Machine learning of big data in gaining insight into successful treatment of hypertension

Abstract

Despite effective medications, rates of uncontrolled hypertension remain high. Treatment protocols are largely based on randomized trials and meta‐analyses of these studies. The objective of this study was to test the utility of machine learning of big data in gaining insight into the treatment of hypertension. We applied machine learning techniques such as decision trees and neural networks, to identify determinants that contribute to the success of hypertension drug treatment on a large set of patients. We also identified concomitant drugs not considered to have antihypertensive activity, which may contribute to lowering blood pressure (BP) control. Higher initial BP predicts lower success rates. Among the medication options and their combinations, treatment with beta blockers appears to be more commonly effective, which is not reflected in contemporary guidelines. Among numerous concomitant drugs taken by hypertensive patients, proton pump inhibitors (PPIs), and HMG CO‐A reductase inhibitors (statins) significantly improved the success rate of hypertension. In conclusions, machine learning of big data is a novel method to identify effective antihypertensive therapy and for repurposing medications already on the market for new indications. Our results related to beta blockers, stemming from machine learning of a large and diverse set of big data, in contrast to the much narrower criteria for randomized clinic trials (RCTs), should be corroborated and affirmed by other methods, as they hold potential promise for an old class of drugs which may be presently underutilized. These previously unrecognized effects of PPIs and statins have been very recently identified as effective in lowering BP in preliminary clinical observations, lending credibility to our big data results.

Hybrid Prediction Model for Type 2 Diabetes and Hypertension Using DBSCAN-Based Outlier Detection, Synthetic Minority Over Sampling Technique (SMOTE), and Random Forest

“…Furthermore, several studies have been conducted and revealed that the machine learning algorithms provide early prediction as well as treatment for hypertension. Koren et al investigated the advantage of machine learning for treatment of hypertension [17]. They used machine learning methods to distinguish determinants that add to the accomplishment of hypertension drug treatment on a massive set of patients.…”

Chloroquine for Covid 19: introducing drug repurposing to medical students

“…For example, it has been recently shown, using novel algorithms based on over 2 millions electronic patient records, that statins and proton pump inhibitors decrease blood pressure independently of typical antihypertensive drugs. 12 Similarly, it has been documented that alpha 2 blockers exert a hypoglycemic effect, independent of the hypoglycemic effects of regular antidiabetic drugs. 13 The second task involved students presenting the published evidence leading to labeling bupropion as an antismoking agent, followed by group discussion .The identification of repurposable agents against Covid 19 involves a screening process in which different in vitro concentrations of a given drug are examined for their ability to inhibit the viral replication in appropriate cell culture.…”

Machine learning and blood pressure

“…In recent years, the relationship between BP and other CVD risk factors have been studied with ML techniques. Surprisingly, beta‐blockers have been shown to be more effective than expected, compared to other anti‐hypertensives (especially in the light of different guidelines for hypertension management), and the concomitant use of statins and proton pump inhibitors appears to be synergistic in improving the success of anti‐hypertensives . Data from the SPRINT trial have been re‐analyzed with random forest plot to predict cardiovascular outcomes and it was shown that the most important determinants were urine albumin/creatinine ratio, estimated GFR, age, serum creatinine, history of subclinical cardiovascular disease (CVD), serum cholesterol, a variable representing SBP signals using wavelet transformation, HDL levels, the 90th percentile of SBP, and serum triglyceride with an overall AUC (Area Under the Curve) of 0.71 .…”