What question did this study set out to answer?

June 3, 20260 citationsOpen Access

Machine Learning-Based Heart Disease Prediction

Key Points

The aim is to predict heart disease using machine learning techniques on a dataset of patient records.
Analyzed a dataset of 5,000 patient records with 13 clinical features.
Implemented five classification algorithms: Logistic Regression, ANN, KNN, Decision Tree, and Gaussian Naive Bayes.
Conducted data preprocessing, exploratory data analysis, correlation analysis, and model evaluation.
Decision Tree achieved the highest accuracy of 100%.
ANN followed with an accuracy of 98.5%.
Model validation showed 100% cross-validation accuracy and an ROC-AUC score of 1.000.

Abstract

This research paper focuses on predicting heart disease using machine learning techniques on a dataset of 5,000 patient records with 13 clinical features. Five classification algorithms—Logistic Regression, ANN, KNN, Decision Tree, and Gaussian Naive Bayes were implemented and compared. The study includes data preprocessing, exploratory data analysis, correlation analysis, and model evaluation. Results showed that the Decision Tree achieved the highest accuracy of 100%, followed by ANN with 98.5%. A 10-fold cross-validation and ROC-AUC analysis further validated the model's performance, achieving 100% cross-validation accuracy and an ROC-AUC score of 1.000. The findings demonstrate the potential of machine learning for accurate and early heart disease prediction.

Ask AI

Helpful

Bookmark

View Full Paper