Key result
A Random Forest algorithm using phonocardiogram and ballistocardiogram features estimated systolic blood pressure with a mean error of 3.3 mmHg and a standard deviation of ± 5 mmHg.
Why the study?
Most current cuffless blood pressure monitoring relies on pulse transit or arrival time using ECG or peripheral pulse signals, prompting the exploration of noninvasively detected PCG and BCG signals to estimate systolic blood pressure.
Does a Random Forest algorithm using phonocardiogram and ballistocardiogram signals accurately estimate systolic blood pressure in healthy volunteers?
Cross-Sectional (n=21)
No
Does a Random Forest algorithm using phonocardiogram and ballistocardiogram signals accurately estimate systolic blood pressure in healthy volunteers?
Effect estimate: mean error 3.3 mmHg (± 5 mmHg SD)
A cuffless blood pressure estimation method using PCG and BCG signals combined with a Random Forest algorithm can estimate systolic blood pressure with a mean error of 3.3 mmHg.
PCG-BCG features supported feasible cuffless SBP estimation in volunteers; leaves open wearable validation in larger, diverse cohorts before clinical consideration.
Cuffless blood pressure measurement enables unobtrusive and continuous monitoring that can be integrated with wearable devices to extend healthcare to non-hospital settings. Most of the current research has focused on the estimation of blood pressure based on pulse transit time or pulse arrival time using ECG or peripheral cardiac pulse signals as proximal time references. This study proposed the use of a phonocardiogram (PCG) and ballistocardiogram (BCG), two signals detected noninvasively, to estimate systolic blood pressure (SBP). For this, the PCG and the BCG were simultaneously measured in 21 volunteers in the rest, activity, and post-activity conditions. Different features were considered based on the relationships between these signals. The intervals between S1 and S2 of the PCG and the I, J, and K waves of the BCG were statistically analyzed. The IJ and JK slopes were also estimated as additional features to train the machine-learning algorithm. The intervals S1-J, S1-K, S1-I, J-S2, and I-S2 were negatively correlated with changes in SBP (p-val < 0.01). The features were used as explanatory variables for a regressor based on the Random Forest. It was possible to estimate the systolic blood pressure with a mean error of 3.3 mmHg with a standard deviation of ± 5 mmHg. Therefore, we foresee that this proposal has potential applications for wearable devices that use low-cost embedded systems.
No takes yet. Share an insight, caveat, or question.
González-Landaeta et al. (2022) conducted a cross-sectional in Healthy (n=21). Random Forest estimation using PCG and BCG vs. Cuff-based automatic blood pressure monitor was evaluated on Systolic blood pressure estimation error (mean error 3.3 mmHg (± 5 mmHg SD)). A Random Forest algorithm using phonocardiogram and ballistocardiogram features estimated systolic blood pressure with a mean error of 3.3 mmHg and a standard deviation of ± 5 mmHg.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: