Diagnosis Of COVID-19 Research Articles

Integrated ensemble CNN and explainable AI for COVID-19 diagnosis from CT scan and X-ray images

In light of the ongoing battle against COVID-19, while the pandemic may eventually subside, sporadic cases may still emerge, underscoring the need for accurate detection from radiological images. However, the limited explainability of current deep learning models restricts clinician acceptance. To address this issue, our research integrates multiple CNN models with explainable AI techniques, ensuring model interpretability before ensemble construction. Our approach enhances both accuracy and interpretability by evaluating advanced CNN models on the largest publicly available X-ray dataset, COVIDx CXR-3, which includes 29,986 images, and the CT scan dataset for SARS-CoV-2 from Kaggle, which includes a total of 2,482 images. We also employed additional public datasets for cross-dataset evaluation, ensuring a thorough assessment of model performance across various imaging conditions. By leveraging methods including LIME, SHAP, Grad-CAM, and Grad-CAM++, we provide transparent insights into model decisions. Our ensemble model, which includes DenseNet169, ResNet50, and VGG16, demonstrates strong performance. For the X-ray image dataset, sensitivity, specificity, accuracy, F1-score, and AUC are recorded at 99.00%, 99.00%, 99.00%, 0.99, and 0.99, respectively. For the CT image dataset, these metrics are 96.18%, 96.18%, 96.18%, 0.9618, and 0.96, respectively. Our methodology bridges the gap between precision and interpretability in clinical settings by combining model diversity with explainability, promising enhanced disease diagnosis and greater clinician acceptance.

Influence of Ethnicity and Deprivation on Occurrence of Paget’S Disease in Greater Manchester, UK

There is important variation in the occurrence of Paget’s disease in different regions and populations. There are though few data concerning the occurrence of clinically diagnosed disease in black and ethnic minority groups in the United Kingdom (UK). We undertook an anonymised search using an integrated primary and secondary care-based database in Greater Manchester, covering a population of over 3 million people. We looked also among those with a first positive COVID test, the influence of Paget’s disease on subsequent admission to hospital within 28 days. Within our database, there were 534,571 people aged 60 years and over alive on 1 January 2020. The majority were white (84%) with 4.7% identifying as Asian or Asian British, and 1.27% Black or Black British. There were 931 with clinically diagnosed Paget’s disease. Overall prevalence in the greater Manchester area was 0.174%. Prevalence was higher in men than women (0.195 vs 0.155%). Compared to the prevalence of Paget’s in whites (0.179%) the prevalence was lower among those identifying as Asian or Asian British (0.048%) and higher among those identifying as Black or Black British (0.344%). Prevalence increased with increasing deprivation. Clinically diagnosed Paget’s disease is uncommon affecting 0.174% of men and women aged 60 or more years. Within Greater Manchester, it was more common in those identifying as Black or Black British and less common in those identifying as Asian or Asian British.

Recommendations for COVID-19 Testing

<no abstract>

The Effects of SSRIs and Antipsychotics on Long COVID Development in a Large Veteran Population

The development of Long COVID is a complex disease process that may be partially driven by neuroinflammation. Antipsychotics have been shown to exert neuroprotective effects under certain conditions. Our study aimed to determine if veterans treated with antipsychotics and/or selective serotonin reuptake inhibitors (SSRIs) for a psychiatric condition had a reduced risk of developing long-term COVID. We conducted a retrospective cohort study with two cohorts of patients based on the COVID-19 wave in which the patient’s initial infection occurred (Cohort 1: alpha/beta waves, and Cohort 2: delta/omicron waves) with stratification by age. A multivariate logistic regression model was used to evaluate the association between the use of antipsychotics and Long COVID diagnosis. In Cohort 1, antipsychotic use was associated with 43% and 34% reductions in the odds of developing Long COVID in patients aged <65 and >65 years, respectively. This association was reduced in the second cohort to 11% in patients aged <65 years and without an association over 65 years of age. SSRIs showed no benefit in either age group or cohort. Our results show that antipsychotic use for the treatment of a mental health condition was associated with a reduction in the risk of developing Long COVID, and the magnitude of this reduction varied between COVID-19 cohorts.

Features of the course of the new coronavirus infection COVID-19 in chronic kidney disease

Purpose of the study. Study of the characteristics of the course of the new coronavirus infection COVID-19 in chronic kidney disease (CKD). Materials and methods. A total of 182 patients who were in the State Budgetary Institution “Emergency Medical Care Hospital” (Cheboksary) with a confirmed diagnosis of COVID-19 were examined. Results. A high incidence of CKD in hospitalized patients is shown. In CKD, there is a high mortality from COVID-19, statistically significant for CKD stage 3, but not for CKD stages 1-2. A number of clinical and laboratory parameters associated with an increased risk of adverse outcome have been identified. CKD is an independent risk factor that increases the risk of death when combined with these parameters. The positive effect of Janus kinase inhibitors is reflected when they are prescribed in the group under 65 years of age and in the first days of patient admission. Conclusion. The results of the study indicate the necessity of studying kidney function in patients with a new coronavirus infection. Patients with chronic kidney disease stages 3-4 require close dynamic monitoring as a risk group for severe disease, affecting survival.

