A novel transformer-based ECG dimensionality reduction stacked auto-encoders for arrhythmia beat detection.

BACKGROUND: Electrocardiogram (ECG) is a powerful tool for studying cardiac activity and diagnosing various cardiovascular diseases, including arrhythmia. While machine learning and deep learning algorithms have been applied to ECG interpretation, there is still room for improvement. For instance, the commonly used Recurrent Neural Networks (RNNs), reply on its previous state to update and is therefore ineffective for parallel computing. RNN also struggles to efficiently address the issue of long-distance reliance. PURPOSE: To reduce computational complexity by dimensionality reduction of ECG signals we constructed a Stacked Auto-encoders model using Transformer for ECG-based arrhythmia detection. And overcome the challenges of long-term dependencies and limited parallelizability in traditional RNNs when applied to ECG signal processing. METHODS: In this paper, a Transformer-Based ECG Dimensionality Reduction Stacked Auto-encoders model is proposed for ECG-based arrhythmia detection. The transformer is used to encode ECG signals into a feature matrix, which is then dimensionally reduced using unsupervised greedy training through the four linear layers. This resulted in a low-dimensional representation of ECG features, which are subsequently classified using support vector machines (SVM) to minimize overfitting. RESULTS: The proposed method is benchmarked on the MIT-BIH Arrhythmia database. In the 10-fold cross validation of beat-based arrhythmia detection, the average accuracy, sensitivity, specificity and F1 score of the proposed method are 99.83%, 98.84%, 99.84% and 99.13%, respectively, for the record-based arrhythmia detection which refers to the approach where the training and testing sets use ECG data from independent recorded patients are 88.10%, 49.79%, 91.56% and 39.95%, respectively. CONCLUSIONS: Compared to other existing ECG-based arrhythmia detection methods, our proposed approach exhibits improved detection accuracy and stronger generalization for arrhythmia beats. Additionally, the use of the record-based data division method makes our approach more suitable for clinical practice.

Entropic nature of the interaction between promoter bound CRP mutants and RNA polymerase.

The interaction between CRP, T127L, S128A, and CRP and RNA polymerase bound to a 104 bp synthetic promoter were determined by ITC at 298 K and ranges from a deltaG(b) degrees = 1.4 +/- 0.8 kJ mol(-)(1) (cAMP-ligated S128A) to 4.5 +/- 0.3 kJ mol(-)(1) (cAMP-ligated double mutant CRP) with endothermicities that range from 4 +/- 3 kJ mol(-)(1) (cAMP-ligated CRP) to 47 +/- 8 kJ mol(-)(1) (cGMP-ligated T127L). The interaction is, thus, entropically driven, exhibits enthalpy-entropy compensation, and increases the binding affinity of the RNA polymerase to the promoter by factors ranging from 1.7 +/- 0.1 (cAMP-ligated S128A) to 6.1 +/- 0.1 (cAMP-ligated CRP). Although the binding affinities to the promoter alone, except for cAMP-ligated S128A, are the same as to a shorter 40 bp duplex containing the same CRP consensus binding site sequence (conDNA), the binding enthalpies of CRP/mutant to the promoter are lower by factors of 2-3 x than the corresponding binding enthalpies to conDNA. Small angle neutron scattering measurements on the DNA-CRP/mutant complexes in D(2)O/H(2)O solutions exhibit an increase in the Rg of the CRP/mutant component from 22 to 27-31 A that can be attributed to a conformational change in the N-terminal domain of CRP. The Rg = 27 A for the bound conDNA can be attributed to a slight unwinding of the DNA in solution that would also enhance the activation of transcription. The Rg = 53 +/- 3 A for the bound promoter is attributed to bending of the promoter in solution that can be responsible for the lower CRP/mutant-promoter binding endothermicities.