Detection Of COVID-19 Patients Research Articles

Detection of COVID-19 Patients Using Machine Learning Techniques: A Nationwide Chilean Study.

Epivigila is a Chilean integrated epidemiological surveillance system with more than 17,000,000 Chilean patient records, making it an essential and unique source of information for the quantitative and qualitative analysis of the COVID-19 pandemic in Chile. Nevertheless, given the extensive volume of data controlled by Epivigila, it is difficult for health professionals to classify vast volumes of data to determine which symptoms and comorbidities are related to infected patients. This paper aims to compare machine learning techniques (such as support-vector machine, decision tree and random forest techniques) to determine whether a patient has COVID-19 or not based on the symptoms and comorbidities reported by Epivigila. From the group of patients with COVID-19, we selected a sample of 10% confirmed patients to execute and evaluate the techniques. We used precision, recall, accuracy, -score, and AUC to compare the techniques. The results suggest that the support-vector machine performs better than decision tree and random forest regarding the recall, accuracy, -score, and AUC. Machine learning techniques help process and classify large volumes of data more efficiently and effectively, speeding up healthcare decision making.

Application of machine learning and medical imaging in the detection of COVID-19 patients: A review article.

ABSTRACTIn the present study, a particular technique of artificial intelligence (AI) is applied for diagnosis and classifying medical images of patients with coronavirus disease (COVID-19). Chest radiography and laboratory-based tests are two of the most important diagnostic approaches for the detection of people with the coronavirus. Recently, a lot of studies have been carried out on using AI techniques for achieving appropriate diagnosis of COVID-19 patients using computed tomography (CT) of the chest. The present study is reviewing all available literature that have investigated the role of chest CT toward AI in the detection of COVID-19. As a novel field of computer science, AI focuses on teaching computers to be capable of learning complex tasks and decide about their solution methods. In this study, we used Matlab, Payton, and Fortran software as well as other software which are suitable for this research. In this regard, the present review study is aimed to collect the information from all the studies conducted on the role of AI as a decisive and comprehensive technology for the detection of coronavirus in patients to have a more accurate diagnosis and investigate its epidemiology.

32. Host Immune-Protein Signature Combining TRAIL, IP-10 and CRP for Early and Accurate Prediction of Severe COVID-19 Outcome

