Previously submitted to: JMIR Medical Informatics (no longer under consideration since Jan 16, 2021)
Date Submitted: Mar 21, 2019
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
A Systolic Blood Pressure Prediction System during Hemodialysis
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. The development of an intelligent system capable of predicting BP profiles for real-time monitoring is important.
Objective:
Our aim was to build a web-based system to predict changes in systolic blood pressure (SBP) during hemodialysis.
Methods:
This study was based on a large set of HD parameters collected from a dialysis equipment connected to the Vital Info Portal gateway and linked to the demographic data stored in the hospital information system. The dataset was divided into three groups: training, test and new patients. The training group was used to build a multiple linear regression model, in which the change in SBP 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 performance of the model using coverage rates with different thresholds. A web-based interactive system based on the model was built to visualize the prediction performance.
Results:
A total of 542,424 BP records were used for 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 model of SBP changes suggested the good performance of our prediction model. In the analysis of absolute SBP values (5, 10, 15, 20 and 25 mmHg), the accuracy of the SBP prediction increased as the threshold value increased.
Conclusions:
This database supported the application of our prediction model in reducing the frequency of intradialytic SBP variability, and therefore, it might aid in the clinical decision-making process when a new patient undergoes HD treatment. Further investigations are needed to determine whether the introduction of the intelligent SBP prediction system decreases the incidence of CV events in HD patients.
Clinicaltrial:
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.