System and method for real-time detection and classification of the health state of arteriovenous fistulas

Abstract

The present invention discloses a system and method for real-time detection and classification of the health state of arteriovenous fistulas. A vascular acoustic sensor captures bruit signals from the arteriovenous fistula, which are amplified and filtered by a signal conditioning module and then digitized by a microcontroller equipped with an analog-to-digital converter. The digitized data are processed by a trained machine learning model, such as a one-dimensional convolutional neural network (1D-CNN), to classify the arteriovenous fistula into an immature state, a mature state, or a stenotic state. Additionally, the classification results are displayed in real time or otherwise communicated, enabling timely clinical assessment without reliance on external computing resources. This invention provides a low-cost, portable, and frequent monitoring solution for arteriovenous fistulas, potentially improving patient care by enabling early detection of maturation issues or stenosis.

Images