Quality Evaluation via PPG on the AVFs of Hemodialysis Patients Based on Both Blood Flow Volume and Degree of Stenosis

The classifier of support vector machine (SVM) learning for assessing quality of arteriovenous fistula (AVF) at hemodialysis (HD) patients using a new photoplethysmography (PPG) sensor are presented in this work. Based on current medical standard, there are two important indices for assessing AVF quality, the blood flow volume (BFV) and the degree of stenosis (DOS). In current clinical practice, BFV and DOS of AVFs are assessed by using an ultrasound Doppler machine, which is bulky, expensive, hard-to-use and time-consuming. Therefore, a new PPG sensor module is designed to provide patients and doctors an inexpensive and small-sized solution to assess AVF quality. The readout of the sensor is successfully optimized to increase the signal to noise ratio (SNR) and reduce the environment interference, the readout circuitries are designed to fit the full dynamic range of analog-digital converter (ADC) and to filter out the noise. To assess quality of AVF, three different machine learning classifiers are developed, where the input features are selected based on optical Beer Lambert's law and hemodynamic model. Finally, the clinical experiment results show that the proposed PPG sensor successfully achieves an accuracy of 87.838% in assessing AVF quality based on satisfactory DOS and BFV measured.