An Iterative Run-to-Run Learning Model to Derive Continuous Brachial Pressure Estimates from Arterial and Venous Lines During Dialysis Treatment

Objective: Non-invasive continuous blood pressure monitoring is not yet part of routine practice in renal dialysis units but could be a valuable tool in the detection and prevention of significant variations in patient blood pressure during treatment. Feasibility studies have delivered an initial validation of a method which utilises pressure sensors in the extra-corporeal dialysis circuit, without any direct contact with the person receiving treatment. Our main objective is to further develop this novel methodology from its current early development status to a continuous-time brachial artery pressure estimator.Method: During an in vivo patient feasibility study with concurrent measurement validation by Finapres Nova experimental physiological measurement device, real-time continuous dialysis line pressures, and intermittent occluding arm cuff pressure data were collected over the entire period of (typically 4-hour) dialysis treatments. There was found to be an underlying quasi-linear relationship between arterial line and brachial pressure measurements which supported the development of a mathematical function to describe the relationship between arterial dialysis line pressure and brachial artery BP. However, unmodelled non-linearities, dynamics and time-varying parameters present challenges to the development of an accurate BP estimation system. In this paper, we start to address the problem of physiological parameter time variance by novel application of an iterative learning run-to-run modeling methodology originally developed for process control engineering applications to a parameterised BP model.Results: The iterative run-to-run learning methodology was applied to the real-time data measured during an observational study in 9 patients, supporting subsequent development of an adaptive real-time BP estimator. Tracking of patient BP is analysed for all the subjects in our patient study, supported only by intermittent updates from BP cuff measurements. Conclusion: The methodology and associated technology is shown to be capable of tracking patient BP non-invasively via arterial line pressure measurement during complete 4-hour treatment sessions. A robust and tractable method is demonstrated, and future refinements to the approach are defined.

Download Full-text

A Feasibility Study of Non-Invasive Continuous Estimation of Brachial Pressure Derived from Arterial and Venous Lines During Dialysis

10.31224/osf.io/xpv65 ◽

2020 ◽

Cited By ~ 1

Author(s):

Jill Stewart ◽

Paul Stewart ◽

Thomas Walker ◽

Tarek Eldehini ◽

Daniela Viramontes Horner ◽

...

Keyword(s):

Blood Pressure ◽

Feasibility Study ◽

Pressure Sensors ◽

Haemodynamic Instability ◽

Routine Practice ◽

Mathematical Function ◽

Physiological Measurement ◽

Patient Movement ◽

Non Invasive ◽

Measurement Validation

Intradialytic haemodynamic instability is a significant clinical problem, leading to end-organ ischaemiaand contributing to morbidity and mortality in haemodialysis patients. Non-invasive continuous bloodpressure monitoring is not part of routine practice but may aid detection and prevention of significantfalls in blood pressure during dialysis. Brachial blood pressure is currently recorded intermittently duringhaemodialysis via a sphygmomanometer. Current methods of continuous non-invasive blood pressuremonitoring tend to restrict movement, can be sensitive to external disturbances and patient movement,and can be uncomfortable for the wearer. Additionally, poor patient blood circulation can lead to unreliable measurements. In this feasibility study we performed an initial validation of a novel methodand associated technology to continuously estimate blood pressure using pressure sensors in the extracorporeal dialysis circuit, which does not require any direct contact with the person receiving dialysistreatment.The paper describes the development of the measurement system and subsequent in vivo patient feasibility study with concurrent measurement validation by Finapres Nova experimental physiological measurement device. We identify a mathematical function to describe the relationship between arterial linepressure and brachial artery BP, which is confirmed in a patient study. The methodology presented requires no interfacing to proprietery dialysis machine systems, no sensors to be attached to the patient directly, and is robust to patient movement during treatment and also to the effects of the cyclical pressurewaveforms induced by the hemodialysis peristaltic blood pump. This represents a key enabling factor tothe development of a practical continuous blood pressure monitoring device for dialysis patients. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.

