Cardiovascular disease diagnosis: A machine learning interpretation approach

Abstract

Research on heart diseases has always been the center of attention of the world health organization. More than 17.9 million people died from it in 2016, which represent 31% of the overall deaths globally. Machine learning techniques have been used extensively in that area to assist physicians to develop a firm opinion about the conditions of their heart disease patients. Some of the existing machine learning models still suffers from limited predication ability, and the chosen analysis approaches are not suitable. As well, it was noticed that the existing approaches pay more attention to building high accuracy models, while overlooking the ability to interpret and understand the recommendations of these models. In this research, different renowned machine learning techniques: Artificial Neural Networks, Support Vector Machines, Naïve Bayes, Decision Trees and Random Forests have been investigated to help in building, understanding and interpreting different heart disease diagnosing models. The Artificial Neural Networks model showed the best accuracy of 84.25% compared to the other models. In addition, it was found that despite some designed models have higher accuracies than others, it may be safer to choose a lower accuracy model as a final design of this study. This sacrifice was essential to make sure that a more transparent and trusted model is being used in the heart disease diagnosis process. This transparency validation was conducted using a newly suggested metric: the Feature Ranking Cost index. The use of that index showed promising results by making it clear as which machine learning model has a balance between accuracy and transparency. It is expected that following the detailed analyses and the use of this research findings will be useful to the machine learning community as it could be the basis for post-hoc prediction model interpretation of different clinical data sets.