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.

COVID Detection Using ECG Image Reports: A Survey

COVID-19 is one of the greatest pandemics that threaten individuals, especially the elders. It was first reported inWuhan, China in 2019. It was discovered recently that COVID-19 disease can be detected using three main protocols. The first protocol is based on Polymerase Chain reaction (PCR), while the second protocol is based on lung chest (ultrasound, X-ray, and CT-Scan), and the final protocol is based on the ECG image reports. This review aims to present a survey on the methodologies and algorithms applied for the detection of COVID disease using electrocardiogram (ECG). In this study, various papers were presented for determining how the COVID can be diagnosed using ECG image reports relying on symptoms and changes in the ECG peaks and intervals. In addition to this, other studies are presented on techniques applied to the ECG reports for the detection of COVID. Also, the main limitations and future works are illustrated. It can be concluded that COVID can be detected with high accuracy using ECG reports and it is even more efficient than other protocols. Finally, based on the performance of the studies it can be shown that the ECG image report is close to an acceptable level in the detection of COVID disease.

The natural history of QTc interval and its clinical impact in coronavirus disease 2019 survivors after 1 year.

Background and objective: Prolonged QTc interval on admission and a higher risk of death in SARS-CoV-2 patients have been reported. The long-term clinical impact of prolonged QTc interval is unknown. This study examined the relationship in COVID-19 survivors of a prolonged QTc on admission with long-term adverse events, changes in QTc duration and its impact on 1-year prognosis, and factors associated with a prolonged QTc at follow-up. Methods: We conducted a single-center prospective cohort study of 523 SARS-CoV-2-positive patients who were alive on discharge. An electrocardiogram was taken on these patients within the first 48 h after diagnosis and before the administration of any medication with a known effect on QT interval and repeated in 421 patients 7 months after discharge. Mortality, hospital readmission, and new arrhythmia rates 1 year after discharge were reviewed. Results: Thirty-one (6.3%) survivors had a baseline prolonged QTc. They were older, had more cardiovascular risk factors, cardiac disease, and comorbidities, and higher levels of terminal pro-brain natriuretic peptide. There was no relationship between prolonged QTc on admission and the 1-year endpoint (9.8% vs. 5.5%, p = 0.212). In 84% of survivors with prolonged baseline QTc, it normalized at 7.9 ± 2.2 months. Of the survivors, 2.4% had prolonged QTc at follow-up, and this was independently associated with obesity, ischemic cardiomyopathy, chronic obstructive pulmonary disease, and cancer. Prolonged baseline QTc was not independently associated with the composite adverse event at 1 year. Conclusions: Prolonged QTc in the acute phase normalized in most COVID-19 survivors and had no clinical long-term impact. Prolonged QTc at follow-up was related to the presence of obesity and previously acquired chronic diseases and was not related to 1-year prognosis.

COVID Detection Using ECG Image Reports: A Survey

COVID-19 is one of the greatest pandemics that threaten individuals, especially the elders. It was first reported in Wuhan, China in 2019. It was discovered recently that COVID-19 disease can be detected using three main protocols. The first protocol is based on Polymerase Chain reaction (PCR), while the second protocol is based on lung chest (ultrasound, X-ray, and CT-Scan), and the final protocol is based on the ECG image reports. This review aims to present a survey on the methodologies and algorithms applied for the detection of COVID disease using electrocardiogram (ECG). In this study, various papers were presented for determining how the COVID can be diagnosed using ECG image reports relying on symptoms and changes in the ECG peaks and intervals. In addition to this, other studies are presented on techniques applied to the ECG reports for the detection of COVID. Also, the main limitations and future works are illustrated. It can be concluded that COVID can be detected with high accuracy using ECG reports and it is even more efficient than other protocols. Finally, based on the performance of the studies it can be shown that the ECG image report is close to an acceptable level in the detection of COVID disease. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Prolonged Use of Tirofiban Infusion Without Percutaneous Coronary Intervention To Achieve Optimal Results in a COVID-19 Positive Patient With Inferior ST Segment Elevated Myocardial Infarction (STEMI) Secondary to Thromboembolism: A Case Report.

