A new statistic has been developed to quantify the amount of regularity in data. This statistic, ApEn (approximate entropy), appears to have potential application throughout medicine, notably in electrocardiogram and related heart rate data analyses and in the analysis of endocrine hormone release pulsatility. The focus of this article is ApEn. We commence with a simple example of what we are trying to discern. We then discuss exact regularity statistics and practical difficulties of using them in data analysis. The mathematic formula development for ApEn concludes the Solution section. We next discuss the two key input requirements, followed by an account of a pilot study successfully applying ApEn to neonatal heart rate analysis. We conclude with the important topic of ApEn as a relative (not absolute) measure, potential applications, and some caveats about appropriate usage of ApEn. Appendix A provides example ApEn and entropy computations to develop intuition about these measures. Appendix B contains a Fortran program for computing ApEn. This article can be read from at least three viewpoints. The practitioner who wishes to use a "black box" to measure regularity should concentrate on the exact formula, choices for the two input variables, potential applications, and caveats about appropriate usage. The physician who wishes to apply ApEn to heart rate analysis should particularly note the pilot study discussion. The more mathematically inclined reader will benefit from discussions of the relative (comparative) property of ApEn and from Appendix A.

A regularity statistic for medical data analysis

Heart disease detection using deep learning methods from imbalanced ECG samples

Electrocardiography (ECG) plays a fundamental role in the diagnostic work-up of a patient. It is amongst the most commonly used investigations; however, it is impossible to avoid misinterpretation of an unusual ECG. The novice may find it challenging to establish a diagnosis and the senior specialist may miss a subtle change in the ECG. Goldbergers 8th edition of Clinical Electrocardiography has been written for the practising clinician to equip him with the necessary knowledge in not only the correct approach to interpretting an ECG, but also in formulating a management plan. It is written to work as a guide for medical students and allied professionals who would like to understand the basic principles underlying the generation of an ECG as well as for the more experienced clinician who wants to refer to it for an abnormal pattern and compose a management plan. The book provides a systematic approach to ECG analysis and has been divided, for this purpose, into three sections, with individual illustrations and images to improve understanding. The first section covers basic principles of electrocardiography. Focus is given to relevant cardiac anatomy, physiology, normal ECG patterns and the major abnormal depolarisation and repolarisation patterns. The second part deals with the diagnosis of key rhythm disorders relevant to today’s clinical practice, along with management tips. The chapters are divided into brady-arrhythmias and tachy-arrhythmias, covering supra-ventricular and ventricular tachycardia and atrio-ventricular block, as well as dissociation. A chapter is also dedicated to ECG recognition of life-threatening arrhythmias that can cause cardiac arrest. The third part summarises a systematic approach to ECG analysis, highlighting a fourteen point plan in approaching an ECG. The aim is to minimise common mistakes, mostly due to errors of omission. In addition, major and avoidable pitfalls in ECG diagnosis are discussed, for example, marked prolongation of the QT interval, a potential precursor of torsades de pointes, and sudden cardiac arrest, which may be overlooked. Personally, as a trainee in cardiovascular sciences with broad experience in the interpretation of ECGs, I found this book a valuable reference which has enabled me to better develop my insight into ECG analysis through a wealth of clinical highlights, including diagnosis and management tips.

Book Review: Goldberger’s Clinical Electrocardiography. A Simplified Approach:

Artificial intelligence-based approach for atrial fibrillation detection using normalised and short-duration time-frequency ECG

In this article, an automated heartbeat classification has been proposed to prevent the growing threats of cardiovascular diseases around the world. The MIT-BIH arrhythmia database has been used for the training and testing of the proposed approach. The database contains 90 095 normal (N), 2781 supraventricular (SVEB), 7008 ventricular (VEB), 802 fusions (F), and 15 unclassified (Q) beats each of 30 min duration. Total 61 features have been extracted using the time-series feature extraction library (TSFEL). Feature selection or reduction methods applied are feature scaling, removal of highly correlated and low variance features, and random forest (RF) recursive feature elimination. The methodological novelty of this study is mainly the incorporation of TSFEL during feature extractions, synthetic minority oversampling technique to create a balanced dataset, and an ensemble of RF and support vector machine (SVM) using weighted majority algorithm for heartbeat classification to improve the results. Grid search has been performed to optimize the hyperparameters of RF and SVM classifiers. A final evaluation has been carried out considering a “subject-specific” scheme. The sensitivity that our approach has achieved for the arrhythmic heartbeat classes is as follows: N: 99.50%, SVEB (S): 74.20%, VEB (V): 94.22%, F: 73.21%, and Q: 0%. The corresponding positive predictive values are N: 98.67%, SVEB (S): 90.09%, VEB (V): 95.95%, F: 88.35%, and Q: 0%. In comparison with machine learning and deep learning based state-of-the-art approaches, significant improvement in efficiency has been found. Impact Statement— Automated classifications of heartbeats from ECG signals are very much required to speed up the diagnosis of cardiovascular diseases (CVDs). Our study demonstrates 98.21% accuracy compared to existing state-of-the-art approaches. This study impacts the intensive health care system by offering an easy, quick, and cost-effective diagnosis of CVDs. Besides, remote patients can also receive the treatments timely. Early intervention and prevention of CVDs can prevent almost 30% of the total death every year. The proposed approach has a societal and economic impact too, as the health, welfare, and productivity of the citizens as well as of the country will be improved significantly. Approximately 2% of gross domestic product (GDP) will be improved across low- and middle-income countries as the proposed approaches will reduce the direct (treatment cost) and indirect costs (loss in productivities at workplaces) associated with CVDs.

Arrhythmic Heartbeat Classification Using Ensemble of Random Forest and Support Vector Machine Algorithm

This letter proposes an automated detection and classification of arrhythmia from the electrocardiogram (ECG) signals to employ deep learning (DL) framework based on long short-term memory (LSTM) network. Instead of using the classical LSTM network, a feature-based bidirectional LSTM (bi-LSTM) is employed, where a unidirectionally processed multifractal detrended fluctuation analysis is used to extract suitable features. The online available ECG signals are examined using multifractal parameters to study its nonlinear, stochastic, and complex fluctuations. A feature set comprising of ten features has been extracted from the segmented ECG beats followed by feeding to a single layer bi-LSTM network. Experimental results reveal that the feature-based bi-LSTM network outperforms the state-of-the-art DL methods compared on the same dataset. The proposed algorithm is a generic one and can be used for any computer-aided diagnosis of cardiovascular diseases.

Automated Detection and Classification of Arrhythmia From ECG Signals Using Feature-Induced Long Short-Term Memory Network

This paper aims to present an intelligent system for autonomous diagnosis of fetal arrhythmia based on fetal ECG recordings. The present scheme uses one dimensional (1D) convolution with a wavelet kernel to extract time domain features from subjects possessing normal fetal ECG and fetal arrhythmia ECG. Time- domain features obtained from the convoluted signals are fed to a trained artificial neural network (ANN) with gradient descent learning to identify and classify fetal ECG signals. The experimental evaluation of the proposed scheme has been tested with a six- channel fetal ECG signal, available in the NIFEADB database. An overall accuracy of 96% is obtained by evaluating standard performance metrics. The use of 1D convolution not only reduces the computational burden but also helps to specify the feature space to develop an intelligent system for portable embedded system applications.

Debanjan Chatterjee

Papers

Automated Detection and Classification of Arrhythmia From ECG Signals Using Feature-Induced Long Short-Term Memory Network

A Non-Invasive Approach for Fetal Arrhythmia Detection and Classification from ECG Signals