A CNN Transfer Learning -Electrocardiogram (ECG) Signal Approach to Predict COVID-19

Deep learning is increasingly gaining traction in cutting-edge medical sciences such as image classification, and genomics due to the high computational performance and accuracy in evaluating medical data. In this study, we investigate the cardiac properties of ECG Images and predict COVID-19 in a binary classification of patients who tested positive for COVID-19 and Normal Persons who tested negative. We analyzed the electrocardiogram (ECG) images by preprocessing the ECG data and building an ECG- Deep Learning- COVID-19 (ECG-DL-COVID) classifier to predict disease. The deep learning models in our experiments constituted CNN, Multi-Layer Perceptron (MLP), and Transfer Learning. Performance evaluation was done to compare the effectiveness of the proposed methodologies with other COVID-19 deep learning-related works. In the three experiments, we achieved an 87% prediction accuracy for MLP, a 90% prediction for CNN and a 93.8% prediction for Transfer Learning. Experimental results and performance evaluation show that the proposed models outperformed previous deep-learning models in the prediction of COVID-19 by a considerable margin. © 2023 IEEE.

"Cardioxy" - A Novel and Portable Instrumentation Amplifier based and IoT enabled ECG device

During the COVID-19 pandemic the healthcare facilities all over world collapsed due to shortage of essential biomedical devices. ECG devices are one of those crucial instruments required for tracing electrical activities of heart. Due to the high cost of gold standard ECG devices used in the medical industries, the availability of on-demand ECG devices was not accessible to everyone. Thus, the need of portable, low cost, on-demand ECG device was needful at the earliest. In this paper we propose a novel, versatile, 3-lead, IoT enabled, LM324/LM741 operational amplifiers in instrumentation amplifier configuration Electrocardiogram machine that is aimed towards providing accurate information about the electrical activity of our heart in real time. In this attempt, we have come up with an analogue circuit design consisting of multiple operational amplifier IC based fundamental circuit blocks. The prototype is designed in such a way that the output of ECG can be visualised worldwide using IoT. © 2023 IEEE.

Remotely Controlled Real-Time Health Surveillance System of COVID-19 Patients

This work focuses on the development of a portable physiological monitoring framework that can continuously monitor the patient's heartbeat, oxygen levels, temperature, ECG measurement, blood pressure, and other fundamental patient's data. As a result of this, the workload and the chances of being infected by COVID-19 of the health workers will be reduced and an efficient patient monitoring system can be maintained. In this paper, an IoT based continuous monitoring system has been developed to monitor all COVID-19 patient conditions and store patient data in the cloud server using Wi-Fi Module-based remote communication. In this monitoring system, data stored on IoT platform can be accessed by an authorized individual and ailments can be examined by the doctors from a distance based on the values obtained. If a patient's physical condition deteriorates, the doctor will immediately receive the emergency alert notification. This model proposed in this research work would be extremely important in dealing with the Corona epidemic around the world. © 2022 IEEE.

Research on fatigue identification methods based on low-load wearable ECG monitoring devices

The identification of fatigue in personal workers in particular environments can be achieved through early warning techniques. In order to prevent excessive fatigue of medical workers staying in infected areas in the early phase of the coronavirus disease pandemic, a system of low-load wearable electrocardiogram (ECG) devices was used as intelligent acquisition terminals to perform a continuous measurement ECG collection. While machine learning (ML) algorithms and heart rate variability (HRV) offer the promise of fatigue detection for many, there is a demand for ever-increasing reliability in this area, especially in real-life activities. This study proposes a random forest-based classification ML model to identify the four categories of fatigue levels in frontline medical workers using HRV. Based on the wavelet transform in ECG signal processing, stationary wavelet transform was applied to eliminate the main perturbation of ECG in the motion state. Feature selection was performed using ReliefF weighting analysis in combination with redundancy analysis to optimize modeling accuracy. The experimental results of the overall fatigue identification achieved an accuracy of 97.9% with an AUC value of 0.99. With the four-category identification model, the accuracy is 85.6%. These results proved that fatigue analysis based on low-load wearable ECG monitoring at low exertion can accurately determine the level of fatigue of caregivers and provide further ideas for researchers working on fatigue identification in special environments. © 2023 Author(s).