Severe acute respiratory syndrome­coronavirus­2 (SARS­CoV­2), responsible for COVID-19, is mainly a respiratory illness, but it can affect other organs also such as heart, kidneys, and liver. Myocardial injury from COVID-19 has been reported in hospitalized patients ranging from pericarditis and myocarditis to acute coronary syndrome (ACS). COVID-19 is highly hypercoagulable state and is associated with both central and peripheral thromboembolism. COVID 19 patients with ACS may not present with classical features of chest pain and electrocardiogram (ECG) is the most important initial investigation in these patients to assess for any ST or T waves changes. COVID-19 patients with cardiac involvement are the most vulnerable group of patients and have increased morbidity and mortality risk. COVID-19 infections can affect the cardiovascular system in patients with or without history of coronary artery disease (CAD), but the risk of type 1 or 2 myocardial infarction (MI), myocardial injury, ST segment elevation, myocarditis, heart failure, cardiogenic shock, and life threatening arrhythmias are more common in the former group. We present a case of 55-year-old patient who presented to our cardiac center with ST elevated myocardial infarction and high blood sugar level. Patient was recently diagnosed with type 2 diabetes mellitus (T2DM) but was not commenced on medications. Echocardiogram showed mildly impaired left ventricular systolic function (LVSF) with inferior wall hypokinesia, and ECG showed inferior leads ST elevation. Coronary angiogram showed severe mid-vessel lesion and occluded posterior left ventricular branch (PLV). Multiple attempts at aspirating the thrombus resulted in thrombolysis in MI grade 2 (TIMI 2) flow in the vessel and patient was commenced on a tirofiban infusion for 72 hours.

Remdesivir-Induced Marked Sinus Bradycardia in COVID-19.

Remdesivir has been extensively employed during the coronavirus disease 2019 (COVID-19) pandemic as it has proven to be efficacious against the causative SARS-CoV-2. However, there is not much evidence on the cardiovascular adverse effect profile of remdesivir. In addition, limited data support the occurrence of sinus bradycardia associated with remdesivir. Herein we chronicle a clinical encounter of a patient suffering from COVID-19 whose clinical course was complicated by marked sinus bradycardia that began acutely after remdesivir initiation and resolved on cessation of the medication. The patient denied symptoms and completed a 5-day course with a resolution of bradycardia on completion of medication. We suggest that the physicians be cognizant of this rare side effect of remdesivir and suggest a continuation of this medication unless symptomatic bradycardia precludes management.

Sensitivity and specificity of automated blood pressure devices to detect atrial fibrillation: A systematic review and meta-analysis of diagnostic accuracy.

Background: Atrial fibrillation (AF) is a prevalent and preventable cause of stroke and mortality. Aim: This systematic review and meta-analysis aimed to investigate the sensitivity and specificity of office and out-of-office automated blood pressure (BP) devices to detect AF. Methods: Diagnostic studies, extracted from databases such as Ovid Medline and Embase, on AF detection by BP device(s), electrocardiography, and reported sensitivity and specificity, were included. Screening of abstracts and full texts, data extraction, and quality assessment were conducted independently by two investigators using Covidence software. The sensitivity and specificity of the BP devices were pooled using a random-effects model. Results: Sixteen studies including 10,158 participants were included. Only a few studies were conducted in primary care (n = 3) or with a low risk of bias (n = 5). Office BP devices, which utilised different algorithms to detect AF, had a sensitivity and specificity of 96.2 and 94%, respectively. Specificity was reduced when only one positive result was considered among consecutive BP measurements. Only a few studies (n = 3) investigated out-of-office BP. Only one study (n = 100) suggested the use of ≥79 and ≥26% of positive readings on 24-h ambulatory BP measurements to detect AF and paroxysmal AF, respectively. Conclusions: Office BP devices can be used clinically to screen for AF in high-risk populations. Clinical trials are needed to determine the effect of AF screening using office BP devices in reducing stroke risk and mortality. Further studies are also required to guide out-of-office use of BP devices for detecting paroxysmal AF or AF. Systematic review registration: https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42022319541, PROSPERO CRD42022319541.

