A prediction model for ventricular tachycardia events using 24h ambulatory ECG

Abstract

Abstract Background Ventricular tachycardia (VT) is a potentially lethal condition that occurs intermittently. The aim of this study was to derive a risk prediction model for VT episodes detected on ≤30 day mobile cardiac telemetry using a 24 hour ambulatory ECG recording. Methods We included patients who were monitored for 2–30 full days in the USA using a full-disclosure mobile cardiac telemetry device in 2017. Patients with a VT episode ≥10 beats duration (VT≥10 beats) on the first full recording day were excluded. Arrhythmias were algorithmically detected and manually verified. A LASSO model was derived for the outcome of a VT≥10 beats detected on days 2–30. Potential predictors included age, sex, and ECG data from the first 24h: heart rate (max, min and mean), premature atrial and ventricular complexes occurring as singles, couplets, triplets, and runs ≥4 beats as well as the fastest rate for each event. The population was split into equal random training and testing samples. Results In a population of 19,789 patients (mean age 65.3, 43.4% men), and during a median recording time of 18 days there were 1,511 patients with at least one VT≥10 beats. The LASSO model had good discrimination in the testing sample, ROC-statistic 0.7586, 95% CI 0.7398–0.7774 (Figure 1a). A model excluding age and gender had similar discrimination (ROC 0.7528, 95% CI 0.7339–0.7717). In the testing sample the model was well calibrated (Figure 1b). In the top quintile more than one in five patients had a VT≥10 beats, enough to warrant extended monitoring. Conclusion A risk score based on variables easily derived from a standard 24h ECG can be used to predict high risk of VT episodes ≥10 beats within 30 days. In the top quintile VT events ≥10 beats were ten times more common than in the bottom quintile. Funding Acknowledgement Type of funding sources: Foundation. Main funding source(s): Hjärt-LungfondenSwedish Society for Medical Research