Authors : Kondeti Sai Likhitha; Pathakamudi Jahnavi; Manchala Siddhardha; Sri. Chekka Ratna Babu

Volume/Issue : Volume 10 - 2025, Issue 5 - May

Google Scholar : https://tinyurl.com/4juz3kkm

Scribd : https://tinyurl.com/3v4wkwbx

DOI : https://doi.org/10.38124/ijisrt/25may175

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : Cardiovascular disease (CVD) remains the leading cause of mortality globally. This study proposes a deep learning-based framework for the detection of cardiovascular conditions from electrocardiogram (ECG) images. Three architectures AlexNet, SqueezeNet, and a custom-designed Convolutional Neural Network (CNN) were trained and evaluated, achieving classification accuracies of 88%, 81%, and 100%, respectively. To facilitate real-world applicability, the models were deployed via a web application using Streamlit, enabling real-time prediction from uploaded ECG images. Furthermore, a majority voting scheme was employed to enhance prediction reliability. The proposed system demonstrates the potential of deep learning models in aiding cardiovascular diagnosis and emphasizes the importance of accessible deployment tools. Future research will focus on larger datasets, additional cardiac conditions, and model interpretability through explainable AI techniques.  Impact Statement Artificial intelligence (AI) continues to transform the field of healthcare, particularly in enhancing early detection and diagnosis of life-threatening diseases. In this work, an automated system for the detection of cardiovascular diseases from ECG images has been developed using deep learning methods, including AlexNet, SqueezeNet, and a custom-designed CNN. The proposed models achieved remarkable classification accuracy, with the custom CNN attaining 100% accuracy on the testing dataset. Importantly, the lightweight architectures are optimized to operate efficiently on systems with limited computational resources, enabling real-time deployment on standard CPUs without the need for high-end GPUs. Furthermore, ensemble techniques such as majority voting have been incorporated to enhance prediction reliability. This advancement has the potential to assist clinicians by providing quick, accurate, and scalable diagnostic support, ultimately contributing to earlier intervention and improved patient outcomes.

References :

1. U. R. Acharya, H. Fujita, S. L. Oh, Y. Hagiwara, J. H. Tan, and M. Adam," Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals," Information Sciences, vol. 415–416, pp. 190–198, Nov. 2017. doi: 10.1016/j.ins.2017.06.027
2. S. Kiranyaz, T. Ince, and M. Gabbouj, "Real-time patient-specific ECG classification by 1-D convolutional neural networks," IEEE Transactions on Biomedical Engineering, vol. 63, no. 3, pp. 664–675, Mar. 2016. doi: 10.1109/TBME.2015.2468589
3. R. Rajpurkar, A. Hannun, M. Haghpanahi, C. Bourn, and A. Y. Ng,"Cardiologist-level arrhythmia detection with convolutional neural networks," arXiv preprint arXiv: 1707.01836, 2017. https://arxiv.org/abs/1707.01836
4. A. A. Talo,"Automated classification of heartbeats using deep neural network with RR interval signals,"Computer Methods and Programs in Biomedicine, vol. 203, p. 106006, Jan. 2021. doi: 10.1016/j.cmpb.2021.106006
5. H. Yildirim,"A novel wavelet sequence based on deep bidirectional LSTM network model for ECG signal classification,"Computers in Biology and Medicine, vol. 96, pp. 189–202, Mar. 2018.
6. World Health Organization (WHO), “Cardiovasculardiseases,” Jun. 11, 2021. Accessed: Dec. 27, 2021. [Online].
7. Government of Westren Australia, Department of Health, “Common medical tests to diagnose heart conditions,” Accessed: Dec.29, 2021. [Online].
8. M. Swathy and K. Saruladha, “A comparative study of classification and prediction of cardio-vascular diseases (CVD) using machine learning and deep learning techniques,” ICT Exp., to be published, 2021. [Online].
9. R. R. Lopes et al., “Improving electrocardiogram-based detection of rare genetic heart disease using transfer learning: An Application to phospholamban p.Arg14del mutation carriers,” Comput. Biol. Med., vol. 131, 2021, Art. No. 104262. [Online].
10. R. J. Martis, U. R. Acharya, and H. Adeli, “Current methods in electrocardiogram characterization,” Comput. Biol. Med.,vol.48, pp. 133–149, 2014. [Online].
11. M. Kantardzic, Data Mining: Concepts, Mode Methods, and Algorithms, 3rded. Hoboken, NJ, USA: Wiley, 2020.
12. S. García, J. Luengo, and F. Herrera, Data Preprocessing in Data Mining, 1st ed. Berlin, Germany: Springer, 2015.
13. G. Dougherty, Pattern Recognition and Classification: An Introduction. Berlin, Germany: Springer, 2013.
14. A. Subasi, Practical Machine Learning for Data Analysis Using Python. Cambridge, MA, USA: Academic, 2020.
15. J. Soni, U. Ansari, D. Sharma, and S.  Soni, “Predictive data mining for medical diagnosis: An overview of heart disease prediction,” Int. J. Comput. Appl., vol. 17, no. 8, pp. 43–48, 2011.
16. K.Dissanayake and M. G. Md Johar, “Comparative study on heart disease prediction using feature selection techniques on classification algorithms,” Appl. Comput. Intell. Soft Compute. vol. 2021, 2021, Art. No. 5581806.
17. A. H. Gonsalves, F. Thabtah, R. M. A. Mohammad, and G. Singh, “Prediction of coronary heart disease using machine learning: An experimental analysis,” in Proc. 3rd Int. Conf. Deep Learn. Technol., 2019, pp. 51–56. [Online].
18. H.Kim, M.I.M.Ishag, M.Piao, T.Kwon, and K.H.Ryu, “Adatamining approach for cardio vascular disease diagnosis using heart Rate variability and images of carotid arteries,” Symmetry, vol. 8, no. 6, 2016, Art. No. 47.
19. T. Ozcan, “A new composite approach for COVID-19 detection in X-ray images,” Appl. Soft Comput., vol. 111, 2021, Art. No. 107669. [Online].
20. F. N. Iandola, S. Han, M. W. Moskewicz,K. Ashraf, W. J. Dally, and K. Keutzer,“SqueezeNet: Alexnet-level accuracy with 50xfewer parameters and< 0.5 MB model size,”2016, arXiv:1602.07360.