A CNN for COVID-19 Detection Using ECG signals

We developed an end-to-end automatic algorithm for the detection of signs of COVID-19 virus infection in ECGs. We analyzed 12-lead ECGs from patients infected by COVID-19 (C-group) and from a control group (NC-group). The C-group (896 cases) included patients (age range [19-96] years) hospitalized at Ospedale San Matteo in Pavia (Italy) during the first 2020 pandemic outbreak. Infection was confirmed by nasal swab testing. The NC-group (also 896 cases) was built by collecting ECG in sinus rhythm from 3 datasets: Georgia ECG (USA), PTB-XL (Germany) and CPSC 2018 (China). Control ECGs were matched by gender, age and heart rate. An additional control group, only used for testing, was extracted from the Ningbo (China) database. A 4-layers convolutional neural network (CNN), with increasing filter size plus a final fully connected (FC) layer, was designed to classify C vs NC-group. The CNN was trained and k-fold cross validated (k=7) on 1536 ECGs (1316 for testing-220 for validation). Every fold model was used to classify the remaining, separate common test set of 256 ECGs. The accuracy was 0.86 ± 0.01 on validation, 0.86 ± 0.01 on the test set. The FPR on the NC-group was 0.14 ± 0.03 on validation, 0.13 ± 0.02 on test and 0.10 ± 0.01 on the Ningbo test set (p > 0.05,ns) showing that no bias was induced by the selection of datasets. © 2022 Creative Commons.

Cardiovascular complications in patients after coronavirus disease-2019

The data of the modern literature describing the long-term consequences of infection of the body with SARS-CoV-2 on the cardiovascular system in the framework of postcovid syndrome are analyzed. To date, postcovid syndrome refers to a condition in which symptoms continue to persist for more than 12 weeks from the moment of diagnosis of COVID-19. Various complaints of patients after undergoing a new coronavirus infection are described, the distinguishing feature of which is their versatility, where cardiovascular manifestations are assigned one of the leading roles. Postural orthostatic tachycardia syndrome, cardiac arrhythmia and conduction disorders are considered. The role of SARS-CoV-2 in the formation of de novo and decompensation of pre-existing cardiovascular diseases has been demonstrated. The possibility of developing heart failure in patients with COVID-19 as an outcome of inflammation of the heart muscle is shown. Particular attention is paid to the analysis of the incidence of myocarditis after 3 months or more from the diagnosis of COVID-19, as well as thrombotic complications, in the genesis of which the main role belongs to the formation of endothelial dysfunction resulting from the interaction of SARS-CoV-2 with vascular endothelial cells. The autoimmune component of the pathogenesis of damage to the cardiovascular system as a result of the formation of endothelial dysfunction in COVID-19 is also considered. The authors present a laboratory-instrumental algorithm for determining cardiovascular complications in people who have undergone COVID-19, including the determination of the N-terminal fragment of the brain natriuretic peptide B-type prohormone, the level of anticardial antibodies, electrocardiography, echocardiography, as well as magnetic resonance imaging of the heart with contrast.

Design of real-time ECG monitoring wearable equipment based on the Holter system

The COVID-19 epidemic has largely restricted the traditional offline medical treatment model. In this study, we designed ECG monitoring smart clothing based on the Holter system after identifying and analyzing the needs of patients and doctors. This clothing is a wearable device that integrates monitoring and remote diagnosis, building a general network platform to realize remote data transfer sharing and online interactive auxiliary diagnosis. Wearable clothing that can monitor ECG in real time is designed and developed by intelligently integrating limb lead wires, conductive fiber fabrics, lead interfaces, and electrode signal storage receivers by using the human body sensing conduction principle of real-time ECG monitoring. Wearable real-time ECG monitoring clothing can help patients achieve fast virtual medical care and auxiliary diagnosis, and solve the design issues with electrode signal storage receivers. © 2022 IEEE.

