Levenberg-Marquardt Neural Network Algorithm for Degree of Arteriovenous Fistula Stenosis Classification Using a Dual Optical Photoplethysmography Sensor.

This paper proposes a noninvasive dual optical photoplethysmography (PPG) sensor to classify the degree of arteriovenous fistula (AVF) stenosis in hemodialysis (HD) patients. Dual PPG measurement node (DPMN) becomes the primary tool in this work for detecting abnormal narrowing vessel simultaneously in multi-beds monitoring patients. The mean and variance of Rising Slope (RS) and Falling Slope (FS) values between before and after HD treatment was used as the major features to classify AVF stenosis. Multilayer perceptron neural networks (MLPN) training algorithms are implemented for this analysis, which are the Levenberg-Marquardt, Scaled Conjugate Gradient, and Resilient Back-propagation, to identify the degree of HD patient stenosis. Eleven patients were recruited with mean age of 77 ± 10.8 years for analysis. The experimental results indicated that the variance of RS in the HD hand between before and after treatment was significant difference statistically to stenosis (p < 0.05). Levenberg-Marquardt algorithm (LMA) was significantly outperforms the other training algorithm. The classification accuracy and precision reached 94.82% and 92.22% respectively, thus this technique has a potential contribution to the early identification of stenosis for a medical diagnostic support system.

A Novel Classification Technique of Arteriovenous Fistula Stenosis Evaluation Using Bilateral PPG Analysis.

The most common treatment for end-stage renal disease (ESRD) patients is the hemodialysis (HD). For this kind of treatment, the functional vascular access that called arteriovenous fistula (AVF) is done by surgery to connect the vein and artery. Stenosis is considered the major cause of dysfunction of AVF. In this study, a noninvasive approach based on asynchronous analysis of bilateral photoplethysmography (PPG) with error correcting output coding support vector machine one versus rest (ESVM-OVR) for the degree of stenosis (DOS) evaluation is proposed. An artificial neural network (ANN) classifier is also applied to compare the performance with the proposed system. The testing data has been collected from 22 patients at the right and left thumb of the hand. The experimental results indicated that the proposed system could provide positive predictive value (PPV) reaching 91.67% and had higher noise tolerance. The system has the potential for providing diagnostic assistance in a wearable device for evaluation of AVF stenosis.