smartphone camera lenses to facilitate more common use. The smartphone application with the OptiBP TM was assessed in Switzerland against both arterial measurements recorded at the fingertips during general anesthesia 13 and reference auscultatory measurements based on the ISO 81,060-2:2018 standards. These studies demonstrated general concordance of OptiBP with reference measurements and highlighted performance gaps in estimating systolic arterial presure [13][14][15][16] .…”

Section: Introductionmentioning

confidence: 99%

“…The smartphone application with the OptiBP TM was assessed in Switzerland against both arterial measurements recorded at the fingertips during general anesthesia 13 and reference auscultatory measurements based on the ISO 81,060-2:2018 standards. These studies demonstrated general concordance of OptiBP with reference measurements and highlighted performance gaps in estimating systolic arterial presure [13][14][15][16] . While this research highlighted the potential of OptiBP, these assessments lacked independent evaluations in line with global validation standards and were conducted exclusively in high-income settings.…”

Section: Introductionmentioning

confidence: 99%

Accuracy of a smartphone application for blood pressure estimation in Bangladesh, South Africa, and Tanzania

et al. 2023

View full text Add to dashboard Cite

Undetected and unmonitored hypertension carries substantial mortality and morbidity, especially during pregnancy. We assessed the accuracy of OptiBPTM, a smartphone application for estimating blood pressure (BP), across diverse settings. The study was conducted in community settings: Gaibandha, Bangladesh and Ifakara, Tanzania for general populations, and Kalafong Provincial Tertiary Hospital, South Africa for pregnant populations. Based on guidance from the International Organization for Standardization (ISO) 81,060–2:2018 for non-invasive BP devices and global consensus statement, we compared BP measurements taken by two independent trained nurses on a standard auscultatory cuff to the BP measurements taken by a research version of OptiBPTM called CamBP. For ISO criterion 1, the mean error was 0.5 ± 5.8 mm Hg for the systolic blood pressure (SBP) and 0.1 ± 3.9 mmHg for the diastolic blood pressure (DBP) in South Africa; 0.8 ± 7.0 mmHg for the SBP and −0.4 ± 4.0 mmHg for the DBP in Tanzania; 3.3 ± 7.4 mmHg for the SBP and −0.4 ± 4.3 mmHg for the DBP in Bangladesh. For ISO criterion 2, the average standard deviation of the mean error per subject was 4.9 mmHg for the SBP and 3.4 mmHg for the DBP in South Africa; 6.3 mmHg for the SBP and 3.6 mmHg for the DBP in Tanzania; 6.4 mmHg for the SBP and 3.8 mmHg for the DBP in Bangladesh. OptiBPTM demonstrated accuracy against ISO standards in study populations, including pregnant populations, except in Bangladesh for SBP (criterion 2). Further research is needed to improve performance across different populations and integration within health systems.

show abstract

“…11,12 This BP estimation technique was subsequently migrated onto smartphone camera lenses to facilitate more common use. The smartphone application with the OptiBP™ is being assessed in Switzerland against both arterial measurements during general anesthesia 13 and reference auscultatory measurements based on the ISO 81,060-2:2018 standards. [13][14][15][16] To ensure the accuracy of OptiBP™ across different environmental conditions and demographic pro les, we conducted a multi-site assessment study in Tanzania and Bangladesh among general populations, and in South Africa among a pregnant population.…”

Section: Introductionmentioning

confidence: 99%

“…The smartphone application with the OptiBP™ is being assessed in Switzerland against both arterial measurements during general anesthesia 13 and reference auscultatory measurements based on the ISO 81,060-2:2018 standards. [13][14][15][16] To ensure the accuracy of OptiBP™ across different environmental conditions and demographic pro les, we conducted a multi-site assessment study in Tanzania and Bangladesh among general populations, and in South Africa among a pregnant population. The inclusion of pregnant populations was particularly important to align with the study's key objective of assessing innovations to improve BP screening within routine antenatal care and management of hypertensive disorders of pregnancy.…”

Section: Introductionmentioning

confidence: 99%

Innovations to address the burden of hypertension: Assessing accuracy of a smartphone application-based blood pressure estimation algorithm in Bangladesh, South Africa and Tanzania among general and pregnant populations

Tamrat

Festo

Vannevel

et al. 2022

Preprint

View full text Add to dashboard Cite

Background: Undetected and unmonitored hypertension carries substantial mortality and morbidity, especially during pregnancy. Innovations have potential to address these challenges. We assessed the accuracy of OptiBPTM, a smartphone application for estimating blood pressure (BP), across diverse settings. Methods: The study was conducted in community settings: Gaibandha, Bangladesh and Ifakara, Tanzania for the general population, and Kalafong Provincial Tertiary Hospital, South Africa for pregnant populations. Based on guidance from the International Organization for Standardization (ISO) 81,060–2:2018 and global consensus statement, we compared BP measurements taken by two independent trained nurses on a standard auscultatory cuff to the BP measurements taken by a research version of OptiBPTM called CamBP. Results: For ISO criterion 1, the mean error was 0.5 ± 5.8 mm Hg for the SBP and 0.1 ± 3.9 mmHg for the DBP in South Africa; 0.8 ± 7.0 mmHg for the SBP and -0.4 ± 4.0 mmHg for the DBP in Tanzania; 3.3 ± 7.4 mmHg for the SBP and -0.4 ± 4.3 mmHg for the DBP in Bangladesh. For ISO criterion 2, the average standard deviation of the mean error per subject was 4.9 mmHg for the systolic BP and 3.4 mmHg for the diastolic BP in South Africa; 6.3 mmHg for the systolic BP and 3.6 mmHg for the diastolic BP in Tanzania; 6.4 mmHg for the systolic BP and 3.8 mmHg for the diastolic BP in Bangladesh. Conclusion: OptiBPTM demonstrated accuracy against ISO standards in study populations, including pregnant populations, except in Bangladesh for systolic BP (criterion 2). Further research is needed to improve performance across different populations and integration within health systems. Funding: This work was funded by the Bill and Melinda Gates Foundation (grant number OPP1201339) and the UNDP-UNFPA-UNICEF-WHO-World Bank Special Programme of Research, Development and Research Training in Human Reproduction (HRP), a cosponsored programme executed by the World Health Organization (WHO).

show abstract

A novel smartphone app for blood pressure measurement: a proof-of-concept study against an arterial catheter

Cited by 7 publications

References 44 publications

Generalization Capability of a Neural Network for Blood Pressure Estimation from Photoplethysmography

Generalization Capability of a Neural Network for Blood Pressure Estimation from Photoplethysmography

Accuracy of a smartphone application for blood pressure estimation in Bangladesh, South Africa, and Tanzania

Innovations to address the burden of hypertension: Assessing accuracy of a smartphone application-based blood pressure estimation algorithm in Bangladesh, South Africa and Tanzania among general and pregnant populations

Contact Info

Product

Resources

About