Copyright © 2026 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{206826,
        author = {Mrs. M. Mounika and Grandhi Ranga Madhupriya and A. Vivekanand and Y. Swarageeth and G. Shashank},
        title = {Heart Disease Prediction Using ECG Signal Analysis and Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {604-612},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206826},
        abstract = {The heart disease detection system is a web-based application that seeks to analyze the images of an electrocardiogram (ECG) and detect potential heart conditions with the help of machine learning algorithms. It is a hybrid model that combines both image processing and supervised learning in order to convert ECG images into numerical signals to be analyzed. Initial steps that are followed by the system after the uploaded ECG image is processing involve: transformation to grayscale, Gaussian filtering followed by thresholding having used Otsu thresholding that makes the images clear. The ECG has been preprocessed then divided into 12 standard leads as well as a longer lead of one. Waveform patterns are then determined by using contour detection strategies and translated into one dimensional numerical signal which represent heart activity. Min-Max scaling is then used to normalize these signals and Principal Component Analysis (PCA) is used to trim off the features and this helps in enhancing efficiency and model performance. The refined information is inputted in a trained machine learning model to classify. The algorithms that were tested during development are logistic regression, random forest, Naive Bayes, and K-nearest neighbors. The last model estimates four conditions, which include normal functioning of the heart, arrhythmia, infarction of the myocardium, and the past history concerning attacks. This system was written in Python by using NumPy, Pandas, Scikit-learn and Scikit-image libraries. The interface was created on the basis of the Streamlit framework, thus allowing users to input ECG pictures and get immediate estimates. This project proves to be a good method of early heart disease detection through image processing methods with machine learning models.},
        keywords = {ECG Classification, Machine Learning, Predictive Modeling, Grayscale Conversion, K-Nearest Neighbors (KNN), Image Processing.},
        month = {July},
        }