Biosignal Databases for Training of Artificial Intelligent Systems

Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. Most people infected with the virus will have mild to moderate respiratory diseases, however, the elderly population is the most vulnerable, becoming seriously ill, requiring continuous medical follow-up. In this sense, technologies were developed that allow continuous and individual monitoring of patients, in a home environment, namely through wearable devices, thus avoiding continuous hospitalization. Thus, these devices allow great improvements in data analysis methods since they can continuously acquire the physiological signals of an individual and process them in real-Time through artificial intelligence (AI) methods. However, training of AI methods is not straightforward, requiring a large amount of data. In this study, we review the most common biosignal databases available in the literature. A total of thirteen databases were selected. Most of the databases (9 databases) were related to ECG signal, as well as 4 databases containing signals from SPO2, Heart Rate, Blood Pressure, etc. Characteristics were described, namely: The population of the databases, data resolution, sampling rates, sample time, number of signal samples, annotated classes, data acquisition conditions, among other aspects. Overall, this study summarizes and described the public biosignals databases available in the literature, which may be important in the implementation of intelligent classification methods. © 2022 ACM.

A Framework for Real-time Remote ECG Monitoring and Diagnoses

Enabled by the fast development of Internet of Things (IoT) technologies in recent years, the healthcare domain has witnessed significant advancements in wearable devices that seamlessly collect vital medical information. With the availability of IoT devices serving the healthcare domain, extraordinary amounts of sensory data are generated in real-time, requiring immediate diagnoses and attention in critical medical conditions. The provision of remote patient monitoring (RPM) and analytics infrastructure proved to be fundamental components of the healthcare domain during the Coronavirus pandemic. Traditional healthcare services are digitized and offered virtually, where patients are monitored and managed remotely without the need to go to hospitals. This paper presents a comprehensive RPM framework for real-time telehealth operations with scalable data monitoring, real-time analytics and decision-making, fine-grained data access and robust notification mechanisms in emergencies and critical health conditions. We focus on the overall framework architecture, enabling technologies integration, various system-level integrations and deployment options. Furthermore, we provide a use case application for patients with chronic heart conditions for real-time electrocardiogram (ECG) monitoring. We are releasing the framework as open-source software to the active research community. © 2022 IEEE.

Monte Carlo Dropout for Uncertainty Analysis and ECG Trace Image Classification

Cardiovascular diseases (CVDs), such as arrhythmias (abnormal heartbeats) are the prime cause of mortality across the world. ECG graphs are utilized by cardiologists to indicate any unexpected cardiac activity. Deep Neural Networks (DNN) serve as a highly successful method for classifying ECG images for the purpose of computer-aided diagnosis. However, DNNs can not quantify uncertainty in predictions, as they are incapable of discriminating between anomalous data and training data. Hence, a lack of reliability in automated diagnosis and the potential to cause severe decision-making issues is created, particularly in medical practises. In this paper, we propose an uncertainty-aware ECG classification model where Convolutional Neural Networks (CNN), combined with Monte Carlo Dropout (MCD) is employed to evaluate the uncertainty of the model, providing a more trustworthy process for real-world scenarios. We use ECG images dataset of cardiac and covid-19 patients containing five categories of data, which includes COVID-19 ECG records as well as data from other cardiovascular disorders. Our proposed model achieves 93.90% accuracy using this dataset. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Multidimensional Signal Processing and Applications—New Approaches

