Abstract
Cardiovascular disease is a problem in the blood vessels that do not run smoothly into the heart. This is fatal in patients with a history of heart disease. This problem often occurs in the flow of blood pumps into the heart. The problem examined in this study is how to complete the level of accuracy of each data set and the reduction of each attribute in heart disease. The purpose of this study is to analyze heart disease and classify heart disease using the chi-square and K-Nearest Neighbor algorithms. The results of the study with patient age 57, gender LK, cp 3, trestbps 200, chol 564, fbs 1, restecg 2, thalach 202, oldpeak 6.2, slope 2, ca 4, and the value of thal 3 for the target is there is disease heart 0 or 1 is detected without heart disease when the max-min data is normalized. while to measure the performance of the algorithm with the value of the confusion matrix with the actual class value of 1, prediction class 1 value 44, actual class 0 and prediction class value 6. while the actual class value 0-1, prediction class 1 value 5 and 0-0 value 36. the final stage value of the accuracy measure is 0.87912, the recall value is 0.89797 and the precision value is 0.85714. The implication of the application of the test has an optimal test, the accuracy value with data K = 303 then it can be concluded that based on the test the calculation of the KNN model obtained an accuracy of 91%
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: JOURNAL OF INFORMATICS AND TELECOMMUNICATION ENGINEERING
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.