Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2020 Oct 2;10(1):16387.
doi: 10.1038/s41598-020-72336-5.

The prototype device for non-invasive diagnosis of arteriovenous fistula condition using machine learning methods

Marcin Grochowina  1 , Lucyna Leniowska  2 , Agnieszka Gala-Błądzińska  2   3
Affiliations

The prototype device for non-invasive diagnosis of arteriovenous fistula condition using machine learning methods

Marcin Grochowina et al. Sci Rep. .

Abstract

Pattern recognition and automatic decision support methods provide significant advantages in the area of health protection. The aim of this work is to develop a low-cost tool for monitoring arteriovenous fistula (AVF) with the use of phono-angiography method. This article presents a developed and diagnostic device that implements classification algorithms to identify 38 patients with end stage renal disease, chronically hemodialysed using an AVF, at risk of vascular access stenosis. We report on the design, fabrication, and preliminary testing of a prototype device for non-invasive diagnosis which is very important for hemodialysed patients. The system includes three sub-modules: AVF signal acquisition, information processing and classification and a unit for presenting results. This is a non-invasive and inexpensive procedure for evaluating the sound pattern of bruit produced by AVF. With a special kind of head which has a greater sensitivity than conventional stethoscope, a sound signal from fistula was recorded. The proces of signal acquisition was performed by a dedicated software, written specifically for the purpose of our study. From the obtained phono-angiogram, 23 features were isolated for vectors used in a decision-making algorithm, including 6 features based on the waveform of time domain, and 17 features based on the frequency spectrum. Final definition of the feature vector composition was obtained by using several selection methods: the feature-class correlation, forward search, Principal Component Analysis and Joined-Pairs method. The supervised machine learning technique was then applied to develop the best classification model.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

Figure 1
Figure 1
Image from fistula USG examination in six stages of its function. The letters and numbers of Figures correspond to the AVF functional classes presented in Table 1.
Figure 2
Figure 2
Example of division of the recorded signal from arteriovenosu fistula into fragments corresponding to single heartbeats.
Figure 3
Figure 3
F-score as a function of the number of features (k-NN classifier); features added in the order indicated by ranking of the Correlation method.
Figure 4
Figure 4
System concept.
Figure 5
Figure 5
The structure of the hardware layer.
Figure 6
Figure 6
The structure of the software layer.
Figure 7
Figure 7
NefDiag application control panel.
Figure 8
Figure 8
NefDiag device.
Figure 9
Figure 9
Indications of the device in response to the fistula signal at various stages of pathologization.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

References

    1. Levey AS, Coresh J. Chronic kidney disease. The Lancet. 2012;379:165–180. doi: 10.1016/S0140-6736(11)60178-5. - DOI - PubMed
    1. Greenberg J, et al. Long-term outcomes of fistula first initiative in an urban university hospital-is it still relevant? Vasc. Endovasc. Surg. 2017;51:125–130. doi: 10.1177/1538574417692454. - DOI - PMC - PubMed
    1. Dhingra RK, Young EW, Hulbert-Shearon T, Leavey SF, Port FK. Type of vascular access and mortality in us hemodialysis patients. Kidney Int. 2001;60:1443–1451. doi: 10.1046/j.1523-1755.2001.00947.x. - DOI - PubMed
    1. Sekhar LN, Wasserman JF. Noninvasive detection of intracranial vascular lesions using an electronic stethoscope. J. Neurosurg. 1984;60:553–559. doi: 10.3171/jns.1984.60.3.0553. - DOI - PubMed
    1. Bosman PJ, et al. Access flow measurements in hemodialysis patients: in vivo validation of an ultrasound dilution technique. J. Am. Soc. Nephrol. 1996;7:966–969. - PubMed