Download Full-text

Analog, compact and economical solution for the compensation of implantable piezoresistive blood pressure sensors for wireless medical monitoring

2020 28th Telecommunications Forum (TELFOR) ◽

10.1109/telfor51502.2020.9306571 ◽

2020 ◽

Author(s):

Serigne Mbacke ◽

Mohammed El Gibari ◽

Chantal Gauthier ◽

Benjamin Lauzier ◽

Hongwu Li

Keyword(s):

Blood Pressure ◽

Pressure Sensors ◽

Medical Monitoring

Download Full-text

Non-invasive cuff-less blood pressure estimation using a hybrid deep learning model

Optical and Quantum Electronics ◽

10.1007/s11082-020-02667-0 ◽

2021 ◽

Vol 53 (2) ◽

Author(s):

Sen Yang ◽

Yaping Zhang ◽

Siu-Yeung Cho ◽

Ricardo Correia ◽

Stephen P. Morgan

Keyword(s):

Machine Learning ◽

Blood Pressure ◽

Deep Learning ◽

Absolute Error ◽

Learning Model ◽

Physiological Measurement ◽

British Hypertension Society ◽

Non Invasive ◽

Blood Pressure Estimation ◽

Deep Learning Model

AbstractConventional blood pressure (BP) measurement methods have different drawbacks such as being invasive, cuff-based or requiring manual operations. There is significant interest in the development of non-invasive, cuff-less and continual BP measurement based on physiological measurement. However, in these methods, extracting features from signals is challenging in the presence of noise or signal distortion. When using machine learning, errors in feature extraction result in errors in BP estimation, therefore, this study explores the use of raw signals as a direct input to a deep learning model. To enable comparison with the traditional machine learning models which use features from the photoplethysmogram and electrocardiogram, a hybrid deep learning model that utilises both raw signals and physical characteristics (age, height, weight and gender) is developed. This hybrid model performs best in terms of both diastolic BP (DBP) and systolic BP (SBP) with the mean absolute error being 3.23 ± 4.75 mmHg and 4.43 ± 6.09 mmHg respectively. DBP and SBP meet the Grade A and Grade B performance requirements of the British Hypertension Society respectively.

Download Full-text

Wearable Sensor-Based Real-Time Gait Detection: A Systematic Review

Sensors ◽

10.3390/s21082727 ◽

2021 ◽

Vol 21 (8) ◽

pp. 2727

Author(s):

Hari Prasanth ◽

Miroslav Caban ◽

Urs Keller ◽

Grégoire Courtine ◽

Auke Ijspeert ◽

...

Keyword(s):

Systematic Review ◽

Gait Analysis ◽

Real Time ◽

Wearable Sensors ◽

Pressure Sensors ◽

Clinical Applications ◽

Performance Comparison ◽

Heel Strike ◽

Rule Based ◽

Pathological Gait

Gait analysis has traditionally been carried out in a laboratory environment using expensive equipment, but, recently, reliable, affordable, and wearable sensors have enabled integration into clinical applications as well as use during activities of daily living. Real-time gait analysis is key to the development of gait rehabilitation techniques and assistive devices such as neuroprostheses. This article presents a systematic review of wearable sensors and techniques used in real-time gait analysis, and their application to pathological gait. From four major scientific databases, we identified 1262 articles of which 113 were analyzed in full-text. We found that heel strike and toe off are the most sought-after gait events. Inertial measurement units (IMU) are the most widely used wearable sensors and the shank and foot are the preferred placements. Insole pressure sensors are the most common sensors for ground-truth validation for IMU-based gait detection. Rule-based techniques relying on threshold or peak detection are the most widely used gait detection method. The heterogeneity of evaluation criteria prevented quantitative performance comparison of all methods. Although most studies predicted that the proposed methods would work on pathological gait, less than one third were validated on such data. Clinical applications of gait detection algorithms were considered, and we recommend a combination of IMU and rule-based methods as an optimal solution.

Download Full-text

Abstract 062: Aortic Stiffness, Blood Pressure Progression and Incident Hypertension: The Framingham Heart Study

Circulation ◽

10.1161/circ.125.suppl_10.a062 ◽

2012 ◽

Vol 125 (suppl_10) ◽

Author(s):

Bernhard M Kaess ◽

Jian Rong ◽

Martin G Larson ◽

Naomi M Hamburg ◽

Joseph A Vita ◽

...

Keyword(s):

