3D ECG display with deep learning approach for identification of cardiac abnormalities from a variable number of leads.

Objective.The objective of this study is to explore new imaging techniques with the use of the deep learning method for the identification of cardiac abnormalities present in electrocardiogram (ECG) signals with 2, 3, 4, 6 and 12-lead in the framework of the PhysioNet/Computing in Cardiology Challenge 2021. The training set is a public database of 88,253 twelve-lead ECG recordings lasting from 6 s to 60 s. Each ECG recording has one or more diagnostic labels. The six-lead, four-lead, three-lead, and two-lead are reduced-lead versions of the original twelve-lead data.Approach.The deep learning method considers images that are built from raw ECG signals. This technique considers innovative 3D display of the entire ECG signal, observing the regional constraints of the leads, obtaining time-spatial images of the 12 leads, where the x-axis is the temporal evolution of ECG signal, the y-axis is the spatial location of the leads, and the z-axis (color) the amplitude. These images are used for training Convolutional Neural Networks with GoogleNet for ECG diagnostic classification.Main results.The official results of the classification accuracy of our team named 'Gio_new_img' received scores of 0.4, 0.4, 0.39, 0.4 and 0.4 (ranked 18th, 18th, 18th,18th, 18th out of 39 teams) for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead versions of the hidden test set with the Challenge evaluation metric.Significance.The results indicated that all these algorithms have similar behaviour in the various lead groups, and the most surprising and interesting point is the fact that the 2-lead scores are similar to those obtained with the analysis of 12 leads. It permitted to test the diagnostic potential of the reduced-lead ECG recordings. These aspects can be related to the pattern recognition capacity and generalizability of the deep learning approach and/or to the fact that the characteristics of the considered cardiac abnormalities can be extracted also from a reduced set of leads.

Modifications in Electrocardiographic and Vectordardiographic Morphological Parameters in Elderly Males as Result of Cardiovascular Diseases and Diabetes Mellitus.

PURPOSE: Morphological electrocardiographic and vectorcardiographic features have been used in the detection of cardiovascular diseases and prediction of the risk of cardiac death for a long time. The objective of the current study was to investigate the morphological electrocardiographic modifications in the presence of cardiovascular diseases and diabetes mellitus in an elderly male population, most of them with multiple comorbidities. METHODS: A database of ECG recordings from the Italian Longitudinal Study on Aging (ILSA-CNR), created to evaluate physiological and pathological modifications related to aging, was considered. The study examined a group of 1109 males with full clinical documentation aged 65-84 years. A healthy control group (219 individuals) was compared to the groups of diabetes mellitus (130), angina pectoris (99), hypertension (607), myocardial infarction (160), arrhythmia (386), congestive heart failure (73), and peripheral artery disease (95). Twenty-one electrocardiographic features were explored, and the effects of cardiovascular diseases and diabetes on these parameters were analyzed. The three-years mortality index was derived and analyzed. RESULTS AND CONCLUSIONS: Myocardial infarction and arrhythmia were the diagnostic groups that showed a significant deviation of 11 electrocardiographic parameters compared to the healthy group, followed by hypertension and congestive heart failure (10), angina pectoris (9), and diabetes mellitus and peripheral artery disease (8). In particular, a set of three parameters (QRS and T roundness and principal component analysis of T wave) increased significantly, whereas four parameters (T amplitude, T maximal vector, T vector ratio, and T wave area dispersion) decreased significantly in all cardiovascular diseases and diabetes mellitus with respect to healthy group. The QRS parameters show a more specific discrimination with a single disease or a group of diseases, whereas the T-wave features seems to be influenced by all the pathological conditions. The present investigation of disease-related electrocardiographic parameters changes can be used in assessing the risk analysis of cardiac death, and gender medicine.

Potential of Rule-Based Methods and Deep Learning Architectures for ECG Diagnostics.

The main objective of this study is to propose relatively simple techniques for the automatic diagnosis of electrocardiogram (ECG) signals based on a classical rule-based method and a convolutional deep learning architecture. The validation task was performed in the framework of the PhysioNet/Computing in Cardiology Challenge 2020, where seven databases consisting of 66,361 recordings with 12-lead ECGs were considered for training, validation and test sets. A total of 24 different diagnostic classes are considered in the entire training set. The rule-based method uses morphological and time-frequency ECG descriptors that are defined for each diagnostic label. These rules are extracted from the knowledge base of a cardiologist or from a textbook, with no direct learning procedure in the first phase, whereas a refinement was tested in the second phase. The deep learning method considers both raw ECG and median beat signals. These data are processed via continuous wavelet transform analysis, obtaining a time-frequency domain representation, with the generation of specific images (ECG scalograms). These images are then used for the training of a convolutional neural network based on GoogLeNet topology for ECG diagnostic classification. Cross-validation evaluation was performed for testing purposes. A total of 217 teams submitted 1395 algorithms during the Challenge. The diagnostic accuracy of our algorithm produced a challenge validation score of 0.325 (CPU time = 35 min) for the rule-based method, and a 0.426 (CPU time = 1664 min) for the deep learning method, which resulted in our team attaining 12th place in the competition.

