International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 07 | July 2023
p-ISSN: 2395-0072
www.irjet.net
Comparative Analysis of Heart Disease Prediction Models: Unveiling the Most Accurate and Reliable Machine Learning Algorithm Aatmaj Amol Salunke1 Computer Science & Engineering Department of Computer Science & Engineering, School of Computer Science and Engineering, Manipal University Jaipur Rajasthan, India ---------------------------------------------------------------------***---------------------------------------------------------------------
Abstract - Heart disease is a significant health concern, warranting accurate prediction models for timely intervention. This research paper presents a comparative analysis of three popular machine learning algorithms, namely Logistic Regression, Support Vector Machines (SVM), and Random Forest, for heart disease prediction. Utilizing a comprehensive dataset encompassing clinical and lifestyle features, each model was developed and evaluated using standard metrics. The study unveils the most accurate and reliable algorithm for heart disease prediction, offering valuable insights into model performance. Furthermore, feature importance analysis sheds light on critical factors influencing accurate predictions. The results aid healthcare professionals in selecting the most appropriate model for efficient heart disease prediction, contributing to improved patient care and clinical decision-making. Random Forest achieved 88% accuracy, outperforming Logistic Regression and SVM for heart disease prediction. Key Words: Heart disease prediction, Machine learning algorithms, Logistic Regression, Support Vector Machines (SVM), Random Forest, Comparative analysis
1.RELATED WORK Ali et al. [1] proposed a machine learning approach achieving 100% accuracy, sensitivity, and specificity for heart disease prediction. Ghosh et al. [2] proposed a model achieving 99.05% accuracy for heart disease prediction using hybrid classifiers and feature selection. Khourdifi et al. [3] proposed a hybrid approach achieving 99.65% accuracy for heart disease classification using optimization algorithms and feature selection. Latha et al. [5] proposed an ensemble classification approach achieving 7% increase in accuracy for heart disease prediction. Bhatla et al. [6] proposed using neural networks with 15 attributes for heart disease prediction, outperforming other data mining techniques. Gonsalves et al. [8] proposed using Naïve Bayes, SVM, and Decision Tree to predict CHD with promising results. Salhi et al. [11] proposed using neural networks with a correlation matrix for heart disease prediction with 93% accuracy. Souri et al. [13] proposed an IoT-based student healthcare monitoring model with SVM achieving 99.1% accuracy. Ramesh et al. [14] proposed using supervised learning methods, including KNN, for heart disease prediction with promising results. Alarsan et al. [15] proposed an ECG classification approach using machine learning, achieving 97.98% accuracy with Random Forest for binary classification.
2.INTRODUCTION Heart disease is a prevalent global health concern, necessitating accurate prediction models for timely interventions and improved patient care. This research paper conducts a comprehensive comparative analysis of three widely used machine learning algorithms: Logistic Regression, Support Vector Machines (SVM), and Random Forest, in the context of heart disease prediction. Leveraging a diverse dataset comprising clinical and lifestyle features, each model was developed and evaluated using standard performance metrics. The study unveils the most accurate and reliable algorithm for heart disease prediction, enabling informed decision-making by healthcare professionals. Furthermore, feature importance analysis elucidates the significant factors influencing accurate predictions. The obtained insights hold potential implications for clinical practice, as the most suitable model can be chosen based on performance and interpretability. Ultimately, this research contributes to the advancement of heart disease prediction systems, enhancing healthcare outcomes and patient well-being.
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 1122