Blood Pressure ◽

Brachial Artery ◽

Aortic Stiffness ◽

Wave Amplitude ◽

Augmentation Index ◽

Vascular Stiffness ◽

Flow Mediated Dilation ◽

Forward Wave ◽

Incident Hypertension

Background: Increased vascular stiffness and excessive blood pressure (BP) pulsatility are important risk factors for age-related morbidity. Vascular stiffness and BP pulsatility are related, with a prevailing view that hypertension antedates and contributes to premature vascular aging and a secondary increase in vascular stiffness. However, temporal relations between comprehensive vascular measures and BP elevation have not been fully delineated in a large community-based sample. Methods: We examined longitudinal relations of BP and 3 measures of vascular stiffness and pressure pulsatility derived from arterial tonometry (carotid-femoral pulse wave velocity [CFPWV], forward wave amplitude and augmentation index) over a 7-year period in 1,898 Framingham Offspring participants (mean age 60 yrs, 1,057 women). We also examined relations between measures of microvascular and endothelial function derived from brachial artery Doppler and future progression of BP or vascular stiffness. Results: In multivariable-adjusted regression models, baseline tonometry measures were separately and jointly associated with higher systolic and pulse pressure and incident hypertension ( Table ). Conversely, higher baseline BP was associated with higher forward wave amplitude and augmentation index (all p<0.05) but not CFPWV at follow-up. Higher baseline resting brachial artery flow and lower flow-mediated dilation were associated with incident hypertension in models that included BP and tonometry measures ( Table ). Conclusion: Higher aortic stiffness (CFPWV), pressure pulsatility (forward wave amplitude), and wave reflection (augmentation index) and lower flow-mediated dilation are associated with blood pressure progression and incident hypertension. Our findings support the notion of aortic stiffness as a precursor of hypertension and further suggest a vicious cycle of increasing pressure pulsatility with advancing age. Table. Correlates of incident hypertension. Predictor Variables (baseline) OR 95% CI P Systolic BP 3.24 (2.17; 4.84) <0.0001 Diastolic BP 1.47 (1.13; 1.92) 0.0042 CFPWV 1.30 (1.02; 1.67) 0.037 Forward wave amplitude 1.66 (1.32; 2.09) <0.0001 Augmentation index 1.78 (1.45; 2.17) <0.0001 Brachial artery baseline flow 1.23 (1.05; 1.45) 0.013 Flow-mediated dilation 0.83 (0.70; 0.98) 0.029 Results of a single multivariable model that further adjusted for age,sex, BMI, height and triglycerides in 1,019 participants free of hypertension at baseline who experienced 337 cases of incident hypertension during follow-up. OR expressed per 1 SD of the independent variable.

Download Full-text

Abstract P466: Circadian Rhythm Disruptions in a Novel Diabetic db/db-mPer2 Luc Mouse Model

Hypertension ◽

10.1161/hyp.70.suppl_1.p466 ◽

2017 ◽

Vol 70 (suppl_1) ◽

Author(s):

Tianfei Hou ◽

Wen Su ◽

Ming C Gong ◽

Zhenheng Guo

Keyword(s):

Blood Pressure ◽

Circadian Rhythms ◽

Real Time ◽

Clock Gene ◽

Ex Vivo ◽

Phase Advance ◽

Luciferase Reporter ◽

High Time Resolution ◽

Peripheral Tissues

Db/db mouse, which lacks functional leptin receptor, is an extensively used model of obesity and type 2 diabetes. We and others have demonstrated that db/db mouse has disruptions in circadian rhythms of behavior, physiology and some clock genes. However, systemic investigations of the alterations in clock gene oscillations in multiple systems with high time resolution in this model are impeded by the impractical demand for large number of animals. To overcome this limitation, we cross bred the db/db mouse with mPer2 Luc mouse in which the clock gene Period2 is fused with a luciferase reporter thus allow real-time monitoring of the clock gene Per2 oscillations. The generated db/db-mPer2 Luc mice had the typical diabetic mellitus including obesity, hyperglycemia, hyperinsulinemia, glucose intolerance and insulin resistance. In addition, the db/db-mPer2 Luc mice also exhibited disruptions in circadian rhythms in behavior (locomotor activity), physiology (blood pressure) and metabolism (respiratory exchange ratio and energy expenditure). Using the LumiCycle system, we monitored in real-time of the Per2 oscillations in both the SCN central clock and multiple peripheral tissues ex vivo . The results showed no difference in the phase of the central SCN Per2 oscillation. However, the peripheral tissues that related to metabolism, such as liver and white adipose clocks, displayed 3.28±0.86 and 4.64±1.06 hours of phase advance respectively. Aorta, mesentery artery and kidney, organs play important role in blood pressure homeostasis, showed 0.99±0.37, and 2.12±0.4, and 2.21±0.5 hours phase advance respectively. Interestingly, no difference was observed in the lung and adrenal gland. We then investigated the Per2 oscillation in vivo by using the IVIS imaging system. Consistent with the ex vivo results, the liver Per2 oscillation were phase advanced in vivo. Our findings demonstrated that clock gene Per2 oscillations were disrupted in multiple peripheral tissues but not in central SCN. Moreover, the extent of phase advance in peripheral tissue varies largely. Our results suggest dyssynchrony of the clock oscillations among various peripheral systems likely contribute to the multiple disruptions in physiology and metabolism in diabetic db/db mice.

Download Full-text