Real-Time Cardiac Abnormality Monitoring and Nursing for Patient Using Electrocardiographic Signals.

Abstract

Introduction: Cardiovascular disease nursing is a critical clinical application that necessitates real-time monitoring models. Previous models required the use of multi-lead signals and could not be customized as needed. Traditional methods relied on manually designed supervised algorithms, based on empirical experience, to identify waveform abnormalities and classify diseases, and were incapable of monitoring and alerting abnormalities in individual waveforms.

Methods: This research reconstructed the vector model for arbitrary leads using the phase space-time-delay method, enabling the model to arbitrarily combine signals as needed while possessing adaptive denoising capabilities. After employing automatically constructed machine learning algorithms and designing for rapid convergence, the model can identify abnormalities in individual waveforms and classify diseases, as well as detect and alert on abnormal waveforms.

Result: Effective noise elimination was achieved, obtaining a higher degree of loss function fitting. After utilizing the algorithm in Section 3.1 to remove noise, the signal-to-noise ratio increased by 8.6%. A clipping algorithm was employed to identify waveforms significantly affected by external factors. Subsequently, a network model established by a generative algorithm was utilized. The accuracy for healthy patients reached 99.2%, while the accuracy for APB was 100%, for LBBB 99.32%, for RBBB 99.1%, and for P-wave peak 98.1%.

Conclusion: By utilizing a three-dimensional model, detailed variations in electrocardiogram signals associated with different diseases can be observed. The clipping algorithm is effective in identifying perturbed and damaged waveforms. Automated neural networks can classify diseases and patient identities to facilitate precision nursing.