Mechanisms of human atrial fibrillation: Lessons learned from 20 years of atrial fibrillation surgery

Computer Aided Diagnosis for atrial fibrillation based on new artificial adaptive systems

BACKGROUND AND OBJECTIVE

Atrial fibrillation (AF) is the most common cardiac arrhythmia in clinical practice, having been recognized as a true cardiovascular epidemic. In this paper, a new methodology for Computer Aided Diagnosis of AF based on a special kind of artificial adaptive systems has been developed.

METHODS

Following the extraction of data from the PhysioNet repository, a new dataset composed of the R/R distances of 73 patients was created. To avoid redundancy, the training set was created by randomly selecting 50% of the subjects from the entire sample, thus making a choice by patient and not by record. The remaining 50% of subjects were randomly split by records in testing and prediction sets. The original ECG data has been transformed according to the following four orders of abstraction: a) sequence of R/R intervals; b) composition of ECG data into a moving window; c) training of different machine learning systems to abstract the function governing the AF; d) fuzzy transformation of Machine learning estimations. In this paper, in parallel with the classic method of windowing, we propose a variant based on a system of progressive moving averages.

RESULTS

The best performing machine learning, Supervised Contractive Map (SVCm), reached an overall mean accuracy of 95%. SVCm is a new deep neural network based on a different principle than the usual descending gradient. The minimization of the error occurs by means of decomposition into contracted sine functions.

CONCLUSIONS

In this research, atrial fibrillation is considered from a completely different point of view than classical methods. It is seen as the stable process, i.e. the function, that manages the irregularity of the irregularities of the R/R intervals. The idea, therefore, is to abstract from mere physiology to investigate fibrillation as a mathematical object that handles irregularities. The attained results seem to open new perspectives for the use of potent artificial adaptive systems for the automatic detection of atrial fibrillation, with accuracy rates extremely promising for real world applications.

Diagnosis and management of atrial fibrillation: an overview

Atrial fibrillation (AF) has been defined as the new cardiovascular "epidemic". Its prevalence is rising in developed countries, and the associated social and economic costs are high. In the last few years, there has been an increasing interest in understanding the mechanisms of AF and its management. New pharmacotherapies together with novel techniques for surgical and catheter treatment of AF have been developed, allowing the maintenance of sinus rhythm and the alleviation of symptoms in a large number of patients with AF. However, there are still some challenges that need to be addressed. This article gives an overview of the current state of the art on novel techniques for diagnosis and management of AF.

Surgical options for treatment of atrial fibrillation

If we want to improve the outcomes, increase the success and reduce the complication rate of existing treatment strategies in concomitant and stand-alone atrial fibrillation (AF) procedures, we will have to increase our understanding of the pathophysiology, and of the disease, the limitations of current energy sources and ablation catheters, the different possible lesion sets, as well as improve communication between the electrophysiologist and cardiac surgeon. The technical limitations of percutaneous endocardial ablation procedures and the empirical techniques in surgical AF procedures necessitate new and innovative approaches. Surgeons should aim to improve the quality of the lesion set and minimize the invasiveness of existing techniques. The Maze procedure remains the basis upon which most of the more limited concomitant ablation procedures are and will be designed, but in stand-alone patients, recent progress has directed us towards either a single-step or sequential combined percutaneous endocardial procedure with a thoracoscopic epicardial procedure on the beating heart. A dedicated team of electrophysiologists and cardiothoracic surgeons can now work together to perform AF procedures. This can guide us to determine if there is an additional value of limiting the lesion set of the Maze procedure in concomitant surgery, and of an epicardial access in the treatment of stand-alone AF on the beating heart. If so, we will better understand which energy sources, lesion sets and surgical techniques are able to give us a three-dimensional knowledge and a three-dimensional treatment of AF. As a result, we can expect to obtain a higher single procedure long-term success rate with an acceptable low complication rate.