Xiao, Peilin

AbstractIntroductionThe efficacy of cardiac resynchronization therapy (CRT) has been widely studied in the medical literature; however, about 30% of candidates fail to respond to this treatment strategy. Smart computational approaches based on clinical data can help expose hidden patterns useful for identifying CRT responders.MethodsWe retrospectively analyzed the electronic health records of 1664 patients who underwent CRT procedures from January 1, 2002 to December 31, 2017. An ensemble of ensemble (EoE) machine learning (ML) system composed of a supervised and an unsupervised ML layers was developed to generate a prediction model for CRT response.ResultsWe compared the performance of EoE against traditional ML methods and the state‐of‐the‐art convolutional neural network (CNN) model trained on raw electrocardiographic (ECG) waveforms. We observed that the models exhibited improvement in performance as more features were incrementally used for training. Using the most comprehensive set of predictors, the performance of the EoE model in terms of the area under the receiver operating characteristic curve and F1‐score were 0.76 and 0.73, respectively. Direct application of the CNN model on the raw ECG waveforms did not generate promising results.ConclusionThe proposed CRT risk calculator effectively discriminates which heart failure (HF) patient is likely to respond to CRT significantly better than using clinical guidelines and traditional ML methods, thus suggesting that the tool can enhanced care management of HF patients by helping to identify high‐risk patients.

Background: Percutaneous stellate ganglion blockade (SGB) has been used for drug-refractory electrical storm due to ventricular arrhythmia (VA); however, the effects and long-term outcomes have not been well studied. Methods: This study included 30 consecutive patients who had drug-refractory electrical storm and underwent percutaneous SGB between October 1, 2013, and March 31, 2018. Bupivacaine, alone or combined with lidocaine, was injected into the neck with good local anesthetic spread in the vicinity of the left stellate ganglion (n=15) or both stellate ganglia (n=15). Data were collected for patient clinical characteristics, immediate and long-term outcomes, and procedure-related complications. Results: Clinical characteristics included age, 58±14 years; men, 73.3%; and left ventricular ejection fraction, 34±16%. At 24 hours, 60% of patients were free of VA. Patients whose VA was controlled had a lower hospital mortality rate than patients whose VA continued (5.6% versus 50.0%; P =0.009). Implantable cardioverter-defibrillator interrogation showed a significant 92% reduction in VA episodes from 26±41 to 2±4 in the 72 hours after SGB ( P <0.001). Patients who died during the same hospitalization (n=7) were more likely to have ischemic cardiomyopathy (100% versus 43.5%; P =0.03) and recurrent VA within 24 hours (85.7% versus 26.1%; P =0.009). There were no procedure-related major complications. Conclusions: SGB effectively attenuated electrical storm in more than half of patients without procedure-related complications. Percutaneous SGB may be considered for stabilizing ventricular rhythm in patients for whom other therapies have failed.