Arteriovenous Shunt Stenosis Evaluation Using a Fractional-Order Fuzzy Petri Net Based Screening System for Long-Term Hemodialysis Patients

Abstract

This paper proposes the evaluation of arteriovenous shunt (AVS) stenosis using a fractional-order Fuzzy Petri net based screening system for long-term hemodialysis treatment of patients. The screening system uses the Burg method, the fractional-order chaos system, and the Fuzzy Petri net (FPN) for early detection of AVS dysfunction. The Burg method is an autoregressive (AR) model that is used to estimate the frequency spectra of a phonoangiographic signal and to identify the spectral peaks in the region from 25 Hz to 800 Hz. In AVS, the frequency spectrum varies between normal blood flow and turbulent flow. The power spectra demonstrate changes in frequency and amplitude as the degree of stenosis changes. A screening system combining fractional-order chaos system and FPN is used to track the differences in the frequency spectra between the normal and stenosis access. The dynamic errors are indexes that can be used to evaluate the degree of AVS stenosis using a FPN. For 42 long-term follow-up patients, testing results show that the proposed screening system is more efficient in the evaluation of AVS stenosis.

Non-Imaging Acoustical Properties in Monitoring Arteriovenous Hemodialysis Access. A Review

“…[11], Kumbar, et al [30], Nishitani & Inada [31], and Allon & Robbin [34] also confirmed that blood flow is highly correlated with stenosis and thrombosis issues [12,13,20,28] that alter the frequency spectral characteristics.…”

“…Most of the studies demonstrated that significant changes in vascular diameter affect the blood flow-rate [28,29] and change the sound characteristics, which can be identified as higher pitch (frequency) and higher intensity (amplitude) [12,19], and also increase venous pressure [28,30]. A few experimental studies presented different sensor positions or locations for auscultation of the fistula area (arterial and venous side), and showed a limited effect on the sound characteristics.…”

“…Many agree that the frequency power spectra of stenosis and normal sound are within 0-1000 Hz; it also varies depending on the access stenosis location and its severity. Some studies state that higher frequencies, in the range of 300 Hz and above, correlate with a higher degree of stenosis [11][12][13].Several analytical techniques have been applied to analyze these acoustic signal features to correlate them with the stages of the stenosis problem. These include root mean square (RMS), true RMS (TRMS), amplitude (A) [11], shorttime Fourier transform (STFT) and wavelet transform (WT) [13][14][15], artificial neural network (ANN) [16], Burg's method [17,18], fuzzy Petri net (FPN), probabilistic neural network (PNN) [12,19], and classifiers such as principal component analysis (PCA) [3], support vector machine (SVM) [3,20], and many others, as summarized in Table 1.…”

“…However, some underlined the direct impact on the results of sensor location, skin condition, as well as movement artifacts [13,19,21,31]. The use of digital signal processing techniques in the screening of fistula conditions has led to the development of a decision-making algorithm that allows identifying or classifying the stenosis or thrombosis in early conditions [12,32,33] and may also be used for continuous monitoring compared to imaging techniques [3,11,30]. The classification of AVA sounds is divided into two conditions: non-stenotic or stenotic, although some researchers propose sub-classes of the severity of stenotic cases [18].…”

“…Chen, et al demonstrated that the changes in sound intensity and frequency may be correlated with the degree of stenotic severity [12]. They developed an algorithm based on Burg's method, the fractional-order chaos system, and fuzzy Petri net (FPN) for detection of early fistula dysfunction, with three degrees of stenosis: normal, moderate and severe.…”