The quest for blood pressure markers in photoplethysmography and its applications in digital health

Abstract

Introduction: Photoplethysmography (PPG) sensors, capturing optical signals from arterial pulses, are debated for their potential in blood pressure (BP) measurement. This study employed the largest dataset to date of paired PPG and cuff BP readings to explore PPG signals for BP estimation.

Methods: 32,152 European residents (age 55.9% ± 11.8, 24% female, BMI 27.7 ± 4.6) voluntarily acquired and used a cuffless BP monitor (Aktiia SA, Switzerland) between March/2,021-March/2023. Systolic and diastolic BP (SBP, DBP) from an upper arm oscillometric cuff were collected simultaneously with wrist PPG (668,080 paired measurements). Six different machine learning models were developed to predict BP using cuff BP readings as reference (75%|15%|15% training|validation|testing): four baseline models [heart rate (HR), Age, Demography (DEM: Age + Gender + BMI), DEM + HR], and two models relying on the analysis of the PPG waveforms (PPG, PPG + DEM). Performance of each model was evaluated on the 4,823 subjects from the testing set using as metrics the Pearson's correlation (r) when comparing the estimated and the reference BP values, and the area under the receiver operating characteristic (AUROC) curves, and true positive and true negative rates (TPR, TNR) for the detection of high BP (reference SBP ≥ 140 or DBP ≥ 90 mmHg, applying a ± 8 mmHg exclusion zone to account for cuff measurement uncertainty).

Results: Baseline models showed low correlation with cuff data and poor high BP detection (r < 0.35; AUROC < 0.65, TPR < 0.65, TNR < 0.58). PPG-based models excelled in correlating with cuff BP (SBP: r = 0.53 for PPG, r = 0.63 for PPG + DEM; DBP: r = 0.58 for PPG, r = 0.67 for PPG + DEM) and high BP detection (SBP: AUROC = 0.84, TPR = TNR = 0.75; DBP: AUROC = 0.89, TPR = TNR = 0.81 for PPG; SBP: AUROC = 0.89, TPR = TNR = 0.80; DBP: AUROC = 0.93, TPR = TNR = 0.86 for PPG + DEM).

Discussion: This study demonstrated that PPG signals contain reliable markers of BP, and that BP values can be estimated using only markers found within PPG's optical pulsatility signals, outperforming models based solely on demographic data. These findings hold the potential to radically transform hypertension screening and global healthcare delivery, paving the way for innovative approaches in patient diagnosis, monitoring and treatment methodologies.

Keywords: continual blood pressure monitoring; cuffless blood pressure; hypertension; optical blood pressure monitor; photoplethysmography.

Figure 1

Framework of the study. A total of 668,080 systolic and diastolic BP (SBP, DBP) from an upper arm oscillometric cuff were collected simultaneously with wrist PPG from 32,152 European residents. Six XGBoost models with different input setups were created to predict BP, using cuff readings for training. Four baseline models incorporated inputs like heart rate (HR), age, and Demography (DEM) data (age, gender, BMI), either individually or combined, while two PPG models utilized PPG signals, with and without Demography data. Model training was performed on 85% of users (27,329 users with 568,708 cuff recordings), and testing was conducted on the remaining 15% of users (4,823 individuals with 99,372 cuff readings). The performance analyses were conducted using only readings from the first day of each user's monitoring period on the testing dataset (14,939 cuff readings).

Figure 2

Pearson's correlation between BP estimates from each model vs. cuff BP values. (A) Correlation for SBP. (B) Correlation for DBP. Error bars represent 95% confidence interval (CI) of the mean correlation calculated from bootstrapping the samples (10,000 replications).

Figure 3

Performance for high BP estimation for each model considering the criterion for high BP set at cuff SBP ≥ 140 mmHg (left-hand side), and cuff DBP ≥ 90 mmHg (right-hand side). (A) ROC curves for high SBP estimation. (B) ROC curves for high DBP estimation. C. Estimation performance metrics as true positive rate (TPR), true negative rate (TNR) and area under the curve (AUC) for high SBP. (C) Estimation performance metrics for high DBP. An exclusion zone of ±8 mmHg was adopted for the creation of the ROC curves to account for cuff measurement uncertainty. N.u., no unit.