Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{174294,
        author = {Sana Harshitha and Samayamanthula Sai Ganesh and Gundapu Shashi Kumar and S.Ramadoss},
        title = {Prediction of cardiovascular disease risk using AI},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {10},
        pages = {3356-3364},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174294},
        abstract = {Cardiovascular disease (CVD) remains a leading cause of global mortality, emphasizing the need for accurate and early risk assessment. This study develops an Artificial Neural Network (ANN)-based model for CVD prediction, utilizing key clinical indicators to enhance diagnostic precision.
The methodology includes comprehensive data preprocessing, such as feature scaling and categorical encoding, to ensure optimal feature representation. The ANN model is designed with multiple hidden layers, dropout regularization, and early stopping to improve predictive performance while minimizing overfitting. Additionally, a Flask-based web interface is integrated, allowing seamless data input, model training, and real-time visualization of performance metrics, including accuracy, confusion matrix, and ROC curves.
Experimental results show that the ANN model achieves an 87.2% accuracy and an AUC-ROC score of 90.1%, outperforming traditional machine learning models like Logistic Regression (83.2% accuracy) and Decision Trees (80.7% accuracy). The model also maintains a strong balance between precision (91.2%) and recall (87.8%), ensuring reliable heart disease classification.
These findings highlight the potential of ANN in improving early CVD detection and risk assessment. Future work will focus on incorporating additional biomarkers, refining model architectures, and exploring ensemble learning techniques to further enhance accuracy and clinical applicability.},
        keywords = {ANN, heart disease prediction, Cardiovascular disease (CVD), Convolutional Neural Networks (CNNs), Adaptive Moment Estimation, Receiver Operating Characteristic (ROC)},
        month = {March},
        }