Classification of Shunt Murmurs for Diagnosis of Arteriovenous Fistula Stenosis

Hemodialysis patients are generally provided with an arteriovenous fistula (AVF), but problems such as stenosis of the blood vessel can occur. Listening to shunt murmurs is an effective way for hemodialysis patients to check their own shunt function. However, manually judging shunt function is difficult and requires correct knowledge and experience. Therefore, a system that can be easily handled by patients and automatically identifies shunt function is required. In this study, we proposed a method for classifying shunt stenosis using the Support Vector Machine (SVM). To record shunt murmurs, we used the electronic stethoscope and the microphone with stethoscope chest piece. We used the resistance index (RI) obtained from the ultrasonic diagnostic equipment as a class label and the normalized cross correlation coefficient, ratio of the frequency power and Mel-frequency cepstral coefficients (MFCC) as the feature. We examined the effectiveness of the proposed method by comparing the accuracy and F-measure. It was found that the classification accuracy of the RI using the SVM was lower than that obtained by human judgment.