ecg image-based cardiovascular disease identification using deep learning
Arun Kumar D S,Balanishanth G,B Johney,Kishore E
Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology
ISSN: 2321-3337 Impact Factor:1.521 Volume:6 Issue:3 Year: 13 April,2026 Pages:2113-2119
Abstract
Cardiovascular diseases (CVDs) are one of the primary reasons for death across the globe which must requires the early diagnosis system. Therefore, we propose a deep learning system for detection of cardiovascular diseases based on the ECG image. The system utilizes Convolutional Neural Network (CNN) as a framework of VGG16 model to automatically discover effective patterns and features of ECG signals from the image. First, ECG images are preprocessed including removing noise, normalization, and segmentation to enhance data quality. Then, the features of ECG signals which are related to the abnormalities of heart are extracted. Finally, a deep learning model is trained to classify the ECG image to classify cardiovascular diseases such as arrhythmia, myocardial infarction, and irregular heart beat pattern. our system result shows that has increased the accuracy and speed up the process of diagnosing the heart disease to assist the doctor’s decision.
Kewords
Cardiovascular Disease (CVDs), Deep Learning, Electrocardiogram (ECG), Convolutional Neural Network (CNN).
Reference
[1] P. G. Shynu, V. G. Menon, R. L. Kumar, S. Kadry and Y. Nam, "Blockchain-Based Secure Healthcare Application for Diabetic-Cardio Disease Prediction in Fog Computing," in IEEE Access, vol. 9, pp. 45706-45720, 2021, doi: 10.1109/ACCESS.2021.3065440. [2] X. Zhang, S. Fishlock, P. Sharpe and J. McLaughlin, "Cystatin C as a biomarker for cardiorenal syndrome diseases quantitative diagnostics and monitoring via point-of-care," 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), Glasgow, Scotland, United Kingdom, 2022, pp. 1428-1431, doi: 10.1109/EMBC48229.2022.9871131. [3] MalCaDD Framework’s Code and User Manual. Accessed: [Online].Available: 8/Machine-Learning [4] X. Y. Gao, A. Amin Ali, H. H. Shaban Hassan, and E. M. Anwar, ‘‘Improving the accuracy for analyzing heart diseases prediction based on the ensemble method,’’ Complexity, vol. 2021, Feb. 2021, Art. no. 6663455. [5] A. Jafar and M. Lee, "HypGB: High Accuracy GB Classifier for Predicting Heart Disease With HyperOpt HPO Framework and LASSO FS Method," in IEEE Access, vol. 11, pp. 138201 138214, 2023, 10.1109/ACCESS.2023.3339225. doi: [6] N. F. A. Alhadeethy, A. M. Zeki, and A. Shah, ‘‘Deep learning model for predicting and detecting overlapping symptoms of cardiovascular diseases in hospitals of UAE,’’ Turkish J. Comput. Math. Educ. (TURCOMAT), vol. 12, no. 14, pp. 5212–5224, 2021 [7] H. E. Bays, P. R. Taub, E. Epstein, E. D. Michos, R. A. Ferraro, A. L. Bailey, H. M. Kelli, K. C. Ferdinand, M. R. Echols, H. Weintraub, and J. Bostrom, ‘‘Ten things to know about ten cardiovascular disease risk factors,’’ Amer. J. Preventive Cardiol., vol. 5, Mar. 2021, Art. no. 100149. [8] G. Battineni, G. G. Sagaro, N. Chintalapudi, and F. Amenta, ‘‘The benefits of telemedicine in personalized prevention of cardiovascular diseases (CVD): A systematic review,’’ J. Personalized Med., vol. 11, no. 7, p. 658, Jul. 2021. [9] L.-C. Tao, J.-N. Xu, T.-T. Wang, F. Hua, and J.J. Li, ‘‘Triglyceride-glucose index as a marker in cardiovascular diseases: Landscape and limitations,’’ Cardiovascular Diabetol., vol. 21, no. 1, pp. 1–17, Dec. 2022. [10] D. Chieng and P. M. Kistler, ‘‘Coffee and tea on cardiovascular disease (CVD) prevention,’’ Trends Cardiovascular Med., vol. 32, no. 7, pp. 399–405, Oct. 2022.