BackgroundAccurately identifying COVID-19 patients at-risk to deteriorate remains challenging. Dysregulated immune responses impact disease progression and development of life-threatening complications. Tools integrating host immune-protein expression have proven useful in determining infection etiology and hold potential for prognosticating disease severity.MethodsAdults with COVID-19 were enrolled at medical centers in Israel, Germany, and the United States (Figure 1). Severe outcome was defined as intensive care unit admission, non-invasive or invasive ventilation, or death. Tumor necrosis factor related apoptosis inducing ligand (TRAIL), interferon gamma inducible protein-10 (IP-10) and C-reactive protein (CRP) were measured using an analyzer providing values within 15 minutes (MeMed Key®). A signature indicating the likelihood of severe outcome was derived generating a score (0-100).Description of derivation cohort RT-PCR, reverse transcription polymerase chain reaction.ResultsBetween March and November 2020, 518 COVID-19 patients were enrolled, of whom 394 were eligible, 29% meeting a severe outcome. Age ranged between 19-98 (median 61.5), with 59.1% male. Patients meeting severe outcomes exhibited higher levels of CRP and IP-10 and lower levels of TRAIL (Figure 2; p < 0.001). Likelihood of severe outcome increased significantly (p < 0.001) with higher scores. The signature’s area under the receiver operating characteristic curve (AUC) was 0.86 (95% confidence interval: 0.81-0.91). Performance was not confounded by age, sex, or comorbidities and was superior to IL-6 (AUC 0.77; p = 0.033) and CRP (AUC 0.78; p < 0.001). Clinical deterioration proximal to blood draw was associated with higher signature score. Scores of patients meeting a first outcome over 3 days after blood draw were significantly (p < 0.001) higher than scores of non-severe patients (Figure 3). Moreover, the signature differentiated patients who further deteriorated after meeting a severe outcome from those who improved (p = 0.004) and projected 14-day survival probabilities (p < 0.001; Figure 4).TRAIL, IP-10, CRP and the severity signature score are differentially expressed in severe and non-severe COVID-19 infection Dots represent patients and boxes denote median and interquartile range (IQR)The signature score of patients meeting a severe outcome on or after the day of blood draw is significantly (p < 0.001) higher than the signature score of non-severe patients. Dots represents patients and boxes denote median and IQRKaplan-Meier survival estimates for signature score bins ConclusionThe derived signature combined with a rapid measurement platform has potential to serve as an accurate predictive tool for early detection of COVID-19 patients at risk for severe outcome, facilitating timely care escalation and de-escalation and appropriate resource allocation. Disclosures Alon Angel, n/a, MeMed (Employee, Shareholder) Niv Samuel Mastboim, BSc, MeMed (Employee, Shareholder) Oded Shaham, PhD, MeMed (Employee, Shareholder) Tahel Ilan Ber, MD, MeMed (Employee, Shareholder) Roy Navon, MSc, MeMed (Employee, Shareholder) Einav Simon, PhD, MeMed (Employee, Shareholder) Michal Rosenberg, PhD, MeMed (Employee) Yael Israeli, PhD, MeMed (Employee) Mary Hainrichson, PhD, MeMed (Employee, Shareholder) Noa Avni, PhD, MeMed (Employee) Eran Reiner, MD, MeMed (Employee) Kfir Oved, MD, PhD, MeMed (Board Member, Employee, Shareholder) Ilya Kagan, MD, MeMed (Scientific Research Study Investigator) Shaul Lev, M.D, MeMed (Scientific Research Study Investigator) Dror Diker, MD, MeMed (Scientific Research Study Investigator) Amir Jarjou’i, MD, MeMed (Scientific Research Study Investigator) Ramzi Kurd, MD, MeMed (Scientific Research Study Investigator) Guy Danziger, MD, MeMed (Scientific Research Study Investigator) Cihan Papan, MD, MeMed (Scientific Research Study Investigator) Sergey Motov, MD, MeMed (Scientific Research Study Investigator) Maanit Shapira, Ph.D, MeMed (Scientific Research Study Investigator) Tanya Gottlieb, PhD, MeMed (Employee, Shareholder) Eran Eden, PhD, MeMed (Board Member, Employee, Shareholder)

S3290 Thermographic Endoscopy for Dynamic Thermal Analysis of Gastrointestinal Disease

Introduction: To date the temperature has not been recognized an important factor in endoscopic fields, though it is physical finding to evaluate the disease. The medical common sense about thermic homeostasis interrupted notifying the availability of temperature measurement for digestive inflammation. Recently the real time monitoring by thermography in esophagus has been reported to prevent patients from burning during the cardiac ablation therapy to treat atrial fibrillation. The thermography has been used for evaluating the Raynaud' s symptom too. The portable thermography has been introduced into military uses or detection of COVID-19 patients in these days. Methods: 1) Thermographic images were obtained by a thermographic unit attached to a conventional colonoscope. It was inserted over the scope style. The protocol was approved by IRB in my hospital. 2) The prototype thermographic unit was composed of 3 parts (optical lens, image sensor (Seek Thermal or FLIR;USA), microprocessor and USB). 3) In the pilot study, the control group consisted of 4 subjects without inflammation and disease group consisted of 4 patients (2 with ulcerative colitis and 2 with polyp or early cancer) were examined. 4) Transient thermal response (TTR) was evaluated by measuring mucosal temperature changes just before and after spraying cool water. Results: 1) The temperature resolution of thermographic endoscope was 0.1 °C and the accuracy was 0.5°C. The measuring time was 0.4 second enough short to evaluate TTR. 2)The colonic temperatures in the control group were as stable as data measured by thermistor thermometer through the forceps channel (DDW2021). On the contrary, that in UC was 0.5∼1.0°C higher in the area with inflammation than in normal mucosa. 3) The increases of the mucosal temperature in UC patients were correlated to Mayor's endoscopic sub-score. 4) On the TTR, temperature recovery after spraying cool water was significantly delayed parts with inflammation in a UC patient compared to that of control group. 6) The hypervascular mucosa in tumor had shorter recovery time than normal mucosa on the TTR analysis. This mechanism enabled the thermographic endoscope to discriminate the lesion. Conclusion: The temperature and image resolution of thermography should be improved in future, thogh they are not adquate compared to the present conventional endoscope. The thermographic endoscope equipped the TTR function has the possibility to clarify the grade of inflammation and to figure out the tumor..

