[https://www.nature.com/articles/s41598-025-93906-5?utm\_source=rct\_congratemailt&utm\_medium=email&utm\_campaign=oa\_20250318&utm\_content=10.1038/s41598-025-93906-5](https://www.nature.com/articles/s41598-025-93906-5?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20250318&utm_content=10.1038/s41598-025-93906-5)The proposed self-attention artificial intelligence auto-encoder algorithmproved an effective cardiac arrhythmia classification strategy with a novel modified Kalman filterpre-processing. We achieved 24.00 SNRimp, 0.055 RMSE, 22.1 PRD% for -5db, 20.4 SNRimp, 0.0245RMSE, 12 PRD% whereas 14.05 SNRimp, 0.010 RMSE, and 7.25 PRD%, which reduces the ECG signalnoise during the pre-processing and improves the visibility of the QRS complex and R-R peaks of ECGwaveform. The extracted features were used in network of neurons to execute the classification forMIT-BIH arrhythmia databases using the newly developed self-attention autoencoder (AE) algorithm.The results are compared with existing models, revealing that the proposed system outperforms theclassification and prediction of cardiac arrhythmia with a precision of 99.91%, recall of 99.86%, andaccuracy of 99.71%. It is confirmed that self-attention-AE training results are promising, and it benefits
the diagnosis of ECGs for complex cardiac conditions to solve real-world heart problems.