Answering Clinical Questions Using Machine Learning: Should We Look at Diastolic Blood Pressure When Tailoring Blood Pressure Control?

Abstract

Background: The guidelines recommend intensive blood pressure control. Randomized trials have focused on the relevance of the systolic blood pressure (SBP) lowering, leaving the safety of the diastolic blood pressure (DBP) reduction unresolved. There are data available which show that low DBP should not stop clinicians from achieving SBP targets; however, registries and analyses of randomized trials present conflicting results. The purpose of the study was to apply machine learning (ML) algorithms to determine, whether DBP is an important risk factor to predict stroke, heart failure (HF), myocardial infarction (MI), and primary outcome in the SPRINT trial database. Methods: ML experiments were performed using decision tree, random forest, k-nearest neighbor, naive Bayesian, multi-layer perceptron, and logistic regression algorithms, including and excluding DBP as the risk factor in an unselected and selected (DBP < 70 mmHg) study population. Results: Including DBP as the risk factor did not change the performance of the machine learning models evaluated using accuracy, AUC, mean, and weighted F-measure, and was not required to make proper predictions of stroke, MI, HF, and primary outcome. Conclusions: Analyses of the SPRINT trial data using ML algorithms imply that DBP should not be treated as an independent risk factor when intensifying blood pressure control.

Keywords: SPRINT trial; cardiovascular risk; diastolic blood pressure; machine learning.

Figure 1

Flowchart presenting ML experiment phases. DBP—diastolic blood pressure, SMOTE—synthetic minority oversampling technique.

Figure 2

Comparison of the performance of the classifiers when DBP was included (DBP (+)) and excluded (DBP (−)) as the predictor presented as boxplots for all outcome variables examined in the unselected population. AUC—area under curve, mF1—mean F-measure, wF1—mean weighted F-measure, no differences detected for all of the comparisons.

Figure 3

Comparison of the performance of the classifiers when DBP was included (DBP (+)) and excluded (DBP (−)) as the predictor presented as boxplots for all outcome variables examined in the selected population of subjects with DBP < 70 mmHg. AUC—area under curve, mF1—mean F-measure, wF1—mean weighted F-measure, no differences detected for all of the comparisons.

Figure 4

Comparison of the performance of the classifiers in the selected (selection) and unselected (no selection) population presented as boxplots for all of outcome variables when diastolic blood pressure was included and excluded as the predictor. AUC—area under curve, mF1—mean F-measure, wF1—mean weighted F-measure, no differences detected for all of the comparisons.

Figure 5

ROC curves of the classifiers detecting of primary outcome when DBP was included as the risk factor. DT—decision tree , KNN—k-nearest neighbor classifier , LR—logistic regression , MLP—multi-layer perceptron , NB—naive Bayesian classifier , RF—random forest .