Abstract: The intent is to create an ECG image-based machine learning system for the detection of cardiovascular disorders. After digitizing ECG recordings, the system preprocesses them using methods including contour detection, noise reduction, and grayscale conversion before extracting important features such the A, BCD, and E waves. To classify the ECG data into distinct disease categories, such as normal, myocardial infarction, and aberrant heartbeats, these properties are examined using machine learning models, such as SVM, KNN, and Random Forest.
By automating the analytical process, the project overcomes the drawbacks of the present manual approaches and increases the speed and accuracy of diagnosis. Clinical decision-making is aided by the real-time feedback and result visualization made possible by an intuitive web interface. The study comes to the conclusion that improvements in image processing and machine learning greatly improve the capacity to identify heart conditions from ECG pictures. To enable a wider range of applications in clinical settings, future work will involve enhancing feature extraction algorithms and growing datasets.
|
DOI:
10.17148/IJARCCE.2024.13904
