A Web-Based System for Blood Pressure Prediction during Hemodialysis (Preprint)

BACKGROUND Cardiovascular (CV) events are the major cause of morbidity and mortality associated with blood pressure (BP) in hemodialysis (HD) patients. BP varies significantly during HD treatment, and the dramatic variation in BP is a well-recognized risk factor for increased mortality. It is important to develop an intellectual system capable of predicting BP profiles for real-time monitory. OBJECTIVE Our aim was to build a web-based system to predict the systolic blood pressure (SBP) change during hemodialysis process. METHODS This study was based on a large stream of HD parameters collected from a dialysis equipment connected to the Vital Info Portal gateway and linked with the demographic data stored in the hospital information system. The data set was divided into three groups - training, test and new patients. The training group was useful to build a multiple linear regression model, in which the SBP change was the dependent variable and the dialysis parameters and demographic data were the independent variables. We used the test and new patient groups to evaluate the model performance using coverage rates in different thresholds. A web-based interactive system based on the model was built for visualizing the prediction performance. RESULTS A total of 542,424 BP records were used in the model building. The accuracy was greater than 80% in the prediction error range of 15%, and 20mmHg of true SBP in the test and new patient groups for the SBP change model suggested a good performance of our prediction model. In the case of absolute SBP values (5, 10, 15, 20 and 25 mmHg), the accuracy of SBP prediction increased as the threshold value augmented. CONCLUSIONS This database supported the application of our prediction model in reducing the frequency of intradialytic SBP variability, and therefore, it could aid in the clinical decision when a new patient undertakes HD treatment. Whether the introduction of SBP prediction intelligent system can lower CV events in HD patients, it needs further investigations.