Cardiovascular Disease Detection in ECG Images Using CNN-BiLSTM Model

Heart and blood vessel diseases are referred to as cardiovascular diseases (CVDs). Diagnosing heart disease is a difficult process that can identify a patient's heart condition and enable more effective treatment. The early and accurate detection of Cardiovascular Diseases plays a vital role in reducing morbidity and mortality rates. Cardiovascular disease (CVD) is commonly detected with electrocardiograms (ECGs). Electrocardiogram (ECG) images provide essential information about the electrical activity of the heart, offering valuable insights for diagnosing various cardiac conditions. CNN is frequently used in the medical field, and prompt identification of ECG abnormalities can be crucial to patient care. In recent years, CNN models have shown remarkable capabilities in medical image analysis. A Bidirectional Long Short-Term Memory (BiLSTM) is a kind of Recurrent Neural Network (RNN) architecture that enhances the capabilities of traditional LSTMs (Long Short-Term Memory networks) which handles input sequences going both forward and backward. This model proposes a novel CNN-BiLSTM method for ECG image-based cardiovascular disease detection. XGBoost proved to be the most accurate algorithm, with 92% accuracy.