The classifier of support vector machine (SVM) learning for assessing the quality of arteriovenous fistulae (AVFs) in hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor device is presented in this work. In clinical practice, there are two important indices for assessing the quality of AVF: the blood flow volume (BFV) and the degree of stenosis (DOS). In hospitals, the BFV and DOS of AVFs are nowadays assessed using an ultrasound Doppler machine, which is bulky, expensive, hard to use, and time consuming. In this study, a newly-developed PPG sensor device was utilized to provide patients and doctors with an inexpensive and small-sized solution for ubiquitous AVF assessment. The readout in this sensor was custom-designed to increase the signal-to-noise ratio (SNR) and reduce the environment interference via maximizing successfully the full dynamic range of measured PPG entering an analog–digital converter (ADC) and effective filtering techniques. With quality PPG measurements obtained, machine learning classifiers including SVM were adopted to assess AVF quality, where the input features are determined based on optical Beer–Lambert’s law and hemodynamic model, to ensure all the necessary features are considered. Finally, the clinical experiment results showed that the proposed PPG sensor device successfully achieved an accuracy of 87.84% based on SVM analysis in assessing DOS at AVF, while an accuracy of 88.61% was achieved for assessing BFV at AVF.
A portable, wireless photoplethysomography (PPG) sensor for assessing arteriovenous fistula (AVF) by using class-weighted support vector machines (SVM) was presented in this study. Nowadays, in hospital, AVF are assessed by ultrasound Doppler machines, which are bulky, expensive, complicated-to-operate, and time-consuming. In this study, new PPG sensors were proposed and developed successfully to provide portable and inexpensive solutions for AVF assessments. To develop the sensor, at first, by combining the dimensionless number analysis and the optical Beer Lambert’s law, five input features were derived for the SVM classifier. In the next step, to increase the signal-noise ratio (SNR) of PPG signals, the front-end readout circuitries were designed to fully use the dynamic range of analog-digital converter (ADC) by controlling the circuitries gain and the light intensity of light emitted diode (LED). Digital signal processing algorithms were proposed next to check and fix signal anomalies. Finally, the class-weighted SVM classifiers employed five different kernel functions to assess AVF quality. The assessment results were provided to doctors for diagonosis and detemining ensuing proper treatments. The experimental results showed that the proposed PPG sensors successfully achieved an accuracy of 89.11% in assessing health of AVF and with a type II error of only 9.59%.
The effects of mis-positioning a newly-designed noninvasive, cuffless blood pressure sensor are thoroughly investigated via simulation and analysis on a 3D fluid-solid-electric finite element model. A subsequent optimal design of this blood pressure is conducted based on the aforementioned mis-positioning effects. A highly-accurate, non-invasive, cuffless blood pressure (BP) sensor was successfully developed recently for an effective personal monitoring device on blood pressures. This new small-sized, portable blood pressure sensor is able to offer continuous BP measurements. The availability of continuous blood pressures are important for monitoring and evaluating personal cardiovascular systems. The sensor contains a strain-sensitive electrode encapsulated by flexible polymer. As the sensor placed on the position right on the top of the center of the wrist pulsation area, the deflection of the sensor induces the resistance changes of the electrode. By measuring the changes in electrode resistance, the level of pulsation is successfully quantified. Subsequent calculation based in this measurement can lead to fair estimates on blood pressures. However, as the sensor is placed on the wrist area where pulsation occurs, the mis-positioning of the sensor to the desired location, the center of the pulsation area, is inevitable. This study is dedicated to investigate the effects of the mis-positioning via a 3D finite element model. A new 3D fluid-solid-electro coupling interaction finite element model of the wrist is built for predicting the vibration of radial artery and then diastolic and systolic blood pressures. The FEM includes sensor of gel capsule and strain-sensing electrodes, radial artery, blood, radius bones, tendon, muscles and the front-end readout circuit. The FEM is the multi physics FEM with fluid, solid and electric. The section of wrist is constructed from magnetic resonance imaging (MRI) and the length of the FEM is 40mm. The complete 3D FEM model successfully simulated the vibration of skin surface and the sensor module. The diastolic and systolic blood pressures can be accurately predicted by the simulated output resistance. The pulsation levels due to varied mis-positionings are simulated by the built model, and simulation results are successfully validated by experiments. It is found that due to the unsymmetrical geometry of the wrist, the pulsation levels are also varied in an un-symmetric fashion with the mis-positionings in different directions. The maximum output of the BP sensor occurs when the sensor is placed ±3 mm away from the center of the pulsation area, while the sensor output remain valid for subsequent signal processing as the sensor is placed within ±5 mm from the pulsation center. Considering the inevitable mis-positionings by all possible users in different genders and ages, the sizes of the sensors are successfully optimized for satisfactory average signal quality over all possible users.
A new non-invasive, cuff-less, low-cost blood pressure (BP) sensor capable of continuous detection is optimized by this study for maximum performance. This blood pressure sensor module encapsulates specially-designed electrodes as a strain sensor to be attached to a flexible plate. In operations, the strain sensor is held stable with top surface contacting tightly with the human skin while the bottom surface under a low pressure exerted by a pressurizing wrist belt. The electrodes and plate are expected to vibrate in a synchronized fashion with artery pulsations as vibrations transmitted to the sensor through the module to vary the net (average) strain of electrodes, thus also varying its resistance. Employing a readout circuit of Wheatstone bridge, an amplifier, a filter, and a digital signal processor, the artery pulsations could be successfully converted to temporal voltage variations for calculating blood pressures via known algorithms. However, due to the small diameter of the artery, around 3 mm, mis-positioning (MP) of the sensor electrode area relative to the artery beneath is inevitable, which may lower sensor sensitivity due to smaller average strains. To remedy the problem, efforts are paid to conduct finite element modeling (FEM) and simulations on the electrodes, sensor module and the wrist including bone, tissue and other bio-structures to predict sensor output variations with respect to varied mis-positionings. Based on the predictions, the sensor optimal length is successfully found as 5 mm, which maximizes average strain, the sensitivity of the sensor.978-1-4799-0162-3/14/$31.00 ©2014 IEEE
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.