The US FDA has cleared the Apple Watch hypertension detection feature on some of its smartwatches. #photoplethysmography (PPG) continuous #blood #pressure estimation. www.reuters.com/sustainabili...
What is PPG? A refresher. eureka.patsnap.com/article/smar...

Estimation of Brachial-Ankle Pulse Wave Velocity With Hierarchical Regression Model From Wrist Photoplethysmography and Electrocardiographic Signals: Method Design Background: Photoplethysmography (PPG) signals captured by wearable devices can provide vascular age information and support pervasive and long-term monitoring of personal health condition. Objective: In this study, we aimed to estimate brachial-ankle pulse wave velocity (baPWV) from wrist PPG and electrocardiography (ECG) from smart watch. Methods: A total of 914 wrist PPG and ECG sequences and 278 baPWV measurements were collected via the smart watch from 80 men and 82 women with average age of 63.4 ± 13.4 and 64.3 ± 11.6 years. Feature extraction and weighted pulse decomposition were applied to identify morphological characteristics regarding blood volume change and component waves in pre-processed PPG and ECG signals. A systematic strategy of feature combination was performed. The hierarchical regression method based on the random forest for classification and extreme gradient boosting (XGBoost) algorithms for regression was employed, which first classified the data into subdivisions. The respective regression model for the subdivision was constructed with an overlapping zone. Results: By using 914 sets of wrist PPG and ECG signals for baPWV estimation, the hierarchical regression model with 2 subdivisions and an overlapping zone of 400 cm/s achieved root mean square error (RMSE) of 145.0 cm/s and 141.4 cm/s for 24 men and 26 women, respectively, which is better than the general XGBoost regression model and the multivariable regression model (all P < 0.001). Conclusions: We for the first time demonstrated that baPWV could be reliably estimated by the wrist PPG and ECG signals measured by the wearable device. Whether our algorithm could be applied clinically needs further verification.

New JMIR BioMedEng: Estimation of Brachial-Ankle Pulse Wave Velocity With Hierarchical Regression Model From Wrist Photoplethysmography and Electrocardiographic Signals: Method Design #HealthTech #WearableDevices #Photoplethysmography #ECG #PulseWaveVelocity

Remote Photoplethysmography Technology for Blood Pressure and Hemoglobin Level Assessment in the Preoperative Assessment Setting: Algorithm Development Study Background: Various studies have been written about noninvasive, remote photoplethysmography-based measurement of blood pressure (BP) and, to a lesser extent, hemoglobin (Hb) concentration. Widespread applicability has yet to be achieved due to limitations with agreement and correlation. There is also limited data on rPPG BP and Hb measurement evaluation in representative populations at the preoperative evaluation clinic (PEC) setting, such as hypertensive patients and patients with diverse, varying skin tones. Objective: We assessed the accuracy of rPPG technology in noninvasive systolic BP (SBP) and diastolic BP (DBP) measurements compared to automated cuffed blood pressure measuring devices (BPMD). Additionally, we compared the accuracy of rPPG Hb concentration measurement to that of clinical laboratory testing. Methods: Nervotec rPPG telehealth and smartphone software utilizes the principle that reflected light from various skin areas is affected by the volume of blood under the skin, which varies according to arterial pulsations and blood flow. This principle allows for an optical measurement technique that measures these variations. The measurements are then analyzed with signal processing algorithms which generate physiological measurements such as BP and Hb. The study was conducted at Singapore General Hospital (SGH) from 15 February 2023 to 6 December 2024. The participants were recruited in two phases. The first group, used for training and evaluating the algorithm, consisted of 100 patients with a mean age of 52.9 ± 13.1 years. In this group, 59% of patients had concomitant medical diseases such as hypertension (HTN) and diabetes mellitus (DM). The second group, used for validation of the algorithm, consisted of 65 patients with a mean age of 55.15 ± 17.27 years. 43% of the patients had concomitant medical conditions such as HTN, DM and ischemic heart disease (IHD). Both groups had an even distribution of males and females, as well as a diverse range of skin tones (1-10) classified according to the Monk Skin Tone (MST) scale. The primary analysis was focused on assessing the accuracy of rPPG BP measurements compared to BPMD BP measurements. The secondary analysis aimed to evaluate the accuracy of rPPG Hb concentration measurement compared to clinical laboratory testing. Results: Our study demonstrated an accuracy of 83.84% for SBP and 90.55% for DBP, with mean absolute percentage errors (MAPE) of 16.16% for SBP and 9.45% for DBP. Furthermore, the model could predict Hb concentration with an accuracy of 88.41%. MAPE was 11.59%, with an error bias of 0.54 g/dL and an error SD of 1.82 g/dL. Conclusions: Our study is the first to evaluate contactless rPPG BP and Hb concentration measurements in a diverse, heterogeneous study population. The model achieved a DBP accuracy rate of 90.55% with a MAPE of 9.45%. We recorded a MAPE of 16.16% for SBP, and a MAPE of 11.59% for Hb concentration. Quartile evaluation indicated stronger correlations in mid-quartile ranges for DBP (70-74 mmHg) and Hb (13.2 - 14.4 g/dL), confirming the model’s reliability in detecting moderate deviations from normal physiological states. Our current model performance carries potential as a triaging tool within both hospital and population health settings. Clinical Trial: The study was approved by the SingHealth Centralised Institutional Review Board (CIRB Ref: 2023/2042) from 15 February 2023 to 6 December 2024 and is registered on ClinicalTrials.gov (Trial number: NCT06320847).

JMIR Formative Res: Remote Photoplethysmography Technology for Blood Pressure and Hemoglobin Level Assessment in the Preoperative Assessment Setting: Algorithm Development Study #RemoteHealth #Photoplethysmography #BloodPressure #Hemoglobin #NoninvasiveTech

Physiological Measurement front cover with IOPP logo and IPEM logo side by side.

Are you working on recent advances in #photoplethysmography (PPG) utilising artificial intelligence? If so, this focus collection issue is for you! Submissions will be accepted until 30th September 2025.

Find more here: ow.ly/9obv50V48LT 🧪⚛️

#AI #PMEA