Application of Artificial Neural Networks for the Diagnosis of the Condition of the Arterio-venous Fistula on the Basis of Acoustic Signals

Flexible, Skin Coupled Microphone Array for Point of Care Vascular Access Monitoring

“…Frequency ranges affected by stenosis Chen 2013 [35] Specific bands of 130-260, 250-500, and 550-800 Hz Akay 1993 [36] 300 -800 Hz Obando, et al 2012 [37] 200 -600 Hz Vasquez, et al 2009 [38] 300-500, 200-800, 250-1000 Hz Mansy, et al 2005 [33] 300 -600 Hz Wang 2011 [39] 700-800 Hz after signal processing Sato, et al 2006 [40] 20 -800 Hz Wang, et al 2014 [34] 200 -600 Hz Chen, et al 2014 [41] 40 -800 Hz Gram, et al 2010 [42] 625 -750 Hz and 875 -1000 Hz Sung, et al 2014 [2] 50 -800 Hz Todo, et al 2012 [43] 51 -270 Hz Chen 2013 [44] 25 -800 Hz Mungia, et al 2009 [45] 200 -1000 Hz Grochowina, et al 2014 [46] 150 and 350 -400 Hz Rousselot 2014 [47] 70-800 Hz; specific bands at 180-300, 310-390, 440-700 Hz Moreover, although most studies agreed that DOS caused enhanced high-frequency spectral power [2], [34]- [37], [39], [40], [42]- [44], [46], [47], one prominent study described an opposite effect [33]. This was perhaps due to the effect of DOS to reduce blood flow because blood pressure is regulated; reduced flow would produce lower overall bruit amplitudes due to reduced turbulence for low blood flow [48], [49].…”

The new method of the selection of features for the k-NN classifier in the arteriovenous fistula state estimation

“…The studies to date [1] [2] show that the character of the sound emitted by the blood flowing within the fistula differs depending on the condition of the fistula.…”

Comparison of SVM and k-NN classifiers in the estimation of the state of the arteriovenous fistula problem

“…250 PROCEEDINGS OF THE FEDCSIS. ŁÓDŹ, 2015 This property has been marked as f 1 and calculated from the equation (1).…”