Electrochemical Immunosensors on Laser-Induced Graphene Platforms for Monitoring of Anti-RBD Antibodies After SARS-CoV-2 Infection

The COVID-19 pandemic, caused by the SARS-CoV-2 virus, has posed a major challenge to global health. The development of fast, accurate, and accessible diagnostic methods is essential in controlling the disease and mitigating its impacts. In this context, electrochemical biosensors present themselves as promising tools for the efficient monitoring of SARS-CoV-2 infection. We have developed a highly specific biosensor for the detection of anti-SARS-CoV-2 antibodies in patient sera. The use of the RBD-S region as an antigen, although purified to minimize cross-linking, poses a specific challenge. The structural similarity between SARS-CoV-2 and other respiratory viruses, as well as the complexity of the serum matrix, hinders robust analytical strategies to ensure diagnostic accuracy. This work presents a novel immunosensor for COVID-19 diagnosis using laser-induced graphene (LIG) electrodes subjected to electrochemical reduction with graphene (named rGraphene-LIG). In the present study, we chose an initial approach focused on demonstrating the concept and evaluating the feasibility of the rGraphene-LIG sensor for SARS-CoV-2 detection. The rGraphene-LIG electrodes presented a notable current increase for the redox probe in the aqueous solution of a mixture of 5 mmol L−1 potassium ferricyanide/ferrocyanide ([Fe(CN)6]3−/[Fe(CN)6]4−) in 0.1 mol L−1 KCl (pH set at 7.4). As a proof of concept, the rGraphene-LIG electrode was applied for antibody determination in real samples using cyclic voltammetry, and a limit of detection (LOD) of 0.032 μg L−1 was achieved. When determining antigens in commercial samples, we obtained an LOD of 560 ηg mL−1 and a limit of quantification of 1677 ηg mL−1. The results of the electrochemical experiments were in accordance with the surface roughness obtained from atomic force microscopy images. Based on these results, the rGraphene-LIG electrode is shown to be an excellent platform for immunoglobulin detection when present in individuals after antigenic exposure caused by SARS-CoV-2.

Caring for Long Covid patients in primary healthcare: a cross-sectional study on general practitioners’ knowledge, perception and experience in Belgium and Malta

BackgroundAt least 10% of Covid-19 recovered individuals experience persistent symptoms (Long Covid). Primary healthcare and general practitioners (GPs) are at the forefront in their care. In this study, GPs’ knowledge, perceptions and experiences with Long Covid, and the definition used in two countries, are investigated to provide insight into GPs’ care for Long Covid patients at a cross-country level.MethodsA cross-sectional study targeted towards GPs was conducted in Belgium and Malta during spring and early summer 2022. An online survey consisting of 15 questions on Long Covid was disseminated. Additionally, country-specific practice and demographic characteristics were collected. Descriptive and logistic regression analyses were performed.ResultsA total of 150 GPs (Belgium = 105; Malta = 45) responded. Female GPs represented 58.0%, median age was 49 years (IQR: 37–61). Concerning GPs’ knowledge and perception on Long Covid, in both countries, most GPs reported insufficient scientific knowledge and information on Long Covid diagnosis and treatment. Access to educational material was limited and an awareness-rising campaign on Long Covid was deemed necessary. Moreover, two out of three GPs stated that Long Covid patients were not well followed up by primary healthcare in mid-2022. For diagnosing Long Covid, 54.7% required a positive Covid-19 test, more often among Belgian GPs than Maltese (64.3% vs. 45.2%, p = 0.036). To assess Long Covid, GPs mainly applied diagnostic criteria by themselves (47.3%) in combination with persistent symptoms (4 weeks to 5 months). Most GPs had experience with Long Covid patients in their practice, regardless of practice type and GPs’ country, sex or age (p = 0.353; p = 0.241; p = 0.194; p = 0.058). Although most GPs (94.7%) stated that Long Covid patients should follow multidisciplinary approach, 48.3% reported providing care for these patients themselves or with GP colleagues and only 29.8% by multidisciplinary cooperation. ConclusionsGPs frequently provide (multidisciplinary) care to Long Covid patients and GPs’ care showed similarities at cross-country level. Although GPs perceive lack of scientific knowledge and educational material on Long Covid, similar diagnostic criteria among GPs were noted. Uniform evidence-based guidelines, scientific support and training for GP across Europe must be a priority to enhance their treatment approach to Long Covid.

