Accuracy of the pacemaker-mediated tachycardia algorithm in Boston Scientific devices

T-Wave Oversensing with Contemporary Implantable Cardioverter-Defibrillators

BACKGROUND

Implantable cardioverter-defibrillators (ICDs) need to reliably detect ventricular tachycardia (VT) and ventricular fibrillation (VF) while avoiding T-wave oversensing (TWOS), which is associated with a risk of inappropriate therapies. The incidence of TWOS with endovascular ICDs appears to differ between manufacturers.

OBJECTIVES

We aimed to evaluate the incidence and clinical consequences of TWOS with contemporary Medtronic and Boston Scientific ICDs.

METHODS

Consecutive patients implanted with a recent Medtronic or Boston Scientific ICD and remotely monitored at three French centers were included. All transmitted EGMs labelled as VF, VT, non-sustained VT (NSVT), or ventricular oversensing (Medtronic) were screened for TWOS.

RESULTS

Among 7589 transmitted episodes from 674 patients with a Boston Scientific ICD, we did not identify a single case of TWOS. Among 16,790 transmitted episodes from 1733 patients with a Medtronic ICD, we identified 60 patients (3.4%) with at least one episode of TWOS. In 46 patients, TWOS was intermittent (NSVT episodes). In the remaining 14 patients, TWOS resulted in 60 sustained episodes (completed counters). No inappropriate therapies were delivered in 12 of these patients because no therapies were programmed (in monitor zones, 11 episodes) or because therapies were inhibited by the morphology discriminator (Wavelet, 19 episodes) or by the anti-TWOS algorithm (26 episodes). Two patients received inappropriate therapies due to TWOS (0.1% of patients with Medtronic ICDs).

CONCLUSION

On review of 24,379 transmitted episodes from 2407 patients with endovascular ICDs, we found no case of TWOS with Boston Scientific devices, whereas TWOS was not uncommon with Medtronic devices. However, the risk of inappropriate therapy with Medtronic ICDs was very low (0.1%) due to the often intermittent nature of this phenomenon, the morphology discriminator, and the anti-TWOS algorithm.

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.

Logic Analysis of Arrhythmia Triggered by Pacemaker Special Functions - An Educational Presentation

Dual-chamber pacemaker is a fully automatic pacemaker with the function of simulating human physiological pacing. It regulates pacing by programming different refractory periods and various special functions, which are closely related to arrhythmia. After in-depth understanding of these special functions, regular electrocardiogram follow-up analysis is required to provide individualized optimal program control and so is appropriate the administration of the pacemaker’s special functions to better provide optimal clinical guidance for patients with arrhythmia.

Cardiac implantable devices during exercise: Normal function and troubleshooting

Normal function and the most common problems that occur during pacemaker operation while performing physical exercise, are discussed. Physically active individuals with an implantable cardiac device, should be evaluated during exercise, because some conflicts issues may arise that are not detectable during routine, at rest, telemetry.

Pacemaker-mediated arrhythmias

Pacemakers can be directly involved in initiating or sustaining different forms of arrhythmia. These can cause symptoms such as dyspnea, palpitations, and decompensated heart failure. Early detection of these arrhythmias and optimal pacemaker programming is pivotal. The aim of this review article is to summarize the different types of pacemaker-mediated arrhythmias, their predisposing factors, and mechanisms of prevention or termination.

Unexpected and undesired side-effects of pacing algorithms during exercise

While the implantable pacemaker has initially been developed to treat symptomatic bradycardia, we demand of modern devices that they also function properly during exercise. In recent years, device manufacturers have implemented multiple proprietary algorithms which aim to improve pacemaker function by avoiding unnecessary right ventricular pacing, optimizing atrial refractory periods and diagnosing pacemaker mediated tachycardia. When activated, these algorithms may save the associated EGM into the device memory which enables later analysis by remote monitoring or device interrogation. In addition, the performance of an exercise-test while analyzing the EGM, enables the verification of proper algorithm function, the evaluation of residual symptoms and the optimization of specific parameters that vary as a function of heart rate. In this manuscript, we demonstrate how pacemaker algorithms may induce dropped P-waves during exercise in pacemaker dependent patients and loss of biventricular pacing in CRT patients.