Analysis of digitalized ECG signals based on artificial intelligence and spectral analysis methods specialized in ARVC

Abstract

Arrhythmogenic right ventricular cardiomyopathy (ARVC) is an inherited heart muscle disease that appears between the second and forth decade of a patient's life, being responsible for 20% of sudden cardiac deaths before the age of 35. The effective and punctual diagnosis of this disease based on electrocardiograms (ECGs) could have a vital role in reducing premature cardiovascular mortality. In our analysis, we first outline the digitalization process of paperbased ECG signals enhanced by a spatial filter aiming to eliminate dark regions in the dataset's images that do not correspond to ECG waveform, producing undesirable noise. Next, we propose the utilization of a low-complexity convolutional neural network for the detection of an arrhythmogenic heart disease, that has not been studied through the usage of deep learning methodology to date, achieving high classification accuracy, namely 99.98% training and 98.6% testing accuracy, on a disease the major identification criterion of which are infinitesimal millivolt variations in the ECG's morphology, in contrast with other arrhythmogenic abnormalities. Finally, by performing spectral analysis we investigate significant differentiations in the field of frequencies between normal ECGs and ECGs corresponding to patients suffering from ARVC. In 16 out of the 18 frequencies where we encounter statistically significant differentiations, the normal ECGs are characterized by greater normalized amplitudes compared to the abnormal ones. The overall research carried out in this article highlights the importance of integrating mathematical methods into the examination and effective diagnosis of various diseases, aiming to a substantial contribution to their successful treatment.

A novel epidemiologically informed particle filter for assessing epidemic phenomena. Application to the monkeypox outbreak of 2022

“…We note that the SEIRD scheme should be considered appropriate for the examination of mpox, since the publicly available datasets only include records for the number of infected and deceased cases, which is a frequently observed phenomenon is other cases of epidemics. Thus, the implementation of a more complex epidemiological structure, can lead to overfitting effects-that accompany both artificial intelligence and statistical models [25,51,52]-since any additional states added to the model, are not supported by real-time data.…”

An improved epidemiological-unscented Kalman filter (hybrid SEIHCRDV-UKF) model for the prediction of COVID-19. Application on real-time data

“…The presented results of fitting and forecasting the spread of the disease in France – even for half a month ahead – confirm the trustworthiness of our model. We argue that this stochastic approach is necessary, as errors in the daily reported observations are known, and encapsulating all possible transitions of the pandemic would lead to a very complex model, making the process computationally expensive and the fitting-predictive performance subject to overfitting [41] . For example, transitions characterized by negligible rates, such as the transitions from infection state directly to ICU admission state or from infection state directly to death state, are included in the system's additive noise.…”

Artificial Intelligence in the Differential Diagnosis of Cardiomyopathy Phenotypes

“…Another ML model based on electrocardiograms was recently developed by Papageorgiou et al to discriminate patients with ARVC. The authors proposed the utilization of a CNN for the detection of arrhythmogenic heart disease, achieving 99.98% accuracy, 99.96% specificity, and 99.98% sensitivity during the training phase and 98.6% accuracy, 98.25% specificity, and 98.9% sensitivity when tested [ 49 ].…”