Artificial intelligence for detection of ventricular oversensing: Machine learning approaches for noise detection within nonsustained ventricular tachycardia episodes remotely transmitted by pacemakers and implantable cardioverter-defibrillators

BACKGROUND

Pacemakers (PMs) and implantable cardioverter-defibrillators (ICDs) increasingly automatically record and remotely transmit nonsustained ventricular tachycardia (NSVT) episodes, which may reveal ventricular oversensing.

OBJECTIVES

We aimed to develop and validate a machine learning algorithm that accurately classifies NSVT episodes transmitted by PMs and ICDs in order to lighten health care workload burden and improve patient safety.

METHODS

PMs or ICDs (Boston Scientific, St Paul, MN) from 4 French hospitals with ≥1 transmitted NSVT episode were split into 3 subgroups: training set, validation set, and test set. Each NSVT episode was labeled as either physiological or nonphysiological. Four machine learning algorithms-2DTF-CNN, 2D-DenseNet, 2DTF-VGG, and 1D-AgResNet-were developed using training and validation data sets. Accuracies of the classifiers were compared with an analysis of the remote monitoring team of the Bordeaux University Hospital using F2 scores (favoring sensitivity over predictive positive value) using an independent test set.

RESULTS

A total of 807 devices transmitted 10,471 NSVT recordings (82% ICD; 18% PM), of which 87 devices (10.8%) transmitted 544 NSVT recordings with nonphysiological signals. The classification by the remote monitoring team resulted in an F2 score of 0.932 (sensitivity 95%; specificity 99%) The 4 machine learning algorithms showed high and comparable F2 scores (2DTF-CNN: 0.914; 2D-DenseNet: 0.906; 2DTF-VGG: 0.863; 1D-AgResNet: 0.791), and only 1D-AgResNet had significantly different labeling from that of the remote monitoring team.

CONCLUSION

Machine learning algorithms were accurate in detecting nonphysiological signals within electrograms transmitted by PMs and ICDs. An artificial intelligence approach may render remote monitoring less resourceful and improve patient safety.

Effect of Segmentation Uncertainty on the ECGI Inverse Problem Solution and Source Localization

Electrocardiographic Imaging (ECGI) is a promising tool to non-invasively map the electrical activity of the heart using body surface potentials (BSPs) and the patient specific anatomical data. One of the first steps of ECGI is the segmentation of the heart and torso geometries. In the clinical practice, the segmentation procedure is not fully-automated yet and is in consequence operator-dependent. We expect that the inter-operator variation in cardiac segmentation would influence the ECGI solution. This effect remains however non quantified. In the present work, we study the effect of segmentation variability on the ECGI estimation of the cardiac activity with 262 shape models generated from fifteen different segmentations. Therefore, we designed two test cases: with and without shape model uncertainty. Moreover, we used four cases for ectopic ventricular excitation and compared the ECGI results in terms of reconstructed activation times and excitation origins. The preliminary results indicate that a small variation of the activation maps can be observed with a model uncertainty but no significant effect on the source localization is observed.

Prediction of Clinical Deep Brain Stimulation Target for Essential Tremor From 1.5 Tesla MRI Anatomical Landmarks

Background: Deep brain stimulation is an efficacious treatment for refractory essential tremor, though targeting the intra-thalamic nuclei remains challenging. Objectives: We sought to develop an inverse approach to retrieve the position of the leads in a cohort of patients operated on with optimal clinical outcomes from anatomical landmarks identifiable by 1.5 Tesla magnetic resonance imaging. Methods: The learning database included clinical outcomes and post-operative imaging from which the coordinates of the active contacts and those of anatomical landmarks were extracted. We used machine learning regression methods to build three different prediction models. External validation was performed according to a leave-one-out cross-validation. Results: Fifteen patients (29 leads) were included, with a median tremor improvement of 72% on the Fahn-Tolosa-Marin scale. Kernel ridge regression, deep neural networks, and support vector regression (SVR) were used. SVR gave the best results with a mean error of 1.33 ± 1.64 mm between the predicted target and the active contact position. Conclusion: We report an original method for the targeting in deep brain stimulation for essential tremor based on patients' radio-anatomical features. This approach will be tested in a prospective clinical trial.