Trio of Rheumatic Mitral Stenosis, Right Posterior Septal Accessory Pathway and Atrial Flutter: A Case Report

A 57-year-old male presented with recurrent palpitations. He was diagnosed with rheumatic mitral stenosis, right posterior septal accessory pathway and atrial flutter. An electrophysiological study after percutaneous balloon mitral valvotomy showed that the palpitations were due to atrial flutter with right bundle branch aberrancy. The right posterior septal pathway was a bystander because it had higher refractory period than atrioventricular node.

TREMORS MIMICKING ATRIAL FLUTTER IN AN ELDERLY LADY

A 77 -year-old lady with history of hypertension and Parkinson`s disease was admitted with cough and fever and diagnosed as pneumonia. On second day of admission, she started having chest pain, initial ECG was interpreted as atrial flutter. When her ECG was reviewed by a cardiologist, ECG features were found to be consistent with artifacts due to tremors. A repeat 12 leads ECG clearly demonstrated normal sinus rhythm and the patient remained completely asymptomatic throughout the hospital stay. Tremor induced artifacts can be mistaken for arrhythmias. Correct diagnosis is important, in order to avoid inappropriate treatment and unnecessary interventions.

Remote magnetic navigation ablation of incisional atrial flutters in adolescent with a giant right atrium after surgical correction of tetralogy of Fallot and Ebstein's anomaly

We describe a clinical case of a 17-years-old adolescent with congenital heart disease after three open-heart surgery procedures for correction of tetralogy of Fallot and Ebstein's anomaly who presented with drug-resistant, persistent atrial flutter and giant right atrium (8.2 cm by transthoracic echocardiography). The successful ablation procedure of the two types of incisional atrial flutter was performed using remote magnetic navigation without any complications with 2.2 minutes of fluoroscopy. The patient remained free of any arrhythmias without antiarrhythmic drugs during 12 months of follow-up with a reduction of right atrium size (5.8 cm by transthoracic echocardiography).

Expert-enhanced machine learning for cardiac arrhythmia classification

We propose a new method for the classification task of distinguishing atrial fibrillation (AFib) from regular atrial tachycardias including atrial flutter (AFlu) based on a surface electrocardiogram (ECG). Recently, many approaches for an automatic classification of cardiac arrhythmia were proposed and to our knowledge none of them can distinguish between these two. We discuss reasons why deep learning may not yield satisfactory results for this task. We generate new and clinically interpretable features using mathematical optimization for subsequent use within a machine learning (ML) model. These features are generated from the same input data by solving an additional regression problem with complicated combinatorial substructures. The resultant can be seen as a novel machine learning model that incorporates expert knowledge on the pathophysiology of atrial flutter. Our approach achieves an unprecedented accuracy of 82.84% and an area under the receiver operating characteristic (ROC) curve of 0.9, which classifies as “excellent” according to the classification indicator of diagnostic tests. One additional advantage of our approach is the inherent interpretability of the classification results. Our features give insight into a possibly occurring multilevel atrioventricular blocking mechanism, which may improve treatment decisions beyond the classification itself. Our research ideally complements existing textbook cardiac arrhythmia classification methods, which cannot provide a classification for the important case of AFib↔AFlu. The main contribution is the successful use of a novel mathematical model for multilevel atrioventricular block and optimization-driven inverse simulation to enhance machine learning for classification of the arguably most difficult cases in cardiac arrhythmia. A tailored Branch-and-Bound algorithm was implemented for the domain knowledge part, while standard algorithms such as Adam could be used for training.