Arrhythmia constitutes a problem with the rate or rhythm of the heartbeat, and an early diagnosis is essential for the timely inception of successful treatment. We have jointly optimized the entire multi-stage arrhythmia classification scheme based on 12-lead surface ECGs that attains the accuracy performance level of professional cardiologists. The new approach is comprised of a three-step noise reduction stage, a novel feature extraction method and an optimal classification model with finely tuned hyperparameters. We carried out an exhaustive study comparing thousands of competing classification algorithms that were trained on our proprietary, large and expertly labeled dataset consisting of 12-lead ECGs from 40,258 patients with four arrhythmia classes: atrial fibrillation, general supraventricular tachycardia, sinus bradycardia and sinus rhythm including sinus irregularity rhythm. Our results show that the optimal approach consisted of Low Band Pass filter, Robust LOESS, Non Local Means smoothing, a proprietary feature extraction method based on percentiles of the empirical distribution of ratios of interval lengths and magnitudes of peaks and valleys, and Extreme Gradient Boosting Tree classifier, achieved an F1-Score of 0.988 on patients without additional cardiac conditions. The same noise reduction and feature extraction methods combined with Gradient Boosting Tree classifier achieved an F1-Score of 0.97 on patients with additional cardiac conditions. Our method achieved the highest classification accuracy (average 10-fold cross-validation F1-Score of 0.992) using an external validation data, MIT-BIH arrhythmia database. The proposed optimal multi-stage arrhythmia classification approach can dramatically benefit automatic ECG data analysis by providing cardiologist level accuracy and robust compatibility with various ECG data sources.
1 November 2017 in Circulation: Arrhythmia and Electrophysiology
Background: Circumferential pulmonary vein isolation (CPVI) alone or combined with adjuvant substrate modifications is unsatisfactory for atrial fibrillation (AF) control in nonparoxysmal AF patients. Ablation targeting the fibrotic areas after CPVI (STABLE-SR [Electrophysiological Substrate Ablation in the Left Atrium During Sinus Rhythm]) is a newly evolved substrate modification strategy. Methods and Results: In this multicenter, randomized clinical trial, 229 symptomatic nonparoxysmal AF patients were 1:1 randomized to STABLE-SR group (n=114) or conventional STEPWISE group (n=115). In the STABLE-SR group, after CPVI, cavotricuspid isthmus ablation and cardioversion to sinus rhythm, left atrial high-density mapping was performed. Areas with low-voltage and complex electrogram were further homogenized and eliminated, respectively. Dechanneling would be done if necessary. In the STEPWISE group, additional linear lesions and defragmentation were performed.The primary end point was freedom from documented atrial tachyarrhythmias for ≥30 s after a single ablation procedure without antiarrhythmic medications at 18 months. At 18 months, 74.0% of the patients in the STABLE-SR group and 71.5% in the STEPWISE group (hazard ratio, 0.78; 95% confidence interval, 0.47–1.29; P =0.325) achieved success according to intention-to-treat analysis. However, less procedure time (186.8±52.7 versus 210.5±48.0 minutes, P <0.001), reduced post-CPVI fluoroscopic time (11.0±7.8 versus 13.7±8.9 minutes, P =0.006), and shorter energy delivery time (60.1±25.1 versus 75.0±24.3 minutes, P <0.001) were observed in the STABLE-SR group compared with the STEPWISE group. Conclusions: STABLE-SR is a simplified, personalized, and effective ablation strategy in nonparoxysmal AF patients. More importantly, over 50% nonparoxysmal AF patients do not need further ablation beyond CPVI and therefore can avoid excessive ablation. Clinical Trial Registration: URL: http://www.clinicaltrials.gov . Unique identifier: NCT01761188.
Experience in procedures combining left atrial appendage (LAA) closure (LAAC) and catheter ablation (CA) was scarce in Chinese nonvalvular atrial fibrillation (AF) patients with high risks for stroke and bleeding. We aimed to investigate the efficacy and safety of the combination therapy with LAAC and AF CA in a single procedure based on the multicenter data and medium-term follow-up results. A total of 122 AF patients with a mean CHA2DS2-VASc score of 4.3 ± 1.4 and HAS-BLED score of 3.3 ± 1.0 were enrolled. The Watchman (n = 83) devices were implanted either before or after AF ablations in the same procedure, while the Amplatzer Cardiac Plug (ACP, n = 39) devices were implanted immediately after CA. AF recurrence and transesophageal echocardiography results were evaluated. All devices were successfully implanted and acute complete LAA occlusions were achieved in 115 (94.3%) of patients. Neither acute nor chronic peri-device leaks greater than 5 mm were detected. Oral anticoagulation was held in all patients but two with asymptomatic device-related thrombi, which were resolved after prolonged anticoagulation. AF-free success rate without antiarrhythmic drugs was 76.2% after a mean follow-up of 11.5 ± 6.8 months. No serious complications were observed during the follow-up. The combination therapy with LAAC and AF ablation in a single procedure was efficacious and safe in the Chinese symptomatic AF population with high risk for stroke and bleeding.
4 May 2018 in Journal of Cardiovascular Electrophysiology