Log in to MyACC
Predicting Ventricular Arrhythmias Using Real-Time Remote Monitoring
Quick Takes
- Real-time remote monitoring physiological data in the 30 days before device therapy may be utilized to predict malignant ventricular arrhythmias treated with ICD shocks or ATP.
- Both conventional logistic regression and neural network modeling demonstrated high correct classification because of excellent negative predictive value, with superior sensitivity and positive prediction in neural networks.
- Neural network modeling complemented and expanded upon variables by identifying time-dependent changes in atrial lead-tip impedance, mean atrial or ventricular heart rate, and patient activity as important predictors of appropriate device therapies.
Study Questions:
Does daily remote monitoring data collected by implantable-cardioverter defibrillator (ICD) and cardiac resynchronization therapy with defibrillator (CRT-D) devices predict appropriate therapies for clinically significant ventricular fibrillation (VF) or ventricular tachycardia (VT)?
Methods:
The investigators conducted a post hoc analysis of IMPACT (Randomized trial of atrial arrhythmia monitoring to guide anticoagulation in patients with implanted defibrillator and cardiac resynchronization devices), a multicenter, randomized, controlled trial of 2,718 patients evaluating atrial tachyarrhythmias and anticoagulation for patients with heart failure and ICD or CRT-D devices. All device therapies were adjudicated as either appropriate (to treat VT or VF) or inappropriate (all others). Remote monitoring data in the 30 days before device therapy were utilized to develop separate multivariable logistic regression and neural network models to predict appropriate device therapies.
Results:
A total of 59,807 device transmissions were available for 2,413 patients (age 64 ± 11 years, 26% women, 64% ICD). Appropriate device therapies (141 shocks, 10 antitachycardia pacing [ATP]) were delivered to 151 patients. Logistic regression identified shock lead impedance and ventricular ectopy as significantly associated with increased risk of appropriate device therapy (sensitivity 39%, specificity 91%, area under the curve [AUC]: 0.72). Neural network modeling yielded significantly better (p < 0.01 for comparison) predictive performance (sensitivity 54%, specificity 96%, AUC: 0.90), and also identified patterns of change in atrial lead impedance, mean heart rate, and patient activity as predictors of appropriate therapies.
Conclusions:
The authors report that daily remote monitoring data may be utilized to predict malignant ventricular arrhythmias in the 30 days before device therapies.
Perspective:
This study reports that real-time remote monitoring physiological data in the 30 days before device therapy may be utilized to predict malignant ventricular arrhythmias treated with ICD shocks or ATP. Of note, both conventional logistic regression and neural network modeling demonstrated high correct classification because of excellent negative predictive value, with superior sensitivity and positive prediction in neural networks. Furthermore, neural network modeling complemented and expanded upon variables of interest by identifying time-dependent changes in atrial lead-tip impedance, mean atrial or ventricular heart rate, and patient activity as important predictors of appropriate device therapies. Additional studies and risk models combining conventional and neural network approaches are indicated to assess complex and nonlinear interactions between remote monitoring data and potentially enhance the dynamic risk stratification for VT and VF.
Clinical Topics: Anticoagulation Management, Arrhythmias and Clinical EP, Heart Failure and Cardiomyopathies, Prevention, Implantable Devices, SCD/Ventricular Arrhythmias, Atrial Fibrillation/Supraventricular Arrhythmias, Acute Heart Failure
Keywords: Anticoagulants, Arrhythmias, Cardiac, Cardiac Resynchronization Therapy Devices, Defibrillators, Defibrillators, Implantable, Electric Impedance, Heart Failure, Heart Rate, Monitoring, Physiologic, Predictive Value of Tests, Secondary Prevention, Shock, Tachycardia, Ventricular, Ventricular Fibrillation
< Back to Listings
