@article { author = {Neshati Tanha, Arezoo and Soleimani, Paria}, title = {Prediction of Acute Heart Attack using Logistic Regression (Case Study: A Hospital in Iran)}, journal = {Advances in Industrial Engineering}, volume = {50}, number = {1}, pages = {109-119}, year = {2016}, publisher = {University of Tehran}, issn = {2783-1744}, eissn = {2783-1744}, doi = {10.22059/jieng.2016.59436}, abstract = {Acute myocardial infarction is the most important reason of mortality in Iran. More than half of these deaths occur without the patient even reaching to a hospital. There is the evidence that patients with better knowledge of the symptoms of MI will seek help earlier. The purpose of this study is to determine how well a predictive model will perform based solely upon patient-reportable clinical history factors, without using diagnostic tests or physical exam findings. We use 28 patient-reportable history factors that are included as potential covariates in our models. Using a derivation data set of 663 patients, we build three logistic regression models and one decision tree model to estimate the likelihood of acute coronary syndrome based upon patient-reportable clinical history factors only. The best performing logistic regression model have a C-index of 0.955 and with an accuracy of 94.9%. The variables, severe chest pain, back pain, cold sweats, shortness of breath, nausea and vomiting is selected as the main features. A decision tree model has a C-index of 0.938. The variables, shortness of breath, palpitations, edema, sweats, left chest pain, age, severe chest pain and nausea are selected as the main features. This model can have important utility in the applications outside of a hospital setting when objective diagnostic test information is not yet available. Given the very high mortality from MI in the Iran, even a small reduction in median time from onset of symptoms to treatment can translate into a substantial number of lives saved.}, keywords = {Acute coronary syndrome,Coronary Artery Disease,Decision Tree,Logistic regression,prediction}, url = {https://aie.ut.ac.ir/article_59436.html}, eprint = {https://aie.ut.ac.ir/article_59436_17e46121797c3e0bdf6bb3e760c5a479.pdf} }