Classification and Prediction on Hypertension with Blood Pressure Determinants in a Deep Learning Algorithm

Abstract

Few studies classified and predicted hypertension using blood pressure (BP)-related determinants in a deep learning algorithm. The objective of this study is to develop a deep learning algorithm for the classification and prediction of hypertension with BP-related factors based on the Korean Genome and Epidemiology Study-Ansan and Ansung baseline survey. We also investigated whether energy intake adjustment is adequate for deep learning algorithms. We constructed a deep neural network (DNN) in which the number of hidden layers and the number of nodes in each hidden layer are experimentally selected, and we trained the DNN to diagnose hypertension using the dataset while varying the energy intake adjustment method in four ways. For comparison, we trained a decision tree in the same way. Experimental results showed that the DNN performs better than the decision tree in all aspects, such as having higher sensitivity, specificity, F1-score, and accuracy. In addition, we found that unlike general machine learning algorithms, including the decision tree, the DNNs perform best when energy intake is not adjusted. The result indicates that energy intake adjustment is not required when using a deep learning algorithm to classify and predict hypertension with BP-related factors.

A systematic review of prediction accuracy as an evaluation measure for determining machine learning model performance in healthcare systems

“…This, we believe is not exhaustive, other evaluation assessments for its applicability in context will be examined in future research studies. Breast cancer risk prediction Support vector machine accuracy 97.13 [29] Breast cancer diagnosis Support vector machine, Random Forest, Logistic Regression, Decision tree (C4.5) and K-Nearest Neighbors accuracy 97.2 [31] Treatment trend prediction for hypothyrodism Extra trees accuracy 84 [32] Chronic kidney disease prediction Random forest, support vector machine, decision tree accuracy 99.8, 95.5, 98.6 [33] Chronic disease progression (sclerosis) K-nearest neighbor, support vector machine, decision tree, logistic regression auc [34] Chronic kidney disease detection K-nearest neighbor, random forest, neural networks accuracy 0.993 [35] Advanced chronic kidney disease prediction Logistic regression, random forest, decision tree accuracy 81.9, 82.1, 82.1 [36] Prediction of hypertension Deep neural network, decision tree accuracy 0.75, 0.69 [37] Risk prediction (hypertension) k-nearest neighbor, multi-layer perceptron accuracy 82.47 [38] Prediction of hypertension Artificial neural network accuracy 82 [39] Heart disease risk prediction [40] Hypertension prediction extreme Gradient Boosting, Gradient Boosting Machine, Logistic Regression, Random forest, Decision tree and Linear Discriminant Analysis accuracy 83-90% [41] Spam detection Naive Bayes, decision tree, neural networks, random forest, support vector machine accuracy 96.9-99.66 [42] Spam detection ensemble accuracy 99.91 [43] Malicious spam in mails Naive Bayes, support vector machine, logistic regression and random forest accuracy 96.15, 96.15, 98.08, 95.38 [44] Sms spam classification Naive Bayes, BayesNet, C4.5, J48, Self-organizing map and Decision tree accuracy 89.64, 91.11, 80.24, 79.2, 88.24, 75.76 [45] Junk email detection Support vector, random forest accuracy 93.52, 91.41 [46] Email spam detection Bagging, random forest, decision tree (J48) accuracy 98 [47] Credit…”

“…Its conclusion recommends an improvement on these prediction accuracy scores. The application of deep learning in the prediction and classification of hypertension with blood pressured related variables for which those positive for hypertension was 1883 and those without hypertension were 6266 [38], a comparative performance evaluation between deep neural network and decision tree classifier with four different datasets showed the following prediction accuracies; Deep neural network: (0.75, 0.739, 0.743, 0.743) and for Decision tree: (0.676, 0.684, 0.690, 0.680). Further risk prediction studies aid at improving prediction performance with reliable techniques [39] for cardiovascular diseases using ML techniques such as K-nearest neighbor and Multi-layer perceptron (MLP) showed a prediction accuracy of 82.47% for MLP.…”

Imbalanced class distribution and performance evaluation metrics: A systematic review of prediction accuracy for determining model performance in healthcare systems

“…Its conclusion recommends improvement on achieved prediction accuracy score. Application of deep learning technique for prediction and classification of hypertension with related variables [ 38 ] showed the following prediction accuracy scores; Deep neural network: (75%, 73.9%, 74.3%, 74.3%) and Decision tree: (67.6%, 68.4%, 69%, 68%). Related study [ 39 ] on the prediction of hypertension using features such as patient demographics, past and current patient health condition and medical records for the determination of risk factors using artificial neural network showed prediction accuracy score of 82%.…”

Advancing diabetes prediction with a progressive self-transfer learning framework for discrete time series data

“…Active research related to chronic diseases including diabetes and hypertension has been conducted due to the growing size of the affected populations and the social interest in these conditions. For example, recent studies have addressed the application of deep neural networks (DNNs) in hypertension 19 , as well as the use of LSTM and multi-layer perceptrons (MLPs) in heart disease 20 . Furthermore, the recent Corona virus 2019 (COVID-19) epidemic has led to various time series prediction tasks, including the use of deep learning algorithms such as LSTM, GRU and bi-LSTM 21 , 22 .…”