Seth, Milan

IntroductionAdjudication of thousands of implantable cardioverter defibrillator (ICD)‐treated arrhythmia episodes is labor intensive and, as a result, is most often left undone. The objective of this study was to evaluate an automatic classification algorithm for adjudication of ICD‐treated arrhythmia episodes.MethodsThe algorithm uses a machine learning algorithm and was developed using 776 arrhythmia episodes. The algorithm was validated on 131 dual‐chamber ICD shock episodes from 127 patients adjudicated by seven electrophysiologists (EPs). Episodes were classified by panel consensus as ventricular tachycardia/ventricular fibrillation (VT/VF) or non‐VT/VF, with the resulting classifications used as the reference. Subsequently, each episode electrogram (EGM) data was randomly assigned to three EPs without the atrial lead information, and to three EPs with the atrial lead information. Those episodes were also classified by the automatic algorithm with and without atrial information. Agreement with the reference was compared between the three EPs consensus group and the algorithm.ResultsThe overall agreement with the reference was similar between three‐EP consensus and the algorithm for both with atrial EGM (94% vs 95%, P = 0.87) and without atrial EGM (90% vs 91%, P = 0.91). The odds of accurate adjudication, after adjusting for covariates, did not significantly differ between the algorithm and EP consensus (odds ratio 1.02, 95% confidence interval: 0.97–1.06).ConclusionsThis algorithm performs at a level comparable to an EP panel in the adjudication of arrhythmia episodes treated by both dual‐ and single‐chamber ICDs. This type of algorithm has the potential for automated analysis of clinical ICD episodes, and adjudication of EGMs for research studies and quality analyses.

Background— Outcome data for patients receiving implantable cardioverter-defibrillator (ICD) and cardiac resynchronization therapy–defibrillator (CRT-D) devices treated outside of clinical trials are lacking. No clinical trial has evaluated mortality after device implantation or after shock therapy in large numbers of patients with implanted devices that regularly transmit device data over a network. Methods and Results— Survival status in patients implanted with ICD and CRT devices across the United States from a single manufacturer was assessed. Outcomes were compared between patients followed in device clinic settings and those who regularly transmit remote data collected from the device an average of 4 times monthly. Shock delivery and electrogram analysis could be ascertained from patients followed on the network, enabling survival after ICD shock to be evaluated. One- and 5-year survival rates in 185 778 patients after ICD implantation were 92% and 68% and were 88% and 54% for CRT-D device recipients. In 8228 patients implanted with CRT-only devices, survival was 82% and 48% at 1 and 5 years, respectively. For the 69 556 ICD and CRT-D patients receiving remote follow-up on the network, 1- and 5-year survival rates were higher compared with those in the 116 222 patients who received device follow-up in device clinics only (50% reduction; P <0.0001). There were no differences between patients followed on or off the remote network for the characteristics of age, gender, implanted device year or type, and economic or educational status. Shock therapy was associated with subsequent mortality risk for both ICD and CRT-D recipients. Conclusions— Survival after ICD and CRT-D implantation in patients treated in naturalistic practice compares favorably with survival rates observed in clinical trials. Remote follow-up of device data is associated with excellent survival, but arrhythmias that result in device therapy in this population are associated with a higher mortality risk compared with patients who do not require shock therapy.