Key result
The proposed CR+Bi-LSTM model with a filter size of 11 achieved a classification accuracy of 95.34% for detecting cardiovascular diseases from 12-lead ECG signals, outperforming traditional LSTM and RNN models.
Why the study?
Early diagnosis of cardiovascular illnesses is critical for efficient therapy, and deep learning techniques using 12-lead ECG data can aid in multi-class disease classification.
A deep learning model combining convolution, residual connections, and Bi-LSTM achieved high accuracy in classifying 12-lead ECGs into five cardiovascular disease categories.
Answers are grounded in this paper and cite their sources.
DL ECG classification may support early CVD detection in limited settings; leaves open need for prospective validation before clinical use.
Cardiovascular disease (CVD) is a major contributor to death rates around the globe. Early diagnosis of cardiac illnesses is critical for efficient therapy, and an electrocardiogram (ECG) is vital for identification. Deep learning techniques have made significant advancements in the classification of ECG signals, achieving a level of accuracy comparable to that of cardiologists. In a medical situation, a cardiologist uses conventional 12-lead ECG data to determine a diagnosis. This work describes a multi-class classifier that can identify five distinct forms of cardiovascular illnesses: NORM, hypertrophy, myocardial infarction, ST-T abnormalities, and conduction disturbances. The model utilizes the abundant input from the usual 12-lead ECG data and acquires knowledge of patterns at the beat, and rhythm, and uses the dataset PTB-XL. Convolution with residual connection with Bi-LSTM performance at different filter sizes, when the filter size increases, we get a little more improvement in the model performance. The comparative study of the performance of 3 different classifiers LSTM, RNN, and Bi-LSTM, evaluates the performance of Accuracy, f1-score, recall, and precision. The performance at CRDM at filter size 11 accuracy, precision, F1-score &recall is 95.34%,91.54%,93.67% and 92.99%.
No takes yet. Share an insight, caveat, or question.
Prasanna et al. (2025) studied Cardiovascular disease (n=18,885). CR+Bi-LSTM model (Convolution and Residual Neural Networks with Bi-LSTM) vs. LSTM and RNN models was evaluated on Classification accuracy. The proposed CR+Bi-LSTM model with a filter size of 11 achieved a classification accuracy of 95.34% for detecting cardiovascular diseases from 12-lead ECG signals, outperforming traditional LSTM and RNN models.
Synapse has enriched 10 related papers. Consider them for comparative context: