COVID-19 Detection Based on Blood Test Parameters using Various Artificial Intelligence Methods (preprint)

In 2019, the world faced a new challenge: a COVID-19 disease caused by the novel coronavirus, SARS-CoV-2. The virus rapidly spread across the globe, leading to a high rate of mortality, which prompted health organizations to take measures to control its transmission. Early disease detection is crucial in the treatment process, and computer-based automatic detection systems have been developed to aid in this effort. These systems often rely on artificial intelligence (AI) approaches such as machine learning, neural networks, fuzzy systems, and deep learning to classify diseases. This study aimed to differentiate COVID-19 patients from others using self-categorizing classifiers and employing various AI methods. This study used two datasets: the blood test samples and radiography images. The best results for the blood test samples obtained from San Raphael Hospital, which include two classes of individuals, those with COVID-19 and those with non-COVID diseases, were achieved through the use of the Ensemble method (a combination of a neural network and two machines learning methods). The results showed that this approach for COVID-19 diagnosis is cost-effective and provides results in a shorter amount of time than other methods. The proposed model achieved an accuracy of 94.09% on the dataset used. Secondly, the radiographic images were divided into four classes: normal, viral pneumonia, ground glass opacity, and COVID-19 infection. These were used for segmentation and classification. The lung lobes were extracted from the images and then categorized into specific classes. We achieved an accuracy of 91.1% on the image dataset. Generally, this study highlights the potential of AI in detecting and managing COVID-19 and underscores the importance of continued research and development in this field.

Coronavirus Disease 2019 Combined with T. marneffei Infection Complicated by Undiagnosed HIV：A case report and literature review (preprint)

Background: Talaromycosis(TSM) commonly occurs in immunodeficient or immunosuppressed individuals, but it can also occur in healthy populations. The present case reports the COVID-19 together with human immunodeficiency virus(HIV) and TSM. Case Presentation: This report describes a 26-year-old male who presented with a fever and cough for 20 days. He was diagnosed with COVID-19 and viral pneumonia through a real-time RT-PCR assay and chest CT scan. However, his symptoms failed to improve significantly despite being treated with high-flow oxygen, levofloxacin antibiotic, and dexamethasone for 5 days. The presence of white streaks in his oral cavity, combined with the patient's history of multiple antibiotics, raised the possibility of a fungal infection. The results of the oral pharyngeal swabs indicated that he was infected with T. marnefii, which led to testing for HIV and eventually confirmed the diagnosis. Conclusion: This case demonstrates the importance of being alert to concurrent fungal infections when infecting with COVID-19 and using multiple antimicrobial agents. Additionally, when infecting with T. marnefii, it is crucial to focus on the presence of HIV infection.

Proximal immune-epithelial progenitor interactions drive chronic tissue sequelae post COVID-19 (preprint)

The long-term health effects of SARS-CoV-2, termed Post-Acute Sequelae of COVID-19 (PASC), are quickly evolving into a major public health concern, but the underlying cellular and molecular etiology remain poorly defined. There is growing evidence that PASC is linked to abnormal immune responses and/or poor organ recovery post-infection. However, the exact processes linking non-resolving inflammation, impaired tissue repair, and PASC are still unclear. In this report, we utilized a cohort of respiratory PASC patients with viral infection-mediated pulmonary fibrosis and a clinically relevant mouse model of post-viral lung sequelae to investigate the pathophysiology of respiratory PASC. Using a combination of imaging and spatial transcriptomics, we identified dysregulated proximal interactions between immune cells and epithelial progenitors unique to respiratory PASC but not acute COVID-19 or idiopathic pulmonary fibrosis (IPF). Specifically, we found a central role for lung-resident CD8+ T cell-macrophage interactions in maintaining Krt8hi transitional and ectopic Krt5+ basal cell progenitors, and the development of fibrotic sequelae after acute viral pneumonia. Mechanistically, CD8+ T cell derived IFN-{gamma} and TNF stimulated lung macrophages to chronically release IL-1{beta}, resulting in the abnormal accumulation of dysplastic epithelial progenitors in fibrotic areas. Notably, therapeutic neutralization of IFN-{gamma} and TNF, or IL-1{beta} after the resolution of acute infection resulted in markedly improved alveolar regeneration and restoration of pulmonary function. Together, our findings implicate a dysregulated immune-epithelial progenitor niche in driving respiratory PASC and identify potential therapeutic targets to dampen chronic pulmonary sequelae post respiratory viral infections including SARS-CoV-2.