Detection of COVID-19 Patients from CT Scan and Chest X-ray Data Using Modified MobileNetV2 and LIME.

The COVID-19 global pandemic caused by the widespread transmission of the novel coronavirus (SARS-CoV-2) has become one of modern history’s most challenging issues from a healthcare perspective. At its dawn, still without a vaccine, contagion containment strategies remained most effective in preventing the disease’s spread. Patient isolation has been primarily driven by the results of polymerase chain reaction (PCR) testing, but its initial reach was challenged by low availability and high cost, especially in developing countries. As a means of taking advantage of a preexisting infrastructure for respiratory disease diagnosis, researchers have proposed COVID-19 patient screening based on the results of Chest Computerized Tomography (CT) and Chest Radiographs (X-ray). When paired with artificial-intelligence- and deep-learning-based approaches for analysis, early studies have achieved a comparatively high accuracy in diagnosing the disease. Considering the opportunity to further explore these methods, we implement six different Deep Convolutional Neural Networks (Deep CNN) models—VGG16, MobileNetV2, InceptionResNetV2, ResNet50, ResNet101, and VGG19—and use a mixed dataset of CT and X-ray images to classify COVID-19 patients. Preliminary results showed that a modified MobileNetV2 model performs best with an accuracy of 95 ± 1.12% (AUC = 0.816). Notably, a high performance was also observed for the VGG16 model, outperforming several previously proposed models with an accuracy of 98.5 ± 1.19% on the X-ray dataset. Our findings are supported by recent works in the academic literature, which also uphold the higher performance of MobileNetV2 when X-ray, CT, and their mixed datasets are considered. Lastly, we further explain the process of feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which contributes to a better understanding of what features in CT/X-ray images characterize the onset of COVID-19.

EVALUATION OF INFECTION MARKERS IN THE PATIENTS WITH COVID-19 AT TERTIARY CARE INSTITUTE: A PROSPECTIVE STUDY

Objectives: The outbreak of 2019 Novel coronavirus disease (COVID-19) has caused global attention. Due to its rapid spread worldwide, COVID-19 was declared as a public health emergency by the World Health Organization. Although most patients have mild symptoms and good prognosis, severe COVID-19 cases may present with acute respiratory distress syndrome (ARDS) and systemic inammation. Thus, it is to evaluate the disease severity and investigate possible biomarkers so as to make fast and correct clinical decisions. Methods: This is a single center, prospective study conducted at Nalanda Medical College and Hospital Patna. We enrolled 100 OPD and inhospital patients with COVID- 19 admitted to the Nalanda Medical College and Hoapital and analyzed infection biomarkers in covid patients who had been tested for ferritin, PCT, CRP, IL-6 and procalcitonin. Results:Average level of Ferritin in Covid-19 patients is 18746.34 ng/ml whereas in control patients it is around 226.29 ng/ml. Around 97 percent of patients affected with COVID-19 having Ferritin level very high from the referred range. Average level of D-dimer in Covid patients is 2807.16 ng/ml and in non COVID patients 276.04 ng/ml. All the covid patients have D-dimer level very high than the referred range. Average level of Procalcitonin in Covid and control patients is 0.93 and 0.53 ng/ml respectively. Around three fourth of covid patients and one third of control patients have this level higher than the referred range. CRPlevel of COVID patients are very high (on an average 483.48 mg/l) in comparison to non covid patients (on an average 6.29 mg/l). All the covid patients have IL-6 level much higher than the referred range. Conclusion: Our ndings suggest that level of Ferritin, D-dimer, PCT, CRP and IL-6 can be used to predict the result of COVID-19 test. They can help in detection of COVID-19 patients.

