Abstract
Background: Hypotension after starting continuous renal replacement therapy (CRRT) is associated with worse outcome, but it is difficult to predict because several factors have interactive and complex effects on the risk. The present study applied machine learning algorithms to develop models to predict hypotension after initiating CRRT.Methods: Among 2,349 adult patients who started CRRT due to acute kidney injury, 70% and 30% were randomly assigned into the training and testing sets, respectively. Hypotension was defined as a reduction in mean arterial pressure (MAP) ≥20 mmHg from the initial value within 6 hours. The area under the receiver operating characteristic curves (AUROCs) in machine learning models, such as support vector machine (SVM), deep neural network (DNN), and light gradient boosting machine (LGBM), were compared with those in disease-severity scores such as the Sequential Organ Failure Assessment and Acute Physiology and Chronic Health Evaluation II.Results: The DNN model showed the highest AUROC (0.822 [0.789–0.856]), and the LGBM and SVM models followed with AUROCs of 0.810 (0.776–0.845) and 0.807 (0.772–0.842), respectively; all machine learning AUROC values were higher than those obtained from disease-severity scores (AUROCs <0.6). Although different definitions of hypotension were used such as a reduction of MAP ≥30 mmHg or a reduction occurring within 1 hour, the AUROCs of machine learning models were higher than those of disease-severity scores. These machine learning models were well calibrated.Conclusion: Machine learning models successfully predict hypotension after starting CRRT and can serve as the basis of systems to predict hypotension before starting CRRT.
Using machine learning models to predict the initiation of renal replacement therapy among chronic kidney disease patients
