1 June 2017 in Circulation: Cardiovascular Quality and Outcomes
Background—: Although right ventricular pacing can contribute to cardiomyopathy, the impact of complete atrioventricular block (cAVB) on heart failure (HF) development in pacemaker patients has not been well characterized. We evaluated the incidence and time course for developing HF after pacemaker implantation for cAVB. Methods and Results—: A MarketScan database identified patients undergoing dual-chamber pacemaker implantation from 2008 to 2014. Patients with cAVB were identified by an atrioventricular node ablation or diagnosis of third-degree AVB. Patients with ≥1 year of continuous MarketScan enrollment before and after implant and without a previous diagnosis of HF were dichotomized into those with cAVB and without AVB. The primary end point was new HF assessed over acute (0–6 months) and chronic (6 months to 4 years) phases post–pacemaker implantation. The cohort included 6994 cAVB patients and 14 208 patients without AVB, followed for 2.35 years (interquartile range, 1.62–3.39 years). After adjustment for baseline covariates, patients with cAVB experienced an increased risk of new-onset HF in the acute phase (hazard ratio, 1.62; 95% confidence interval, 1.48–1.79; P <0.001). Although the risk of HF remained elevated among those with cAVB in the chronic phase, the effect was attenuated (hazard ratio, 1.16; 95% confidence interval, 1.08–1.25; P <0.001). After pacemaker implantation, younger patients (≤55 years of age) and those with an antecedent history of atrial fibrillation experienced the highest risk of HF associated with cAVB. Conclusions—: Patients with a diagnosis of cAVB, and thus presumed to have a higher burden of right ventricular pacing, experienced an increased risk of new-onset HF after pacemaker implantation compared with those without AVB. Better tools are needed to identify patients at high risk of developing HF in the setting of right ventricular pacing and to determine whether these patients benefit from upfront biventricular pacing.
7 December 2021 in Journal of the American Heart Association
Background: Accurate detection of arrhythmic events in the intensive care units (ICU) is of paramount significance in providing timely care. However, traditional ICU monitors generate a high rate of false alarms causing alarm fatigue. In this work, we develop an algorithm to improve life threatening arrhythmia detection in the ICUs using a deep learning approach. Methods and Results: This study involves a total of 953 independent life‐threatening arrhythmia alarms generated from the ICU bedside monitors of 410 patients. Specifically, we used the ECG (4 channels), arterial blood pressure, and photoplethysmograph signals to accurately detect the onset and offset of various arrhythmias, without prior knowledge of the alarm type. We used a hybrid convolutional neural network based classifier that fuses traditional handcrafted features with features automatically learned using convolutional neural networks. Further, the proposed architecture remains flexible to be adapted to various arrhythmic conditions as well as multiple physiological signals. Our hybrid‐ convolutional neural network approach achieved superior performance compared with methods which only used convolutional neural network. We evaluated our algorithm using 5‐fold cross‐validation for 5 times and obtained an accuracy of 87.5%±0.5%, and a score of 81%±0.9%. Independent evaluation of our algorithm on the publicly available PhysioNet 2015 Challenge database resulted in overall classification accuracy and score of 93.9% and 84.3%, respectively, indicating its efficacy and generalizability. Conclusions: Our method accurately detects multiple arrhythmic conditions. Suitable translation of our algorithm may significantly improve the quality of care in ICUs by reducing the burden of false alarms.
3 March 2020 in Journal of the American Heart Association
23 September 2020 in Journal of Cardiovascular Electrophysiology
1 March 2021 in Heart Rhythm