Dual-Factor WBAN Enhanced Authentication System Based on Iris and ECG Descriptors

At present, COVID-19 is still spreading and affecting millions of people worldwide. Minimizing the need for travel can significantly reduce the probability of infection and improve patients’quality of life. The wireless body area network (WBAN) transmits the patients’physiological data to the doctor remotely through the sensors in a way that minimizes physical contact with others. However, existing WBAN security authentication schemes have core limitation that includes weak authentication performance and over-consumption of resources that precludes their widespread adoption in practical applications. Therefore, in this paper, an enhanced dual-factor authentication system that address the mentioned drawbacks is proposed for securing WBAN resources. By combining iris and electrocardiogram (ECG) features, users would be required to pass the first-level iris authentication before performing the second-level ECG authentication, thus enhancing the overall security scheme of a WBAN system. Furthermore, we examined the existing Inter-Pulse-Intervals (IPI) encoding methods and propose a more efficient ECG IPI encoding algorithm which can effectively shorten the encoding time without affecting the overall encoding performance. Finally, extensive experiments were performed to verify the performance of the proposed dual-factor iris and ECG based WBAN authentication system using public iris and ECG databases. The experimental results show that the false acceptance rate (FAR) is close to 0.0% and the false rejection rate (FRR) is close to 3.2%. Findings from this study suggest that the proposed dual-factor authentication scheme could aid adequate deployment of security schemes to protect WBAN resources in practical applications. IEEE

12-Lead ECG Platform for Real-time Monitoring and Early Anomaly Detection

In response to the rapid digital revolution and the COVID-19 pandemic, the healthcare landscape has significantly shifted from physical to virtual care and telemedicine. As a result, healthcare providers and patients have shown increased interest and adoption for up-to-date technologies to monitor ongoing health conditions, including cardiovascular diseases. Driven by the importance of an efficient remote cardiovascular monitor for virtual care, we present a platform that enables remote ECG testing and provides ubiquitous data access to patients and their healthcare providers. A patent-pending 12-lead data acquisition ECG patch is attached to the patient's body to simultaneously collect heart signals, perform binary classification, and transmit the data to healthcare providers for further analysis at a high rate of up to 480 samples per second. As a preliminary classification phase, the presented platform introduces a machine learning technique to classify ECG signals near the ECG patch. The classification function is optimized for power-constrained devices using machine learning techniques. Moreover, the preliminary results of the energy consumption profile show that the ECG patch provides up to 37 hours of continuous 12-lead ECG streaming. © 2022 IEEE.

Real-time artificial intelligence based health monitoring, diagnosing and environmental control system for COVID-19 patients.

By upgrading medical facilities with internet of things (IoT), early researchers have produced positive results. Isolated COVID-19 patients in remote areas, where patients are not able to approach a doctor for the detection of routine parameters, are now getting feasible. The doctors and families will be able to track the patient's health outside of the hospital utilizing sensors, cloud storage, data transmission, and IoT mobile applications. The main purpose of the proposed research-based project is to develop a remote health surveillance system utilizing local sensors. The proposed system also provides GSM messages, live location, and send email to the doctor during emergency conditions. Based on artificial intelligence (AI), a feedback action is taken in case of the absence of a doctor, where an automatic injection system injects the dose into the patient's body during an emergency. The significant parameters catering to our project are limited to ECG monitoring, SpO2 level detection, body temperature, and pulse rate measurement. Some parameters will be remotely shown to the doctor via the Blynk application in case of any abrupt change in the parameters. If the doctor is not available, the IoT system will send the location to the emergency team and relatives. In severe conditions, an AI-based system will analyze the parameters and injects the dose.

ECG-iCOVIDNet: Interpretable AI model to identify changes in the ECG signals of post-COVID subjects.