This chapter is a short introduction in the contemporary approaches aimed at the multidimensional processing and analysis of various kinds of signals, investigated in related research works, which were presented at the Third International Workshop "New Approaches for Multidimensional Signal Processing”, (NAMSP), held at the Technical University of Sofia, Bulgaria in July 2022. Some of the works cover various topics, as: moving objects tracking in video sequences, automatic audio classification, representation of color video чpeз 2-level tensor spectrum pyramid, etc., and also introduce multiple applications of the kind: analysis of electromyography signals, diagnostics of COVID based on ECG, etc. Short descriptions are given for the main themes covered by the book, which comprises the following three sections: multidimensional signal processing;applications of multidimensional signal processing, and applications of blockchain and network technologies. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Advanced ECG holter with 2.4 GHz communication

In this article we present the latest version of our ECG holter. The request for his design arose in difficult COVID times. The device is developed in cooperation and based on the specification of F. D. Roosevelt University Hospital in Banska Bystrica, Slovakia. The ECG holter is built modularly, its digital part can be used in several telemedicine projects. In addition to measuring ECG and respiration, the device also includes a wide set of physical sensors, and in order to achieve higher resistance of the device to interference, we use our own 2.4 GHz proprietary protocol. © 2022 IEEE.

Registration of the post-COVID state using machine-learning approach

In this study we applyed machine-learning approach for registration of the post-COVID state. During the study, a marker of the post-COVID state of a person was found in the electrocardiogram data. We have shown that this marker in the patient's ECG signal can be used to diagnose a post-COVID state. © 2022 IEEE.

The Optimization of ECG-Leads Based Cardiovascular Abnormal Detection Scheme

An electrocardiogram, often known as an ECG, is a diagnostic tool that measures the electrical activity of the heart in order to identify potential heart abnormalities. Although the normal 12-lead ECG is the dominant approach in cardiac diagnostics, it is still challenging to identify distinct heart illnesses using a single lead or a reduced number of leads. Automatic diagnosis of cardiac abnormalities via the ECG with a reduced lead system (less than the typical 12-lead system) may give a helpful diagnostic alternative to traditional 12-lead ECG equipment that is both simple to use and less expensive. This alternative uses fewer leads than the standard system. This study considers the use of Recurrent Neural Networks Long Short-Term Memory (RNN- LSTM) to identify the ability to use less standard ECG leads to detect cardiac abnormalities using various lead combinations, including 6, 4, 3, 2, 1, and 12 lead ECG data. The results of this investigation are presented in this article. Data pre-processing, model design, and hyperparameter tuning are all essential for RNN-LSTM multi-label classification. The initial step was to pre-process the ECG readings to eliminate the base-line wander noise for ECG signals;the next stage is lead combination selection and clipped to have an equal duration of 10 seconds at various used leads. The gathered results show a possibility of using a single lead instead of multiple leads for preliminary cardiovascular diseases (CVDs) identification. It is a critical issue, especially during emergencies such as the COVID- 19 pandemic or in crowded hospitals when medical resources are limited and online (internet-based) monitoring technologies are vital. © 2022 IEEE.

Heart Rate Variability of Healthcare Workers during Covid-19

The outbreak of Covid-19 has exacerbated the mental health of Healthcare Workers (HCWs), caused by an increase in their stress levels owing to an exponential rise in their workloads. Previous works have revealed visible changes in Heart Rate Variability (HRV), in response to increased/decreased stress levels. This study focused on analyzing HRV as a parameter to observe the impact of higher stress levels, on clinicians, due to the pandemic. Their responses to a Perceived Stress Score (PSS) questionnaire were used as a reference to determine their escalated stress levels. The responses showed that 40% of clinicians revealed increased levels of high chronic stress while the remaining were affected by moderate chronic stress. We computed HRV for each clinician from HR data obtained using a chest-based wearable device during sleep and ward sessions. Through detailed analysis of HRV, we observed clinicians with high chronic stress showed lower HRV when compared to clinicians with moderate chronic stress during both sleep and ward sessions. Later we did a close investigation of their HRV on Day 1 and Day 2 in Covid-IP (Inpatient) and compared the HRV features. Finally, we compared the HRV features of clinicians between Covid-IP Covid-OP (Outpatient) ward sessions. The above study validated that HRV is a reliable parameter for an objective assessment of stress levels. © 2022 IEEE.

