Predicting the Causal Effect Relationship Between COPD and Cardio Vascular Diseases

Abstract

Coronary Obstructive Pulmonary Disease (COPD) is one of the critical factors that areaffecting the health of the population worldwide and in most cases affects the patientwith cardiovascular diseases and their mortality. The onset of COPD in a patient in mostof the cases affects him/her with cardio vascular disease and the management of the dis-ease becomes more complex for medical practitioners to handle. The factors affectingCOPD and cardiovascular disease in patients are most of the times, concurrent and areresponsible for their mortality. The list of factors and their underlying causes have beenidentified by experts and are treated with utmost importance before the patient suffersfrom an emergency condition and its management becomes even more difficult.This paper discusses the need to study COPD and the factors affecting it to avoidcardiovascular deaths. The dataset used for the study is a novel one and has beencollected from a Government Medical College, for study and experimentation. Classi-fication methods like Decision Trees, Random Forest (RF), Logistic Regression (LR),SVM (Support Vector Machine), KNN (K-Nearest Neighbours) and Naive Bayes havebeen used and Random Forests have given the best results with 87.5% accuracy. Theimportance of the paper is in the attempt to infer important links between the associ-ated features to predict COPD. To the best of our knowledge, such an attempt to inferthe decision regarding the prediction of COPD using Machine Learning classifiers hasnot been made yet. We have attempted to show an important correlation between theassociated features of COPD and compare different supervised classifiers to check theprediction performance after pre-processing the raw data. Coronary Pulmonate, Age,and Smoking have shown a strong correlation with the presence of COPD and the per-formance analyses of the classifiers have been shown using the ROC (Receiver OperatingCharacteristic) curve.