Machine learning for prediction of ventricular arrhythmia episodes from intracardiac electrograms of automatic implantable cardioverter-defibrillators.

BACKGROUND: Despite effectiveness of the implantable cardioverter-defibrillator (ICD) in saving patients with life-threatening ventricular arrhythmias (VAs), the temporal occurrence of VA after ICD implantation is unpredictable. OBJECTIVE: The study aimed to apply machine learning (ML) to intracardiac electrograms (IEGMs) recorded by ICDs as a unique biomarker for predicting impending VAs. METHODS: The study included 13,516 patients who received Biotronik ICDs and enrolled in the CERTITUDE registry between January 1, 2010, and December 31, 2020. Database extraction included IEGMs from standard quarterly transmissions and VA event episodes. The processed IEGM data were pulled from device transmissions stored in a centralized Home Monitoring Service Center and reformatted into an analyzable format. Long-range (baseline or first scheduled remote recording), mid-range (scheduled remote recording every 90 days), or short-range predictions (IEGM within 5 seconds before the VA onset) were used to determine whether ML-processed IEGMs predicted impending VA events. Convolutional neural network classifiers using ResNet architecture were employed. RESULTS: Of 13,516 patients (male, 72%; age, 67.5 ± 11.9 years), 301,647 IEGM recordings were collected; 27,845 episodes of sustained ventricular tachycardia or ventricular fibrillation were observed in 4467 patients (33.0%). Neural networks based on convolutional neural networks using ResNet-like architectures on far-field IEGMs yielded an area under the curve of 0.83 with a 95% confidence interval of 0.79-0.87 in the short term, whereas the long-range and mid-range analyses had minimal predictive value for VA events. CONCLUSION: In this study, applying ML to ICD-acquired IEGMs predicted impending ventricular tachycardia or ventricular fibrillation events seconds before they occurred, whereas midterm to long-term predictions were not successful. This could have important implications for future device therapies.

Evaluation of cardiovascular implantable electronic device leads post implant: ElectroPhysiology Predictable And SuStainable Implementation Of National Registries (EP PASSION).

Post-market evaluation is important to ensure the ongoing safety and effectiveness of cardiovascular implantable electronic device (CIED) leads. The Twenty-First Century Cures Act and subsequent Food and Drug Administrative (FDA) Guidance provide an opportunity to leverage real-world data sources for this purpose. The past 4 years have seen the development of EP PASSION: a multi-stakeholder, collaborative effort between the FDA, CIED manufacturers, Heart Rhythm Society, and academics. Using real-world data, EP PASSION enables longitudinal evaluation of the long-term safety of CIED leads, addressing limitations of current approaches to generate evidence that informs regulatory, clinical, and manufacturer decision-making. This state of the art article describes the impetus for and launch of EP PASSION, the lessons learned, its current state, the current analytic approach, and the strengths and limitations of leveraging extant data sources for post-market lead evaluation. We also compare EP PASSION to traditional post-approval studies and describe possible future directions.

Utilization and programming of an automatic MRI recognition feature for cardiac rhythm management devices.

BACKGROUND: Cardiac implantable electronic devices (CIED)-ie, pacemakers, implantable cardioverter-defibrillators, and cardiac resynchronization therapy devices-have recently been designed to allow for patients to safely undergo magnetic resonance imaging (MRI) when specific programming is implemented. MRI AutoDetect is a feature that automatically switches CIED's programming into and out of an MR safe mode when exposed to an MRI environment. OBJECTIVE: The purpose was to analyze de-identified daily remote transmission data to characterize the utilization of the MRI AutoDetect feature. METHODS: Home Monitoring transmission data collected from MRI AutoDetect-capable devices were retrospectively analyzed to determine the workflow and usage in patients experiencing an MRI using the MRI AutoDetect feature. RESULTS: Among 48,756 capable systems, 2197 devices underwent an MRI using the MRI AutoDetect feature. In these 2197 devices, the MRI AutoDetect feature was used a total of 2806 times with an average MRI exposure of 40.83 minutes. The majority (88.9%) of MRI exposures occurred on the same day as the MRI AutoDetect programming. A same day post-MRI exposure follow-up device interrogation was performed 8.6% of the time. A device-related complaint occurred within 30 days of the MRI exposure in 0.25% of MRI exposures using MRI AutoDetect but with no adverse clinical outcome. CONCLUSION: As a result of automation in device programming, the MRI AutoDetect feature eliminated post-MRI device reprogramming in 91.4% of MRI exposures and, while less frequent, allowed for pre-MRI interrogations prior to the day of the MRI exposure-reducing resource utilization and creating workflow flexibility.

A novel spatiotemporal analysis of peri-ictal spiking to probe the relation of spikes and seizures in epilepsy.

The relation between epileptic spikes and seizures is an important but still unresolved question in epilepsy research. Preclinical and clinical studies have produced inconclusive results on the causality or even on the existence of such a relation. We set to investigate this relation taking in consideration seizure severity and spatial extent of spike rate. We developed a novel automated spike detection algorithm based on morphological filtering techniques and then tested the hypothesis that there is a pre-ictal increase and post-ictal decrease of the spatial extent of spike rate. Peri-ictal (around seizures) spikes were detected from intracranial EEG recordings in 5 patients with temporal lobe epilepsy. The 94 recorded seizures were classified into two classes, based on the percentage of brain sites having higher or lower rate of spikes in the pre-ictal compared to post-ictal periods, with a classification accuracy of 87.4%. This seizure classification showed that seizures with increased pre-ictal spike rate and spatial extent compared to the post-ictal period were mostly (83%) clinical seizures, whereas no such statistically significant (α = 0.05) increase was observed peri-ictally in 93% of sub-clinical seizures. These consistent across patients results show the existence of a causal relation between spikes and clinical seizures, and imply resetting of the preceding spiking process by clinical seizures.