The effect of coronavirus infection on QT and QTc intervals of hospitalized patients in Qazvin, Iran

Electrocardiographic (ECG) changes have been investigated in the condition of coronavirus disease (COVID-19) indicating that COVID-19 infection exacerbates arrhythmias and triggers conduction abnormalities. However, the specific type of ECG abnormalities in COVID-19 and their impact on mortality fail to have been fully elucidated. The present retrospective, tertiary care hospital-based cross-sectional study was conducted by reviewing the medical records of all patients diagnosed with COVID-19 infection who were admitted to Booali Sina Hospital in Qazvin, Iran from March to July 2020. Demographic information, length of hospital stay, treatment outcome, and electrocardiographic information (heart rate, QTc interval, arrhythmias, and blocks) were extracted from the medical records of the patients. Finally, a total of 231 patients were enrolled in the study. Atrial fibrillation was a common arrhythmia, and the left anterior fascicular block was a common cardiac conduction defect other than sinus arrhythmia. The deceased patients were significantly older than the recovered ones (71 ± 14 vs. 57 ± 16 years, p < 0.001). Longer hospital stay (p = 0.036), non-sinus rhythm (p < 0.001), bundle and node blocks (p = 0.002), ST-T waves changes (p = 0.003), and Tachycardia (p = 0.024) were significantly prevalent in the deceased group. In baseline ECGs, no significant difference was observed in terms of the absolute size of QT;however, a prolonged QTc in the deceased was about twice of the recovered patients (using Bazett, Sagie, and Fridericia’s formula). Serial ECGs are recommended to be taken from all hospitalized patients with COVID-19 due to increased in-hospital mortality in patients with prolonged QTc interval, non-sinus rhythms, ST-T changes, tachycardia, and bundle, and node blocks. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

IoT Based Healthcare Kit for Domestic Usage

Every country faces obstacles in dealing with COVID-19 as a sickness, but the challenges posed by developing and growing economies are distinct. The availability of healthcare is limited. Hospitals in developing countries lack the necessary infrastructure to assist patients. As a result, routine exams and clinics are no longer feasible. Hence, the internet of things can be used to address these issues. This manuscript presents a development of a real-time, automated, low-cost, IoT-based instrument to measure a patient's heartbeats per minute, SpO2, temperature, and electrocardiogram at home without having to go to the hospital. © 2022 IEEE.

Remote Health Monitoring and Doctor on Call System

People's lives can be lost if they do not receive timely medical treatment;therefore, prompt medical care is vital. Furthermore, due to a lack of constant vital monitoring, early symptoms of major medical conditions, such as an irregular heartbeat or abnormal ECG output, are occasionally ignored. As a result, remote monitoring of the elderly and disabled is important during the COVID 19 outbreak. To solve these issues, a "Remote Health Monitoring and Doctor on Call System"has been developed. Health data exchange between healthcare providers and family members is becoming more prevalent these days. It ensures that patients' health results are safer and better. Sharing health-care data is also essential for lowering health-care expenses. It is feasible to remotely monitor a crippled or elderly patient's health. In addition to specialists, guardians can obtain a comprehensive picture of the patient's medical history. To address the issue of insufficient medical care and assistance for elderly and disabled patients, a unique and comprehensive Remote Health Monitoring and Doctor on Call System that can monitor the patient's vital signs such as heart rate, body temperature, and ECG output of the heart;monitor the patient's environment;display and store all of this information via a cloud server using ThingSpeak and Ubidots IoT platform;display these critical statistics with a mobile application for Android/iOS and in the event of an emergency or if vital signs are abnormal, contact the nearest hospital was developed in this paper. © 2022 IEEE.

