A system for non-invasively measuring blood pressure on a treadmill

B3X: a novel efficient algorithm for accurate automated auscultatory blood pressure estimation

Objective.The auscultatory technique is still considered the most accurate method for non-invasive blood pressure (NIBP) measurement, although its reliability depends on operator's skills. Various methods for automated Korotkoff sounds analysis have been proposed for reliable estimation of systolic (SBP) and diastolic (DBP) blood pressures. To this aim, very complex methodologies have been presented, including some based on artificial intelligence (AI). This study proposes a relatively simple methodology, named B3X, to estimate SBP and DBP by processing Korotkoff sounds recordings acquired during an auscultatory NIBP measurement.Approach.The beat-by-beat change in morphology of adjacent Korotkoff sounds is evaluated via their cross-correlation. The time series of the beat-by-beat cross-correlation and its first derivative are analyzed to locate the timings of SBP and DBP values. Extensive tests were performed on a public database of 350 annotated measurements, and the performance was evaluated according to the BHS, AAMI/ANSI, and International Organization for Standardization (ISO) quality standards.Main results.The proposed approach achieved 'A' scores for SBP and DBP in the BHS grading system, and passed the quality tests of AAMI/ANSI and ISO standards. The B3X algorithm outperformed two well-established algorithms for oscillometric NIBP measurement in both SBP and DBP estimation. It also outperformed four AI-based algorithms in DBP estimation, while providing comparable performance for SBP, at the cost of a much lower computational burden. The full code of the B3X algorithm is provided in a public repository.Significance.The very good performances ensured by the proposed B3X algorithm, at a low computational cost and without the need for parameter training, support its direct implementation into clinical blood pressure (BP) monitoring devices. The results of this study pave the way for solving/overcoming the trade-off between the accuracy of the auscultatory technique and the objectivity of oscillatory measurements, by bringing an automated auscultatory BP measurement method in clinical practice.

Deep learning-based robust automatic non-invasive measurement of blood pressure using Korotkoff sounds

This paper proposes a method that automatically measures non-invasive blood pressure (BP) based on an auscultatory approach using Korotkoff sounds (K-sounds). There have been methods utilizing K-sounds that were more accurate in general than those using cuff pressure signals only under well-controlled environments, but most were vulnerable to the measurement conditions and to external noise because blood pressure is simply determined based on threshold values in the sound signal. The proposed method enables robust and precise BP measurements by evaluating the probability that each sound pulse is an audible K-sound based on a deep learning using a convolutional neural network (CNN). Instead of classifying sound pulses into two categories, audible K-sounds and others, the proposed CNN model outputs probability values. These values in a Korotkoff cycle are arranged in time order, and the blood pressure is determined. The proposed method was tested with a dataset acquired in practice that occasionally contains considerable noise, which can degrade the performance of the threshold-based methods. The results demonstrate that the proposed method outperforms a previously reported CNN-based classification method using K-sounds. With larger amounts of various types of data, the proposed method can potentially achieve more precise and robust results.

Model based analysis of the variation in Korotkoff sound onset time during exercise

In this study, a minimal mathematical model of the cardiovascular system is used to study the effects of changes in arterial compliance and cardiac contractility on the onset time of Korotkoff sounds during an auscultatory procedure. The model provides blood pressure waveforms in the ventricle, the aorta and the brachial artery. From these waveforms, pre-ejection time, pulse propagation time and rise time of the blood pressure at the brachial artery can be computed. The time delay between onset time of ECG Q wave and onset time of Korotkoff sound is the sum of these three times. Rise time is zero and the time delay is minimal when the cuff pressure is slightly above the diastolic pressure. This minimum time delay is represented by QKD. Simulation results suggest that during the Bruce exercise protocol QKD decreases to one-third of its pre-exercise value if the cardiac contractility increases threefold. The effect of arterial compliance is not as significant as that of the cardiac contractility. From data recorded during an exercise test, it is observed that QKD decreases considerably as the test load is increased. We show in this study that the amount of decrease in QKD can be used as an index of the amount of increase in cardiac contractility during an exercise ECG test. Use of signal averaging for reducing the effect of motion artifacts during an exercise test is also shown to be very instrumental for making accurate QKD measurements.

A new method for automated blood pressure measurement

We propose a new technique for automated indirect blood pressure measurement based on the auscultatory method. Systolic, diastolic and blood mean pressure are identified by looking at trend changes in the spectral energy dispersion of Korotkoff sounds. The detection is solely based on patient measurements, not on population studies. By comparing the automatic detection with common auditory detection, in 286 measurements taken in 15 subjects there was agreement (+/- 1 sound--400 Pa error) in 278 cases for the systole and 276 cases for the diastole.