Downloads: 18 | Views: 274 | Weekly Hits: ⮙2 | Monthly Hits: ⮙4

Research Paper | Computer Science & Engineering | India | Volume 13 Issue 10, October 2024 | Popularity: 6.6 / 10

Rate This Article!      

Advancements in Heart Disease Prediction: A Machine Learning Approach for Early Detection and Risk Assessment

Aniruth Ramanathan V, Sriram Yerra, Dr. Swetha N. G. , Pralipth Gandikota

Abstract: This study aims to evaluate the efficacy of various machine learning models in predicting heart disease risk based on clinical data. Heart disease risk prediction is clinically essential, so the authors used machine learning (ML) on clinical data to identify and assess the impact of various features on the classification of patients with and without heart disease. The authors used cross-sectional clinical data in this study. The designed ML approach established the role of various clinical features in the prognosis of heart disease. Among the evaluated attributes, certain features were identified as strong predictors with significant values. The authors employed seven ML classifiers, including Logistic Regression, Decision Tree, Random Forest, k-Nearest Neighbors, Naive Bayes, Support Vector Machine (SVM), and Neural Networks. The performance of each model was assessed based on accuracy metrics, with SVM exhibiting the highest accuracy at 91.51%. The Support Vector Machine (SVM) model exhibited the highest accuracy at 91.51%, demonstrating superior predictive capability among the evaluated models. The findings highlight the potential of advanced computational methodologies in cardiovascular risk assessment and management. This study underscores the potential of machine learning models in enhancing cardiovascular risk assessment and management. The high accuracy of the SVM model demonstrates its value in clinical settings, paving the way for future advancements in personalized medicine and proactive healthcare interventions.

Keywords: Machine Learning, Heart Disease Prediction, Support Vector Machine, Clinical Data, Cardiovascular Risk Assessment, Predictive Modeling, Personalized Medicine

Edition: Volume 13 Issue 10, October 2024

Pages: 774 - 780

DOI: https://www.doi.org/10.21275/SR241004171836

Make Sure to Disable the Pop-Up Blocker of Web Browser

Click to Cite this Article

Similar Articles