Towards eradication of inappropriate therapies for ICD lead failure by combining comprehensive remote monitoring and lead noise alerts

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.

2023 HRS/EHRA/APHRS/LAHRS expert consensus statement on practical management of the remote device clinic

Remote monitoring is beneficial for the management of patients with cardiovascular implantable electronic devices by impacting morbidity and mortality. With increasing numbers of patients using remote monitoring, keeping up with higher volume of remote monitoring transmissions creates challenges for device clinic staff. This international multidisciplinary document is intended to guide cardiac electrophysiologists, allied professionals, and hospital administrators in managing remote monitoring clinics. This includes guidance for remote monitoring clinic staffing, appropriate clinic workflows, patient education, and alert management. This expert consensus statement also addresses other topics such as communication of transmission results, use of third-party resources, manufacturer responsibilities, and programming concerns. The goal is to provide evidence-based recommendations impacting all aspects of remote monitoring services. Gaps in current knowledge and guidance for future research directions are also identified.

2023 HRS/EHRA/APHRS/LAHRS Expert Consensus Statement on Practical Management of the Remote Device Clinic

Remote monitoring is beneficial for the management of patients with cardiovascular implantable electronic devices by impacting morbidity and mortality. With increasing numbers of patients using remote monitoring, keeping up with higher volume of remote monitoring transmissions creates challenges for device clinic staff. This international multidisciplinary document is intended to guide cardiac electrophysiologists, allied professionals, and hospital administrators in managing remote monitoring clinics. This includes guidance for remote monitoring clinic staffing, appropriate clinic workflows, patient education, and alert management. This expert consensus statement also addresses other topics such as communication of transmission results, use of third-party resources, manufacturer responsibilities, and programming concerns. The goal is to provide evidence-based recommendations impacting all aspects of remote monitoring services. Gaps in current knowledge and guidance for future research directions are also identified.

2023 HRS/EHRA/APHRS/LAHRS Expert Consensus Statement on Practical Management of the Remote Device Clinic

Remote monitoring is beneficial for the management of patients with cardiovascular implantable electronic devices by impacting morbidity and mortality. With increasing numbers of patients using remote monitoring, keeping up with higher volume of remote monitoring transmissions creates challenges for device clinic staff. This international multidisciplinary document is intended to guide cardiac electrophysiologists, allied professionals, and hospital administrators in managing remote monitoring clinics. This includes guidance for remote monitoring clinic staffing, appropriate clinic workflows, patient education, and alert management. This expert consensus statement also addresses other topics such as communication of transmission results, use of third-party resources, manufacturer responsibilities, and programming concerns. The goal is to provide evidence-based recommendations impacting all aspects of remote monitoring services. Gaps in current knowledge and guidance for future research directions are also identified.

Indications and management of implantable cardioverter-defibrillator therapy in childhood hypertrophic cardiomyopathy

Sudden cardiac death is the most common mode of death during childhood and adolescence in hypertrophic cardiomyopathy, and identifying those individuals at highest risk is a major aspect of clinical care. The mainstay of preventative therapy is the implantable cardioverter-defibrillator, which has been shown to be effective at terminating malignant ventricular arrhythmias in children with hypertrophic cardiomyopathy but can be associated with substantial morbidity. Accurate identification of those children at highest risk who would benefit most from implantable cardioverter-defibrillator implantation while minimising the risk of complications is, therefore, essential. This position statement, on behalf of the Association for European Paediatric and Congenital Cardiology (AEPC), reviews the currently available data on established and proposed risk factors for sudden cardiac death in childhood-onset hypertrophic cardiomyopathy and current approaches for risk stratification in this population. It also provides guidance on identification of individuals at risk of sudden cardiac death and optimal management of implantable cardioverter-defibrillators in children and adolescents with hypertrophic cardiomyopathy.

Time course of oversensing and impedance changes in developing implantable cardioverter-defibrillator lead fracture

Background

Pace-sense conductors comprise a pacing coil to the tip electrode and cable to the ring-electrode. Implantable cardioverter-defibrillator (ICD) lead-monitoring diagnostics include pacing impedance (direct current resistance [DCR]) and measures of oversensing. How they change as fractures progress is unknown.

Objectives

To characterize the relationship between oversensing, impedance, and structural changes in ICD leads developing pace-sense conductor fractures.

Methods

We performed bending tests on 39 leads connected to ICD generators in an electrolyte bath with simulated electrograms. DCR was recorded every 3 minutes; electrograms were telemetered continuously. Twenty-two leads were tested to develop partial or complete fracture criteria confirmed by imaging, using DCR or DCR variability measured by standard deviation (σ_DCR). Results are reported for 17 other test leads.