Personal Verification/Identification via Analysis of the Peripheral ECG Leads: Influence of the Personal Health Status on the Accuracy.

Traditional means for identity validation (PIN codes, passwords), and physiological and behavioral biometric characteristics (fingerprint, iris, and speech) are susceptible to hacker attacks and/or falsification. This paper presents a method for person verification/identification based on correlation of present-to-previous limb ECG leads: I (r I), II (r II), calculated from them first principal ECG component (r PCA), linear and nonlinear combinations between r I, r II, and r PCA. For the verification task, the one-to-one scenario is applied and threshold values for r I, r II, and r PCA and their combinations are derived. The identification task supposes one-to-many scenario and the tested subject is identified according to the maximal correlation with a previously recorded ECG in a database. The population based ECG-ILSA database of 540 patients (147 healthy subjects, 175 patients with cardiac diseases, and 218 with hypertension) has been considered. In addition a common reference PTB dataset (14 healthy individuals) with short time interval between the two acquisitions has been taken into account. The results on ECG-ILSA database were satisfactory with healthy people, and there was not a significant decrease in nonhealthy patients, demonstrating the robustness of the proposed method. With PTB database, the method provides an identification accuracy of 92.9% and a verification sensitivity and specificity of 100% and 89.9%.

A review on electrocardiographic changes in diabetic patients.

Prevalence of diabetes mellitus (DM) is progressively increasing, contributing to a parallel increase in cardiovascular morbidity and mortality, and more than doubling the incidence of sudden cardiac death (SCD). Certain electrocardiographic (ECG) characteristics, such as alternans of the T wave (TWA), heart rate variability (HRV) and dispersion of the QT interval, have been found to be predictive of the risk of SCD. This review focuses on ECG changes that could be found in diabetics and their potential implication for SCD risk.

QT dispersion in the elderly. The ILSA Study.

BACKGROUND AND AIMS: In the last few years there has been active interest in the study of QT interval dispersion (QT-d) calculated from the 12-lead ECG, as a non-invasive method of investigating the homogeneity of ventricular recovery time. The aim of this study was to evaluate QT interval dispersion, analyzing in particular gender and age relationships. Discussion of its electrophysiologic and clinic meaning is still open; moreover, the method must be standardized and normal values should be clearly defined. METHODS: The two common indices, range and standard deviation of QT, were taken into account. The study sample is part of the population-based Italian Longitudinal Study on Aging (ILSA) with individuals older than 64 years. Three groups were identified by clinical data: 256 healthy subjects, 98 patients with only cardiac diseases, and 472 patients with only hypertension. RESULTS: Age (< 75 and > 75) and gender subgroups were considered, showing that age and gender influence the QT-d differently in the three groups. QT-d indices were influenced in the healthy group by gender (p < 0.001), in the cardiopathy group by age (p < 0.001), and in the hypertension group by age (p < 0.02) and gender (p < 0.01). Then the two gender groups were considered separately. In the female group, QT-d increased significantly with age only in the healthy group (p < 0.02), whereas in the male group it increased significantly in the cardiopathy and hypertension groups (p < 0.01). CONCLUSIONS: The two QT-d indices behaved in a very similar way in all the comparisons. In older people, gender and age influenced the three clinical selected groups differently. However, it was shown that is not possible to indicate a clear, definite threshold value classifying with accuracy a single subject in the clinical groups; and a clear-cut, direct clinic application is still doubtful.

An interactive framework for an analysis of ECG signals.

In this study, we introduce and discuss a development of a highly interactive and user-friendly environment for an ECG signal analysis. The underlying neural architecture being a crux of this environment comes in the form of a self-organizing map. This map helps discover a structure in a set of ECG patterns and visualize a topology of the data. The role of the designer is to choose from some already visualized regions of the self-organizing map characterized by a significant level of data homogeneity and substantial difference from other regions. In the sequel, the regions are described by means of information granules-fuzzy sets that are essential in the characterization of the main relationships existing in the ECG data. The study introduces an original method of constructing membership functions that incorporates class membership as an important factor affecting changes in membership grades. The study includes a comprehensive descriptive modeling of highly dimensional ECG data.