Clinical Outcomes of Pediatric Cancer Patients with COVID-19: A Cross-Sectional Study

Background: Considering the widespread COVID-19 pandemic and its impact, especially on children, particularly those with cancer, in terms of transmission risk, mortality, and the occurrence of the disease based on various studies in different countries, we decided to conduct this study to improve the care of children with cancer regarding COVID-19. Materials and Methods: A descriptive cross-sectional study with a confirmed diagnosis of COVID-19 consisted of obtaining 20 mL of blood samples from the participants in a random manner. Diagnostic examinations, including CT scans, chest X-rays, and a range of hematologic and blood tests, such as complete blood count, ESR, CRP, and D-Dimer, were performed on all patients. Results: This study contains 26 males and 12 females. The mean age of the patients was 3.81 ± 6.35 years. The majority of cancer patients with COVID-19 were diagnosed with Acute Lymphoblastic Leukemia (ALL) (47.7%). The most common symptoms of COVID-19 in the patients were fever (73.7%), cough (39.5%), and nausea/vomiting (21.1%). 40.4% of the patients had pathological findings suggestive of COVID-19 on their chest CT scans. 60.52% of the patients had an elevated Erythrocyte Sedimentation Rate (ESR), and 73.68% had an elevated C-reactive protein (CRP) level. Conclusion: Despite the outcomes of COVID-19 in most children with cancer in this study, children with cancer still experience risks from COVID-19, and it is unclear how delays and interruptions in cancer treatment and direct damage from the virus may impact long-term outcomes in these patients.

The effects of CoVID-19 diagnosis and national lockdown on hearing loss, tinnitus, vertigo and migraine: the outcome of a prospective cohort study.

The effects of CoVID-19 diagnosis and national lockdown on hearing loss, tinnitus, vertigo and migraine: the outcome of a prospective cohort study.

Clinical and immunologic abnormalities in COVID-19

Objective: to find approaches to improve diagnostics of the debut of rheumatic manifestations, associated with COVID-19.Material and methods. Data from 1000 patients from the COVID-19 registry were included in the prospective cohort study. In all patients, the diagnosis of COVID-19 was confirmed by polymerase chain reaction. Of these patients, 380 (41.8% men and 58.2% women, mean age 47.0±2.5 years) had rheumatic manifestations. Patients were examined using routine clinical methods. Immunological markers of rheumatic diseases were determined, including antibodies against cyclic citrullinated peptide, rheumatoid factor, antiphospholipid antibodies and antinuclear factor (ANF), and an immunoblot for antinuclear antibodies was performed if ANF titer was >1:160.Results and discussion. Patients had the following rheumatic manifestations: arthralgias (in 342), myalgias (in 23), skin rashes (in 15). ANF titers >1:160 were found in 57.6% of patients. No reliable data indicating the development of an antiphospholipid syndrome were found in the study group. Lupus anticoagulant was detected in 5.7% of cases, antibodies against β2-glycoprotein in 5.7%, antibodies against cardiolipin in 3.8%. High ANF titers were found in 63.9% of patients with arthralgia. Gender-specific differences were found when analyzing the correlation between ANF titers and rheumatic manifestations: in men, high ANF tires were associated with myalgias, and in women with arthralgias. The presence of rheumatic manifestations depended directly on the severity of the disease. A correlation between arthralgia and leucopenia was also found – leucocyte count < 3,9 ‧109 /L was a predictor of arthralgias. The sensitivity and specificity of the model were 99.3 and 91.2%, respectively.Conclusion. The results suggest that COVID-19 can provoke the development of immunological abnormalities that may subsequently lead to the development of an autoimmune diseases (AID). The optimal approach to prevention and early detection of AID in patients with coronavirus infection caused by SARS-CoV-2 is to monitor laboratory parameters – leukocyte count and CRP level. If rheumatic manifestations are present, the use of immunological and imaging examinations is also recommended.

Management of vulnerable patients hospitalized for COVID-19 with remdesivir: a retrospective comparative effectiveness study of mortality in US hospitals.