Results

Initial oversensing occurred with partial pacing coil fracture vs complete ring cable fracture and correlated with bending-induced DCR peaks. These peaks were too small to be detected by clinical impedance measurements and were characterized by small increases in σ_DCR (≥0.5 Ω). Impedance threshold alerts occurred at complete pacing coil fracture but only later for ring cable fractures. The oversensing alert triggered before device-detected ventricular fibrillation more frequently than impedance alerts (94% vs 17%; P = .00002).

Conclusions

In conductor fracture, early oversensing corresponds to partial pacing coil fracture or complete ring cable fracture and correlates with transient bending-induced impedance increases, which are detected by impedance variability but too small to trigger clinical impedance alerts. This explains why clinical oversensing alerts provide more warning for device-detected ventricular fibrillation than impedance alerts and suggests how to improve impedance diagnostics based on short-term variability.

Clinical performance of implantable cardioverter-defibrillator lead monitoring diagnostics

BACKGROUND

Implantable cardioverter-defibrillator (ICD) lead monitoring diagnostic alerts facilitate the diagnosis of structural lead failure.

OBJECTIVE

The purpose of this study was to prospectively study the performance of Medtronic ICD lead monitoring alerts.

METHODS

A prespecified ancillary substudy, World-Wide Randomized Antibiotic Envelope Infection Prevention Trial, was conducted in patients with an ICD with all available alerts enabled. The investigators reported possible lead system events (LSEs), with or without an alert. An independent committee reviewed all data and classified events as lead failure, other LSE, or nonlead system events (NLEs).

RESULTS

In 4942 patients who were followed for 19.4 ± 8.7 months, there were 124 alerts (65 LSEs, 59 NLEs) and 19 LSEs without an alert. Lead monitoring alerts had 100% sensitivity for the 48 adjudicated lead failures (95% confidence interval 92.6%-100%) and for 10 events adjudicated as either lead failure or connection issue. The positive predictive value of alerts for lead failure was 38.7% (48 of 124). For 34 pace-sense lead failures, an alert that incorporated oversensing was more sensitive than the pacing impedance threshold alert (33 patients [97.1%] vs 9 patients [26.5%]; P < .0001). However, the sensitivity was only 13.6% for lead dislodgments or perforations. Inappropriate shocks occurred in 2 patients with pace-sense lead failure (5.9%). No patient had unnecessary lead replacement for any of the NLEs.

CONCLUSION

In this first real-world prospective study, lead monitoring alerts had 100% sensitivity for identifying lead failures. Although their positive predictive value was modest, no false-positive alerts resulted in an unnecessary lead replacement. For the diagnosis of pace-sense lead failure, an alert for oversensing was more sensitive than a pacing impedance threshold alert.

TRIAL REGISTRATION

ClinicalTrials.gov identifier: NCT02277990.

Interpreting device diagnostics for lead failure

Implantable cardioverter-defibrillators (ICDs) incorporate automated, lead-monitoring alerts (alerts) and other diagnostics to detect defibrillation lead failure (LF) and minimize its adverse clinical consequences. Partial conductor fractures cause oversensing, but pacing or high-voltage alerts for high impedance detect only complete conductor fracture. In both pacing and high-voltage insulation breaches, low-impedance alerts require complete breach with metal-to-metal contact. Oversensing alerts for pace-sense LF also require complete breach, but not metal-to metal contact. Electrograms (EGMs) from leads with confirmed fractures have characteristics findings. In insulation breach, however, oversensed EGMs reflect characteristics of the source signal. Oversensing alerts that operate on the sensing channel analyze R-R intervals for 2 patterns typical of LF but uncommon in other conditions: a rapidly increasing count of "nonphysiological" short intervals and rapid "nonsustained tachycardias." These alerts are sensitive but nonspecific. Alerts that compare sensing and shock channels define oversensing as sensed events that do not correlate temporally with EGMs on the shock channel. Their performance depends on implementation. Specific advantages and limitations are reviewed. Most ICDs measure impedance using subthreshold pulses. Patterns in impedance trends provide diagnostic information, whether or not an alert is triggered. Gradual increases in impedance do not indicate structural LF, but they may cause failed defibrillation if shock impedance is high enough. Because impedance-threshold alerts are insensitive, normal impedance trends never exclude LF, but an abrupt increase that triggers an alert almost always indicates a header connection issue or LF. Methods for discriminating connection issues from LF are reviewed.

