Key result
A convolutional neural network achieves 75% accuracy in discriminating HBP and myocardial capture types.
Why the study?
Distinguishing between the three electrocardiographic capture types of His-bundle pacing can be challenging and time-consuming even for experts.
Does a convolutional neural network accurately discriminate between different electrocardiographic responses to His-bundle pacing in patients who have undergone HBP?
Observational
Does a convolutional neural network accurately discriminate between different electrocardiographic responses to His-bundle pacing in patients who have undergone HBP?
p-value: p=<.0001
A convolutional neural network can be trained to automate the discrimination between different His-bundle pacing ECG responses, providing proof of concept for AI-assisted ECG analysis to facilitate HBP implantation.
No takes yet. Share an insight, caveat, or question.
May aid HBP implantation via automated ECG analysis; leaves open prospective validation before clinical adoption.
Arnold et al. (2020) conducted an observational in His-bundle pacing. Convolutional neural network (CNN) was evaluated on Overall accuracy in discriminating HBP ECG responses (p=<.0001). A convolutional neural network achieved an overall accuracy of 75% in discriminating between selective His-bundle pacing, non-selective His-bundle pacing, and myocardium-only capture (P<.0001).
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: