Cardio Vision - Innovating Healthcare for well being through Cardio Vascular Disease Detection

CardioVision successfully demonstrates an effective and reliable approach for the automated detection and classification of cardiovascular abnormalities using ECG images by integrating deep learning and traditional machine learning techniques. The preprocessing stage played a vital role in enhancing the quality and consistency of ECG images, which in turn improved the accuracy and stability of feature extraction. Deep learning models based on convolutional neural network architectures effectively learned complex spatial and morphological patterns present in ECG signals, capturing subtle waveform variations associated with different cardiac conditions. These extracted features were then utilized by machine learning classifiers to establish clear and reliable decision boundaries, leading to accurate classification outcomes. The system achieved consistent performance across multiple cardiac categories, highlighting its potential to assist medical professionals in timely and informed diagnostic decision-making. Furthermore, the integration of the trained models into a user-friendly web-based interface improved system accessibility and practical usability in clinical settings. Overall, the experimental results validate that the proposed hybrid CardioVision framework can serve as a dependable and efficient decision-support tool for the early detection and classification of heart disorders.  

  1.       Acharya, U. R., Oh, S. L., Hagiwara, Y., Tan, J. H., Adam, M., & Gertych, A. (2017).Application of Deep Convolutional Neural Network for Automated Detection of Myocardial Infarction Using ECG Signals. Information Sciences, Vol. 415–416, pp. 190–198.   2.       Bharti, R., Khamparia, A., Shabaz, M., Dhiman, G., Pande, S., & Singh, K. (2021).Prediction of Heart Disease Using a Combination of Deep Learning and Machine Learning Techniques. Computers, Materials & Continua, Vol. 67, pp. 1399–1412.   3.       Khan, M. A., & Zubair, M. (2023). An Ensemble Deep Learning Model for ECG Image Classification in Cardiac Diagnosis. IEEE Access, Vol. 11, pp. 55678–55690.   4.       Kiranyaz, S., Ince, T., & Gabbouj, M. (2016). Real-Time Patient-Specific ECG Classification by 1-D Convolutional Neural Networks. IEEE Transactions on Biomedical Engineering, Vol. 63, No. 3, pp. 664–675.   5.       Li, Q., Rajagopalan, C., & Clifford, G. D. (2021). A Machine Learning-Based Approach for Detecting Cardiac Abnormalities from ECG Signals. Physiological Measurement, Vol. 42, No. 10, pp. 105003. 6.       Pal, A., & Pandey, S. (2022). Heart Disease Prediction Using Deep Neural Networks and Transfer Learning Techniques. International Journal of Advanced Computer Science and Applications, Vol. 13, pp. 1–8.   7.       Rajasekharan, S. and Vijayalakshmi Pai, G. A. (2005). Neural Networks, Fuzzy Logic and Genetic Algorithms: Synthesis and Applications, Fifth Edition, PHI Learning.   8.       Sattar, S., Khan, A., & Rahman, F. (2024). Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets. IEEE Transactions on Biomedical Engineering, Vol. 71, No. 4, pp. 1289–1302.   9.       Seema Acharya. (2018). Data Analytics Using R, Wiley India Pvt. Ltd   10.    Shashikumar, S. P., Shah, A. J., Li, Q., Clifford, G. D., & Nemati, S. (2020). A Deep Learning Approach to Monitoring and Detecting Cardiac Arrhythmias Using ECG Signals. IEEE Journal of Biomedical and Health Informatics, Vol. 24, No. 2, pp. 437–446.