FORECASTING DISCLOSURE OF CARDIOVASCULAR DISEASE USING MACHINE LEARNING

Abstract

Data mining is a process that uses a combinational framework out of a supportable assessment and machine learning data collection development to eliminate hidden models from massive informative collections. Further, clinical data mining is a basic assessment field in light of its substance in the progression of numerous applications in the flourishing clinical benefits zone. However, considering the current occurrences around the globe, the coronary ailment radiates an impression of being the primary source. The ID of the probability of coronary disease in an individual is a tangled endeavor for clinical experts since it requires extended lengths of contribution and genuine clinical preliminaries to be considered. In this study, four data mining techniques for data collection, namely K-Nearest Neighbour, Random Forest, Decision Tree, Navie Bayes, are utilized to establish a figure model to evaluate and identify risk factors of coronary disease. primary goal of this preliminary inquiry is to determine the optimal representation count fitting for providing the highest level of precision when collecting data from regular and periodic individuals. With the assistance of the coronary disease benchmark dataset recovered from the UCI repository, an unstable setup was created for the evaluation of the show of counts. When compared to other estimations for coronary disease inference, Random Forest count achieves the highest accuracy with 90.16 %.

Keywords

• data mining
• random forest
• coronary disease
• naive bayes
• knn