OBJECTIVE: Studies showed that many COVID-19 survivors develop sub-clinical to clinical heart damage, even if subjects did not have underlying heart disease before COVID. Since Electrocardiogram (ECG) is a reliable technique for cardiovascular disease diagnosis, this study analyzes the 12-lead ECG recordings of healthy and post-COVID (COVID-recovered) subjects to ascertain ECG changes after suffering from COVID-19. METHOD: We propose a shallow 1-D convolutional neural network (CNN) deep learning architecture, namely ECG-iCOVIDNet, to distinguish ECG data of post-COVID subjects and healthy subjects. Further, we employed ShAP technique to interpret ECG segments that are highlighted by the CNN model for the classification of ECG recordings into healthy and post-COVID subjects. RESULTS: ECG data of 427 healthy and 105 post-COVID subjects were analyzed. Results show that the proposed ECG-iCOVIDNet model could classify the ECG recordings of healthy and post-COVID subjects better than the state-of-the-art deep learning models. The proposed model yields an F1-score of 100%. CONCLUSION: So far, we have not come across any other study with an in-depth ECG signal analysis of the COVID-recovered subjects. In this study, it is shown that the shallow ECG-iCOVIDNet CNN model performed good for distinguishing ECG signals of COVID-recovered subjects from those of healthy subjects. In line with the literature, this study confirms changes in the ECG signals of COVID-recovered patients that could be captured by the proposed CNN model. Successful deployment of such systems can help the doctors identify the changes in the ECG of the post-COVID subjects on time that can save many lives.

Arrhythmia Detection on ECG Signal Using Neural Network Approach

The world has been shook by a rigorous pandemic covid-19 additionally it has accentuated a consequentiality on automating the health sectors from manually reading the reports to utilizing machine learning as an implement to getting the results of findings of sundry reports in an automated manner. There are many studies which have proved that the persons suffering from corona virus had optically discerned its effect on heart health. In rigorous cases it lead to cardiac apprehend proving it to be fatal for the patients. ECG (Electro cardiogram) is undertaken on patients to monitor their heart health;the ECG reports are then manually checked by medicos to conclude about heart health of a person. Cardiology is a study of heart and includes a variety of intricate diseases to be studied. This paper presents an efficient way of arrhythmia detection utilizing dataset which would be subsidiary for implementation of machine learning in this disease detection. Neural network has been utilized in the proposed work and is found to be 99% efficient thereby exhibiting a precise and tested method to further facilitate automation in this sector. © 2021 IEEE.

Design and Implementation of Real-Time Bio Signals Management System based on HL7 FHIR for Healthcare Services

Recently, attention has been focused on services that combine medical technology with ICT technologies such as artificial intelligence, big data, Internet of Things, and block chains. In addition, Research on healthcare services that can collect bio signal data through wearable sensors using IoT technology and monitor and manage health based on the collected data is increasing significantly. In particular, in a situation where the world is entering a rapidly aging society, health care services are being researched and developed in the direction of preventing diseases in advance and maintaining a healthy life. Healthcare services are bringing important changes in the pandemic era caused by covid-19. There is a need for a system capable of efficiently sharing and exchanging information of heterogeneous services to prevent emergencies and support optimal medical services. In this paper, we designed and developed a system that can collect, convert, and store bio-signals from various wearable sensors into international standard data to develop such healthcare services. HL7 (health level seven) FHIR (fast healthcare interoperability resources) applied mutandis in this paper is a standard protocol for data exchange between medical information systems of real-Time collected bio signals. In this paper, we implement an interface module that converts bio signals such as EEG (electroencephalography), ECG (electrocardiogram), EMG (electromyography), and PPG (photoplethysmography) collected in real time from a wearable sensor into a message structure defined by HL7 FHIR. The interface module consists of a client part and a server part. The client part generates a variety of signal data from the healthcare service user and delivers the message to the server part. The server part is designed and implemented to parse the received message by segment field unit and transmit whether the message is abnormal or not to the client part. The system designed and implemented in this paper will be utilized as a technology that can mutually share and exchange medical information in a customized healthcare service that reflects the needs of various customers and a telemedicine system. © 2021 IEEE.