Remote Monitoring of Heart Failure in Patients with Implantable Cardioverter-Defibrillators: Current Status and Future Needs

The management of heart failure remains challenging despite evidence-based medical and pharmacological advances, especially in the ambulatory setting. There is an urgent need to develop strategies to reduce hospitalizations and readmission rates due to heart failure. Frequent monitoring of high-risk patients is imperative, and with the development of wireless and remote technology, frequent monitoring is now possible via remote monitoring. Nowadays, remote management of patients with cardiac implantable electronic devices is being increasingly adopted and integrated into clinical practice. Several clinical trials studied the impact of remote monitoring on clinical outcomes in patients with implantable cardioverter-defibrillators (ICDs) and cardiac resynchronization defibrillators (CRT-Ds). This point of view will focus on the remote monitoring of ICDs and CRT-Ds in patients with heart failure and discusses whether remote monitoring can be used as a potential instrument for the early identification of patients at risk of worsening heart failure.

Impedance in the Diagnosis of Lead Malfunction

Impedance is the ratio of voltage to current in an electrical circuit. Cardiovascular implantable electronic devices measure impedance to assess the structural integrity electrical performance of leads, typically using subthreshold pulses. We review determinants of impedance, how it is measured, variation in clinically measured pacing and high-voltage impedance and impedance trends as a diagnostic for lead failure and lead-device connection problems. We consider the differential diagnosis of abnormal impedance and the approach to the challenging problem of a single, abnormal impedance measurement. Present impedance provides a specific but insensitive diagnostic. For pacing circuits, we review the complementary roles of impedance and more sensitive oversensing diagnostics. Shock circuits lack a sensitive diagnostic. This deficiency is particularly important for insulation breaches, which may go undetected and present with short circuits during therapeutic shocks. We consider new methods for measuring impedance that may increase sensitivity for insulation breaches.

Optimal Strategies to Reduce Inappropriate Implantable Cardioverter-defibrillator Shocks

Since the widespread implementation of implantable cardioverter-defibrillators (ICDs), their effectiveness in various situations has become well-established. However, despite many advances in both the technology and its utilization, inappropriate therapy remains a risk. Here, we review ICD shocks, their effect on outcomes, and current methods to reduce inappropriate therapy, finding overall that inappropriate ICD shocks are common and associated with adverse outcomes. However, strategies do exist to minimize inappropriate shock rates including device selection and programming, medication, catheter ablation, and remote monitoring. Overall, ICDs are useful in reducing the risk of sudden cardiac death, but many patients with an ICD will receive an inappropriate shock. Understanding strategies to prevent inappropriate shocks is crucial to improving the care of patients with ICDs.

105 Inappropriate ICD Shocks in a Patient with Dilated Cardiomyopathy and Broca’s Aphasia

With a growing number of ICD recipients, device complications are seen more frequently in the clinical setting and outpatient departments. Among the most severe are ICD infections and inappropriate therapies caused by oversensing of atrial tachycardias or lead fracture. We report on a 76-year-old female patient with dilative cardiomyopathy and Broca's aphasia after stroke, who experienced 105 consecutive inappropriate ICD shocks due to cluster missensing of her fractured ICD lead. The diagnosis was complicated and delayed by patient's aphasia emphasizing the need for intensified remote monitoring along with regular in-person visits, especially in people with intellectual or communication disabilities.

Increasing Role of Remote Monitoring of Cardiac Resynchronization Therapy Devices in Improving Outcomes

Remote monitoring has become an essential component of the care of patients with a cardiac implantable electronic device, including those undergoing cardiac resynchronization therapy-defibrillator implantations. It allows for earlier detection of battery- and lead-related issue, atrial and ventricular arrhythmias, and may facilitate early identification of patients at risk for developing an exacerbation of heart failure. The data for the clinical utility of remote monitoring have been mixed. Additional studies are ongoing to determine how best to detect heart failure in these patients and how best to manage these patients based on the information.

Inappropriate disabling of an ICD noise-detection algorithm in pacemaker-dependent patients

SecureSense is an implantable cardioverter defibrillator algorithm that differentiates lead-related oversensing from ventricular tachycardia/ventricular fibrillation by continuous comparison between the near-field (NF) and the far-field (FF) electrogram. If lead noise is identified, inappropriate therapy is withheld. Undersensing on the FF channel could result in inappropriate inhibition of life-saving therapy. Thus, the device automatically switches SecureSense to passive mode if undersensing on the FF channel is suspected. We report here the first cases of inappropriate automatic SecureSense deactivation due to misdiagnosed FF undersensing in pacemaker-dependent patients. Physicians should be aware that SecureSense does not withhold an inappropriate therapy for sustained oversensing in pacemaker-dependent patients.