Machine Learning Algorithms for Predicting Coronary Artery Disease: Efforts Toward an Open Source Solution

Abstract

The development of Coronary Artery Disease (CAD), one of the most prevalent diseases in the world, is heavily influenced by several modifiable risk factors. Predictive models built using machine learning (ML) algorithms may assist healthcare practitioners in timely detection of CAD, and ultimately, may improve outcomes. In this study, we have applied six different ML algorithms to predict the presence of CAD amongst patients listed in an openly available dataset provided by the University of California Irvine (UCI) Machine Learning Repository, named "the Cleveland dataset." All six ML algorithms achieved accuracies greater than 80%, with the "Neural Network" algorithm achieving accuracy greater than 93%. The recall achieved with the "Neural Network" model is also highest of the six models (0.93). Additionally, five of the six algorithms resulted in very similar AUC-ROC curves. The AUC-ROC curve corresponding to the "Neural Network" algorithm is slightly steeper implying higher "true positive percentage" achieved with this model. We also extracted the variables of importance in the "Neural Network" model to help in the risk assessment. We have released the full computer code generated in this study in the public domain as a preliminary effort toward developing an open solution for predicting the presence of coronary artery disease in a given population and present a workflow model for implementing a possible solution.

Predictive Model and Feature Importance for Early Detection of Type II Diabetes Mellitus

“…These results are comparable to the findings of several previous studies [31,35,64]. For example, using a neural network model, Akella and Kaushik (2020) identified resting blood pressure, serum cholesterol and blood glucose as part of the top 10 variables of importance in cardiovascular disease prediction [65].…”

Application of Machine Learning Algorithms in Coronary Heart Disease: A Systematic Literature Review and Meta-Analysis

“…The number of publications on this phenomenon decreased from 12 in 2019 to 7 in 2020. CAD presence prediction 23 [25] Heart disease prediction 5 [26] Coronary heart disease prediction 24 [27] Heart disease prediction 6 [28] CHD detection 25 [29] CHD prediction 7 [30] CAD prediction 26 [31] CHD prediction 8 [32] predict coronary heart disease 27 [33] prediction of CHD 9 [16] CHD Prediction based on risk factors 28 [34] classification of coronary artery disease medical data sets [1] Accuracy of ML algorithms for predicting clinical events 29 [35] Prediction of CHD [17] methodology of predicting CHD 30 [36] CAD detection [37] CAD detection 31 [2] CHD Prediction [38] prediction of heart diseases 32 [39] Heart Disease Diagnosis [40] prediction of heart diseases 33 [41] CHD prediction [42] CAD diagnosis 34 [43] CHD prediction [44] Prediction of CHD 35 [45] NN-based prediction of CHD [46] Diagnosing CHD 36 [47] Prediction of CHD [48] prediction of heart disease 37 [49] Prediction of CHD [50] CHD Diagnosis…”

Clinical utility of brain-derived neurotrophic factor as a biomarker with left ventricular echocardiographic indices for potential diagnosis of coronary artery disease

“…We construct SVM models which showed significant improvement in detecting CAD with BDNF as one of the attributes (Table 5). Recently, Akella et al, 2020 use a variety of machine learning algorithms and achieved maximum accuracy of 93% in detecting CAD 26 . Interestingly our study showed benefit of adding the BDNF as one of the attribute to SVM models that represents blood parameters (neutrophils and total cholesterol) and echocardiography indices (LVMI, MV E/A, PV AR, and Biplane LVEF) in CAD (Tables 3, 4).…”