Quality Assurance in Pre-Endoscopic Evaluation

Endoscopy is an essential component of gastroenterology, allowing for the diagnosis and management of a variety of gastrointestinal diseases. Although most endoscopies are considered to be low risk procedures, several factors including the sedation, patient, and procedure play a role in determining overall risk. Patient assessment prior to endoscopy is essential to risk-stratification and provides an opportunity to review comorbidities, adjust medications if necessary, and identify an optimal sedation plan. Several best practice recommendations and guidelines have been developed to ensure that safe, high-quality endoscopies are performed to minimize risks and optimize outcomes. The purpose of this review is to highlight best practices related to pre-endoscopic evaluation and, when available, review quality indicators.

COV-ECGNET: COVID-19 detection using ECG trace images with deep convolutional neural network.

The reliable and rapid identification of the COVID-19 has become crucial to prevent the rapid spread of the disease, ease lockdown restrictions and reduce pressure on public health infrastructures. Recently, several methods and techniques have been proposed to detect the SARS-CoV-2 virus using different images and data. However, this is the first study that will explore the possibility of using deep convolutional neural network (CNN) models to detect COVID-19 from electrocardiogram (ECG) trace images. In this work, COVID-19 and other cardiovascular diseases (CVDs) were detected using deep-learning techniques. A public dataset of ECG images consisting of 1937 images from five distinct categories, such as normal, COVID-19, myocardial infarction (MI), abnormal heartbeat (AHB), and recovered myocardial infarction (RMI) were used in this study. Six different deep CNN models (ResNet18, ResNet50, ResNet101, InceptionV3, DenseNet201, and MobileNetv2) were used to investigate three different classification schemes: (i) two-class classification (normal vs COVID-19); (ii) three-class classification (normal, COVID-19, and other CVDs), and finally, (iii) five-class classification (normal, COVID-19, MI, AHB, and RMI). For two-class and three-class classification, Densenet201 outperforms other networks with an accuracy of 99.1%, and 97.36%, respectively; while for the five-class classification, InceptionV3 outperforms others with an accuracy of 97.83%. ScoreCAM visualization confirms that the networks are learning from the relevant area of the trace images. Since the proposed method uses ECG trace images which can be captured by smartphones and are readily available facilities in low-resources countries, this study will help in faster computer-aided diagnosis of COVID-19 and other cardiac abnormalities.

Incomplete Trifascicular Block and Mobitz Type II Atrioventricular Block in COVID-19.

A 74-year-old female with a history of diabetes presented with chest pain and shortness of breath for two days. She was hypoxic to an oxygen saturation of 60% in the emergency department, requiring bilevel positive airway pressure (BiPAP) to maintain saturations. Chest X-ray demonstrated bilateral hazy opacities suspicious for viral pneumonia. Coronavirus disease 2019 (COVID-19) was confirmed. Right bundle branch block (RBBB) with left anterior fascicular block was noted on admission electrocardiogram (ECG). Cardiac enzymes and brain natriuretic peptide levels were within normal limits. After noting frequent pauses on telemetry, a repeat ECG was performed that demonstrated RBBB with left posterior fascicular block as well as second-degree atrioventricular block (Mobitz type II). Transcutaneous pacing pads were placed, and atropine was placed at the bedside. Cardiac enzymes remained negative. Interleukin-6 levels were elevated at 159 pg/mL. Hydroxychloroquine was deferred due to the patient's arrhythmia and prolonged QTc. Tocilizumab was deferred due to the patient's age. The patient's oxygen requirements and mental status continued to worsen. She continued to desaturate despite maximal BiPAP therapy and eventually died. Cardiac involvement in COVID-19, whether caused primarily by the virus, secondary to its clinical sequelae, or even due to its treatment, cannot be ignored. Further high-quality research is needed to clarify the cardiac pathophysiology. Thorough cardiac exams with electrocardiographic correlation should be performed on all patients with COVID-19. Clinicians should not hesitate to consult cardiovascular services in the event of abnormality.