Clinical evaluation of an expert system for arteriovenous fistula assessment

The monitoring of ionic dialysance in hemodialysis allows early detection of arterio-venous fistula stenosis. One limitation to the practical use of ionic dialysance is that the analysis is very time consuming on a majority of normal cases. The purpose of the study is to evaluate the utility of an expert system reproducing a human analysis and allowing continuous monitoring of the ionic dialysance by helping the physician to focus his or her expertise on the abnormal cases. The method is based on a Bayesian model that analyzes the blood flow rate, the ionic dialysance, and the venous and arterial pressures measured on the extra corporeal circuit. The clinical evaluation was performed on 90 dialysis patients at the hospital dialysis center of Saint Brieux in France with a history of at least four consecutive months of validated recording. The retrospective automated analysis was evaluated in comparison to vascular access problems identified from invasive investigation or treatment. The sensitivity of the automated analysis is 92% with a specificity of 75%. As a conclusion we suggest that this expert system could be used in a continuous vascular access monitoring procedure consisting in a weekly review of the patient population at the dialysis center. The patients with the highest risk score need a further investigation of their historical data and their medical history in order to decide whether or not to perform an invasive intervention.