Improving Accuracy in Intelligent Coronary Heart Disease Diagnosis Prediction Model using Support Vector Clustering Technique Compared over Random Forest Classifier Algorithm

Babu, Mudragada Sai; Karthick, V.

doi:10.1109/icses55317.2022.9914283

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is hoped that the results of this study can contribute new knowledge about the best classification algorithm for heart disease prediction models. In addition (Babu & Karthick, 2022;Hackshaw dkk., 2018;Latha & Jeeva, 2019), the prediction model produced in this study can be used to prevent and diagnose heart disease more quickly and accuratel. Thus, health workers can take more appropriate prevention and treatment steps.…”

Section: Introductionmentioning

confidence: 99%

Prediction Model for Diagnosing Heart Disease Using Classification Algorithm

Pradini,

Anshori,

Haris

et al. 2023

J. of World Future Medicine, Health and Nursing

View full text Add to dashboard Cite

Heart disease often causes death if not treated quickly and appropriately. Early diagnosis can prevent more serious complications and treat heart disease patients best. The existence of a disease prediction model can help health workers to diagnose diseases more quickly and accurately. The heart disease prediction model using a classification algorithm is a system built using machine learning techniques. The classification algorithm chosen is NN, Naive Bayes, Random Forest, and SVM because it is the best algorithm for predicting heart disease. This study makes a comparison of the four algorithms using a dataset of 918 instances with 11 features. The result is that the Random Forest algorithm produces the highest accuracy, with 86.8%, and has the best ability to distinguish classes based on the ROC curve.

show abstract

Section: Introductionmentioning

confidence: 99%