Molecular Review Covid19 from the Pathogenesis and Transmission Aspect

Introduction: Corona disease-19 virus (COVID-19) spread and caused a pandemic that affected people all over the world. COVID-19 is also called Severe Acute Respiratory Syndrome-Coronavirus Disease (SARS-CoV). Discussion: COVID-19 is a β-coronavirus serotype which is a single strain of RNA virus and was an outbreak in 2002 (SARS-CoV) and 2012 (MERS-CoV). COVID-19 has Open Reading Frames (ORFs) consisting of Spikes (S), Envelopes (E), Membranes (M), and Nucleocapsids (N) with S parts being a glycoprotein that can attach to receptors owned by host cells, the receptors are CD 26, ACE-2, Ezrin, and Cyclophilins with the main receptor being ACE-2 in the lung organs. Process would evoke a host body's immune response consisting of natural and adaptive immune systems, involving the Antigen Presenting Cell (APC) system which consists of two, namely: Major Histocompatibility Complex (MHC) class I and II. APC could also generate adaptive immune system, consists of B and T cells. COVID-19 had the ability to survive in B and T cells, so that cytokine-chemokine secretion continues to be known as cytokine storm that trigger Acute Respiratory Distress Syndrome (ARDS) and death. Conclusion: The recovery prognosis of COVID-19 depended on the detection of COVID-19 patients because it was related to the severity of ARDS, so the earlier it was detected, the greater the chance of recovery.

Laboratory Parameters in Detection of COVID-19 Patients with Positive RT-PCR; a Diagnostic Accuracy Study.

The role of laboratory parameters in screening of COVID-19 cases has not been definitely established. This study aimed to evaluate the accuracy of laboratory parameters in predicting cases with positive RT-PCR for COVID-19. This diagnostic accuracy study was conducted on suspected COVID-19 patients, who presented to Behpooyan Clinic Medical center in Tehran (Iran) from 22 Februaryto 14 March, 2020. Patients were divided into two groups based on the results of real time reverse transcriptase-polymerase chain reaction (RT-PCR) for COVID-19, and the accuracy of different laboratory parameters in predicting cases with positive RT-PCR was evaluated using area under the ROC curve (AUC). Two hundred cases with the mean age of 41.3± 14.6 (range: 19-78) years were studied (0.53% male). The result of RT-PCR for COVID-19 was positive in 70 (35%) cases. Patients with positive RT-PCR had significantly higher neutrophil (NEU) count (p = 0.0001), and C-reactive protein (CRP) (p = 0.04), lactate dehydrogenase (LDH) (p = 0.0001), aspartate aminotransferase (AST) (p = 0.001), alanine aminotransferase (ALT) (p = 0.0001), and Urea (p = 0.001) levels in serum. In addition, patients with positive RT-PCR had lower white blood cell (WBC) count (p = 0.0001) and serum albumin level (p = 0.0001) compared to others. ALT (AUC = 0.879), CRP (AUC = 0.870), NEU (AUC = 0.858), LDH (AUC = 0.835), and Urea (AUC = 0.835) had very good accuracy in predicting cases with positive RT-PCR for COVID-19, respectively. Our findings suggest that level of LDH, CRP, ALT and NEU can be used to predict the result of COVID-19 test. They can help in detection of COVID-19 patients.