Search

Introduction The benefit of implantable cardioverter‐defibrillator (ICD) implantation in patients with hemodynamically not tolerated ventricular tachycardia (VT) and midrange reduced to normal ejection fraction (LVEF >35%) is currently unclear. The purpose of this study was to investigate follow‐up after hemodynamically not tolerated VT in patients with LVEF >35%. In addition, we aimed to find possible predictive factors to identify who will benefit from ICD implantation. Methods In a retrospective single‐centre case series, all patients with hemodynamically not tolerated VT and LVEF >35% that underwent electrophysiological study (EPS) and/or radiofrequency VT ablation were included. Results Forty‐two patients (5 women, median age 68 years) with hemodynamically not tolerated VT and LVEF >35% underwent EPS. VT ablation was performed in thirty‐one patients, which was considered successful in twenty‐three patients. Nineteen patients had an ICD at discharge while 23 patients were discharged without an ICD. The severity of hemodynamic compromise, LVEF and ablation success played an important role in the decision‐making for ICD implantation. Six patients (14.3%) had recurrence of VT, all hemodynamically tolerated. Conclusions In this small case series, patients with hemodynamically not tolerated VT and LVEF >35% had a relatively low recurrence rate and all recurrences were nonfatal. Based on our results, we hypothesize that the severity of hemodynamic compromise, LVEF and ablation success might modify the risk for VA recurrence. A prospective study to determine the prognostic value of these factors in patients with hemodynamically not tolerated VT and LVEF >35% is necessary.

BACKGROUND The correct interpretation of the ECG is pivotal for the accurate diagnosis of many cardiac abnormalities, and conventional computerized interpretation has not been able to reach physician‐level accuracy in detecting (acute) cardiac abnormalities. This study aims to develop and validate a deep neural network for comprehensive automated ECG triage in daily practice. METHODS AND RESULTS We developed a 37‐layer convolutional residual deep neural network on a data set of free‐text physician‐annotated 12‐lead ECG s. The deep neural network was trained on a data set with 336.835 recordings from 142.040 patients and validated on an independent validation data set (n=984), annotated by a panel of 5 cardiologists electrophysiologists. The 12‐lead ECG s were acquired in all noncardiology departments of the University Medical Center Utrecht. The algorithm learned to classify these ECG s into the following 4 triage categories: normal, abnormal not acute, subacute, and acute. Discriminative performance is presented with overall and category‐specific concordance statistics, polytomous discrimination indexes, sensitivities, specificities, and positive and negative predictive values. The patients in the validation data set had a mean age of 60.4 years and 54.3% were men. The deep neural network showed excellent overall discrimination with an overall concordance statistic of 0.93 (95% CI , 0.92–0.95) and a polytomous discriminatory index of 0.83 (95% CI , 0.79–0.87). CONCLUSIONS This study demonstrates that an end‐to‐end deep neural network can be accurately trained on unstructured free‐text physician annotations and used to consistently triage 12‐lead ECG s. When further fine‐tuned with other clinical outcomes and externally validated in clinical practice, the demonstrated deep learning–based ECG interpretation can potentially improve time to treatment and decrease healthcare burden.