Key result
Personalized LSTM networks outperform generalized models in deriving vectorcardiography and diagnostic parameters from 12-lead ECGs.
Why the study?
VCG provides valuable diagnostic information complementing standard 12-lead ECG, but clinical use is limited by extra hardware and electrodes, creating a need to derive VCG directly from ECG.
Do personalized LSTM neural networks improve the accuracy of deriving VCG from 12-lead ECG compared to generalized networks?
Do personalized LSTM neural networks improve the accuracy of deriving VCG from 12-lead ECG compared to generalized networks?
Personalized LSTM neural networks outperform generalized models in deriving vectorcardiograms from standard 12-lead ECGs, potentially enhancing diagnostic accuracy without additional hardware.
Vectorcardiography (VCG) is a valuable diagnostic tool that complements the standard 12-lead ECG by offering additional spatiotemporal information to clinicians. However, due to the need for additional measurement hardware and too many electrodes in a clinical scenario if performed along with a standard 12-lead, there is a need to find methods to derive the VCG from the ECG. We have evaluated the use of Long Short-term Memory (LSTM) neural networks to learn the transformation from 12-lead ECG to VCG that is applicable across subjects and for each subject. We refer to these networks as generalized and personalized, respectively. We calculated the Root Mean Square Error (RMSE), R2, and Pearson correlation coefficient to compare waveforms of derived and actual VCG. We also extracted and compared diagnostic parameters from VCG, namely the QRS-loop magnitude, T-loop magnitude, and QRS-T spatial angle, from actual and derived VCGs using the Pearson correlation coefficient and Bland Altman limits of agreement. The personalized models performed better than generalized models in waveform comparisons and in the error of extracted diagnostic parameters from VCG waveforms. The use of personalized transformations for the derivation of VCG from standard 12-lead has the potential to improve and augment the diagnostic yield and accuracy of a standard 12-lead interpretation.
No takes yet. Share an insight, caveat, or question.
Kumar et al. (2023) studied ECG to VCG derivation. Personalized LSTM neural networks vs. Generalized LSTM neural networks was evaluated on Waveform comparison (RMSE, R2, Pearson correlation) and diagnostic parameters (QRS-loop magnitude, T-loop magnitude, QRS-T spatial angle). Personalized LSTM neural networks performed better than generalized models in deriving vectorcardiography from 12-lead ECG waveforms and extracting diagnostic parameters.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: