|
AUTHOR(S): Achuthananda Reddy Polu, Bhumeka Narra, Dheeraj Varun Kumar Reddy Buddula, Hari Hara Sudheer Patchipulusu, Navya Vattikonda, Anuj Kumar Gupta
|
TITLE Advanced AI Techniques for Cardiovascular Disease Forecasting Using Large-Scale Health Data |
 PDF |
ABSTRACT The early and accurate prediction of CVDs is of great importance in order to make timely interventions and avoid life-threatening complications. The heart disease is forecasted using machine learning using the XGBoost (Extreme Gradient Boosting) algorithm in this study. It develops and test the model on a large heart disease dataset of 8,763 records with different features such as demographic info, medical history, clinical indicators and lifestyle habits. Missing value imputation, outlier removal, attribute reduction and feature scaling are done to extensive data preprocessing to enhance the model reliability. Key performance measures, such as accuracy, precision, recall, and F1-score, are used to compare the proposed XGBoost model to the existing classification techniques, K-Nearest Neighbors (KNN) and Naïve Bayes (NB). The results show how much better the proposed model performs than the existing models; its F1-score is 94.46%, accuracy is 92.38%, precision is 99.43%, and recall is 89.9%. The results of this confirm the ability of XGBoost for the prediction of cardiovascular disease and its promise for practical real-world healthcare applications of early diagnosis and risk assessment. |
KEYWORDS Cardiovascular Disease Prediction, Machine Learning, XGBoost, Heart Disease Dataset |
|
Cite this paper Achuthananda Reddy Polu, Bhumeka Narra, Dheeraj Varun Kumar Reddy Buddula, Hari Hara Sudheer Patchipulusu, Navya Vattikonda, Anuj Kumar Gupta. (2025) Advanced AI Techniques for Cardiovascular Disease Forecasting Using Large-Scale Health Data. International Journal of Computers, 10, 251-259 |
|