Clinical pattern and diagnostic of comorbidity of respiratory tuberculosis and viral pneumonia caused by Herpesvirus Simplex, Human Cytomegalovirus and SARS-CoV-2 in patients with late-stage HIV infection with immunodeficiency (preprint)

Aim. To study features of social status, clinical pattern and diagnosis in cases of comorbidity of respiratory tuberculosis and viral pneumonia caused by Herpesvirus Simplex of type 1, Human Cytomegalovirus and SARS-CoV-2 in patients with late-stage HIV infection with immunodeficiency. Materials and methods. The prospective study included 25 patients with comorbid condition of respiratory tuberculosis with Mycobacterium tuberculosis in excreta, herpesvirus and coronavirus pneumonia, and 21 patients with respiratory tuberculosis as well as cytomegalovirus and coronavirus pneumonia (1a and 2a main groups) and, respectively, 25 and 21 similar patients, but without coronavirus pneumonia (1b and 2b comparison group) in the late stages of HIV infection with immunodeficiency. For the etiological diagnosis of herpesvirus and cytomegalovirus pneumonia, the PCR test was used for recognition of DNA of Herpesvirus Simplex of type 1 and Human Cytomegalovirus in the diagnostic material of respiratory tract and for the etiological diagnosis of coronavirus pneumonia, the PCR for recognition of RNA was used to reveal SARS-CoV-2. Statistical analysis of the data was performed by the use of the Microsoft Office Excel 2019 software for calculation of group mean, standard error of mean and confidence interval. Results. The comorbidity of respiratory tuberculosis, herpes-, cytomegalo- and coronavirus pneumonia in patients with late-stage HIV infection in the phase of progression and in the absence of ART was characterized by severe immunodeficiency and generalization of tuberculosis with multiple extrapulmonary lesions. The results displayed similarity of clinical manifestations and visualization of changes in CT-picture in cases of comorbidity the diseases which hampers their recognition due to simultaneous combination of several pathologies with similar clinical manifestations that requires a complex etiological diagnosis of the specific diseases to prescribe a timely comprehensive treatment and reduce lethality in this severe contingent of patients. Conclusion. Patients with respiratory tuberculosis and HIV infection registered in the office of tuberculosis care for HIV-infected individuals in the antituberculosis dispensary represent a group of high risk from COVID-19 infection and CVP disease, and, in cases of combination with severe immunodeficiency, HVP and CMVP, the patients should be regularly subjected to preventive studies for timely detection of COVID-19 for the purpose of their emergency isolation and treatment.

Changes in respiratory infection trends during the COVID-19 pandemic in the haematologic malignancy patients (preprint)

Background: The coronavirus disease 2019 (COVID-19) pandemic globally changed respiratory infection patterns. However, its impact on community-acquired pneumonia (CAP) in high risk patients with haematological malignancies (HM) is uncertain. We aimed to examine CAP aetiology changes in patients with HM pre- and post-COVID-19 pandemic. Methods: This retrospective study included 524 HM patients hospitalised with CAP between March 2018 and February 2022. Those who underwent bronchoscopy within 24 hours after admission to identify CAP aetiology were included. Data on patient characteristics, laboratory findings, and results of bronchioalveolar lavage fluid cultures and PCR tests were analysed to compare etiological changes and identify in-hospital mortality risk factors. Results: Patients were divided into pre-COVID-19 (44.5%) and post-COVID-19 (55.5%) groups. This study found a significant decrease in viral CAP in the post-COVID-19 era, particularly for influenza A, parainfluenza, adenovirus, and rhinovirus (3.0% vs. 0.3%, respectively, P = 0.036; 6.5% vs. 0.7%, respectively, P = 0.001; 5.6% vs. 1.4%, respectively, P = 0.015; 9.5% vs. 1.7%, respectively, P < 0.001). Bacterial, fungal, and unknown CAP aetiologies remain unchanged. Higher Sequential Organ Failure Assessment scores and lower platelet count correlated with in-hospital mortality after adjusting for potential confounding factors. Conclusion: The incidence of CAP in HM patients did not decrease after COVID-19. Additionally, CAP aetiology among patients with HM changed following the COVID-19 pandemic, with a significant reduction in viral pneumonia while bacterial and fungal pneumonia persisted. Further studies are required to evaluate the impact of COVID-19 on the prognosis of patients with HM and CAP.

ACE2 and COVID-19 and the resulting ARDS.

This article reviews the correlation between ACE2 and COVID-19 and the resulting acute respiratory distress syndrome (ARDS). ACE2 is a crucial component of the renin-angiotensin system (RAS). The classical ACE-angiotensin Ⅱ (Ang II)-angiotensin type 1 receptor (AT1R) axis and the ACE2-Ang(1-7)-Mas counter-regulatory axis play an essential role in RAS system. ACE2 antagonises the activation of the classical RAS ACE-Ang II-AT1R axis and protects against lung injury. Similar to severe acute respiratory syndrome-related coronavirus, 2019 novel coronavirus (2019-nCoV) also uses ACE2 for cell entry. ARDS is a clinical high-mortality disease which is probably due to the excessive activation of RAS caused by 2019-nCoV infection, and ACE2 has a protective effect on ARDS caused by COVID-19. Because of these protective effects of ACE2 on ARDS, the development of drugs enhancing ACE2 activity may become one of the most promising approaches for the treatment of COVID-19 in the near future. In the meantime, however, the use of RAS blockers such as ACE inhibitors and angiotensin II receptor blockers that inhibit the damaging (ACE-Ang II) arm of the RAS cascade in the lung may also be promising. Trial registration number: NCT04287686.