Abstract:
New technologies such as machine learning and big Data analytics has proven to be a promising solution for the biomedical community, health problems and patients care. It is accurate and therefore useful for early disease prognosis Interpretation of medical information. Disease control strategies Recognizing early symptoms can lead to further improvement Illness. This initial prediction also helps Disease symptoms and proper symptom control Treatment of illness. Machine learning methods can be used Prognosis of chronic diseases like kidney and heart Diseases form classification models. In this paper We propose a comprehensive preprocessing method to predict coronary arteries disease (CAD). This method involves zero substitution Standardization, resampling, normalization, classification, Prediction. This study aims to predict the risk of CAD use machine learning algorithms such as Random Forest, Decision Tree, Naïve Bayes, Logistic Regression and K-Nearest Neighbors. Comparative studies Among these algorithms, prediction accuracy is based on to be done. Additionally, generation are using k-fold cross validation. This algorithm has been tested dataset containing 1190 records and 12 features where Random Forest, Decision Tree, Logistic Regression, K-Nearest Neighbor, Naïve Bayes, and Support Vector Machine achieved 96% accuracy, 93%, 84% and 71% respectively. Therefore, using our in the preprocessing step, random forest classification gives more information more accurate results compared to other machine learning algorithms.