Importance of myocardial ischemia detected with protocol-based measurements of high-sensitivity troponin, ECG and echocardiography in critically ill patients without acute coronary syndrome-a prospective study

Elevated cardiac troponin is detected in the majority of critically ill patients. This study aimed to evaluate the prognostic value of protocol-guided detection of myocardial ischemia (MI) (serial 12-lead electrocardiograms (ECG), high-sensitivity troponin T (hsTnT) measurements, and echocardiography) and compare it with a retrospective cohort with only clinically driven detection of MI. In a prospective observational study, 95 patients hospitalized 48 hours for reasons other than acute coronary syndrome in medical or surgical intensive-care unit (ICU) were enrolled. A protocol-based approach, with regular 12-lead ECG recordings, hsTnT measurements and admission echocardiography was conducted. All events possibly indicating MI were documented, and ECG, hsTnT, echocardiography were repeated. The protocol-based approach was compared to a retrospective group with only clinically driven detection of MI. In the prospective group, 95.8% of patients had at least one elevated hsTnT value. A hsTnT >70 ng/L was associated with the use of inotropes (OR 3.35 (95% CI: 1.184, 9.472), p = 0.022), left ventricular ejection fraction <30% (OR 9.65 (95% CI: 1.172, 76.620), p = 0.035), regional wall motion abnormalities (OR 3.87 (95% CI: 1.032, 14.533), p = 0.045), ICU mortality (OR 8.38 (95% CI: 1.004, 69.924), p = 0.0495), hospital mortality (OR 3.05 (95% CI: 1.133, 8.230), p = 0.027) and 1-year mortality (OR: 5.43 (95% CI: 2.1099, 13.971), p = 0.005). The incidence of MI was higher in the prospective, as compared to the retrospective group (22.1% vs 5.3%;p = 0.001). MI, compared to the high "hsTnT positive only" group, predicted hospital mortality (OR 3.33 (95% CI: 1.190, 9.329), p = 0.02) and 1-year mortality (OR 4.66 (95% CI: 1.647, 13.222), p = 0.0037). A protocol-based compared to a clinically driven approach for the detection of MI reveals more patients with MI. The majority of critically ill patients have elevated hsTnT levels. Detected MI additionally stratifies patients with elevated hsTnT to higher hospital and 1-year mortality.

Different modalities to assess right ventricular function in post-COVID taking ST-elevation as a gold standard and arrhythmias in post-COVID

The COVID-19 caused by novel single-stranded RNA enveloped severe acute respiratory syndrome coronavirus-2 (SARS CoV-2) first appeared in Wuhan, China. A lot of focus has been given to pulmonary complications. According to several case reports, cardiovascular associated clinical manifestations include myocarditis, arrhythmias, veno-thromboembolic events, acute coronary syndrome (ACS), and pericarditis. Different modalities in diagnosis like 2D, doppler can help in the early diagnosis of right ventricular function. This study evaluates the cardiac changes in recovered COVID-19 positive patients by 2D echocardiogram and other modalities. In this prospective observational study, 139 participants recently recovered from COVID-19 illness were identified and recruited after obtaining the Informed concerned form (ICF). The patients once enrolled were subjected to 2D echo and ECG as part of routine clinical practice. Out of 139 patients, 89 (64.03%) were males, and the rest were females. Based on the severity scale, 13 (9.35%) participants had suffered a severe form of COVID-19 infection. Right ventricular functional assessment, right ventricular global strain (RVGLS) was abnormal in 72 (51.80%) participants. Arrhythmias were reported in 31 (22.30%) participants;among them, 30 participants had sinus bradycardia. Our study demonstrates the association between COVID-19 and cardiac changes/ incidence of cardiovascular complications in recovered COVID-19 patients. This study provides first-hand evidence of the incidence of abnormal LVGLS and RVGLS in COVID-19 recovered patients. In addition, there was a higher incidence of arrythmias.