COVID-19 remains a major public health concern, with continued resurgences of cases and substantial risk of mortality for hospitalized patients. Remdesivir has become standard-of-care for hospitalized COVID-19 patients. Given the continued evolution of the disease, clinical management relies on evidence from the current endemic period. Using the PINC AI Healthcare database, effectiveness of remdesivir was evaluated among adults hospitalized with a primary diagnosis of COVID-19 between December 2021 and February 2024. Three cohorts were analysed: adults, elderly (≥65 years), and those with documented COVID-19 pneumonia. Analyses were stratified by oxygen requirements. Patients receiving remdesivir were matched to those not receiving remdesivir using propensity score matching. Cox proportional hazards models were used to examine in-hospital mortality. 169,965 adults hospitalized for COVID-19 were included, of which 94,129 (55.4%) initiated remdesivir in the first two days of hospitalization. Remdesivir was associated with a significantly lower mortality rate as compared to no remdesivir among patients with no supplemental oxygen charges (NSOc) (aHR [95% CI]: 14-day, 0.75 [0.69-0.82]; 28-day, 0.77 [0.72-0.83]) and among those with supplemental oxygen charges (SOc): 14-day, 0.76 [0.72-0.81]; 28-day, 0.79 [0.74-0.83]) (p<0.0001, for all). Similar findings were observed for elderly patients and those hospitalized with COVID-19 pneumonia. This evidence builds on learnings from randomized controlled trials from the pandemic era to inform clinical practices. Remdesivir was associated with significant reduction in mortality for hospitalized patients including the elderly and those with COVID-19 pneumonia.

The Incidence and Characteristics of Oral Candidiasis in Patients Hospitalized for SARS-CoV-2 Infection During the Circulation of Alpha, Beta, and Delta Variants

Background: Oral candidiasis has been documented in patients with SARS-CoV-2 infection, with varying prevalence rates across geographic regions and patient demographics. This study aimed to ascertain the incidence, characteristics, and risk factors associated with the development of oral candidiasis in patients hospitalized for SARS-CoV-2 infection in a tertiary infectious diseases hospital in Romania. Methods: A retrospective analysis was conducted on adult patients hospitalized between March 2020 and December 2022 with moderate or severe forms of SARS-CoV-2 infection, for whom a culture of lingual scrapings for Candida spp. was performed. Results: A total of 294 patients were deemed eligible for inclusion in the analysis, with an incidence rate of oral candidiasis of 17.0%. The incidence of oral candidiasis was 4.2 times higher in patients with severe forms of SARS-CoV-2 infection compared to those with moderate forms. Patients with a diagnosis of COVID-19 and oral candidiasis were more likely to receive antibiotics (98.0% vs. 86.1%, p = 0.017) and corticosteroids (100% vs. 83.6%, p = 0.003) than those without oral candidiasis. These findings were associated with a 19% higher relative risk of developing oral candidiasis for patients who received corticosteroid therapy compared to those who did not, and a 13% higher relative risk for those who were administered antibiotics compared to those who were not. The presence of respiratory insufficiency increased the odds of oral candidiasis association 4.7-fold (88.0% vs. 61.1%, p &lt; 0.001). Conclusions: Although the data have been analyzed retrospectively, we have shown that individuals with severe forms of COVID-19 exhibited an elevated risk of developing oral candidiasis. The administration of antibiotics and corticosteroids was identified as a positive predictor for the development of oral candidiasis. The data presented here suggest that a key aspect of the therapeutic management of patients with SARS-CoV-2 infection should include the implementation of preventive measures to minimize the risk of secondary fungal infections.

Clinical and sociodemographic factors associated with COVID-19 in non-hospitalized patients in southwest Goiás, Brazil, 2020 to 2022

Considering that COVID-19 has had a major impact on public health around the world, we aimed to elucidate the clinical and sociodemographic characteristics of non-hospitalized patients in Quirinópolis, southwest Goiás, from 2020 to 2022. We performed a cross-sectional study, using secondary data on all suspected COVID-19 visits in Basic Health Units, bivariate data analysis and logistic regression. 18,036 suspected cases were registered with 56.1% laboratory confirmed. COVID-19 was concentrated in the central regions of the city and was more associated with the vaccinated group, which may be a reflection of the vaccine's protective effect on the worsening of symptoms. The final logistic regression model showed a higher risk of COVID-19 among mixed race (1.30; CI1:20-1.42) and young people as a protective factor (0.88; CI:0.78-0.98). Gustatory (2.78; IC:2.19-3.53) and olfactory (2.83; IC: 2.18-3.66) disorders, headache (1.11; IC: 1.02-1.11), fever (1.77; CI: 1.62-1.92) and cough (1.48; CI: 1.36-1.61) were also associated with a positive diagnosis of COVID-19. Only respiratory disease was found to be a risk factor, probably due to underreporting of other factors. COVID-19 is ubiquitous among non-hospitalized patients, with easy transmission in clusters and with striking demographic and clinical characteristics: Brown population, taste and olfactory disorders, headache, fever, cough and respiratory disease as risk factors; young people apparently as a protective factor and vaccinated more related to COVID-19 may be a reflection of the profile of the sampled group (outpatients). The ubiquity of SARS-CoV-2 in the municipality may be related to public policies promoting ineffective medicines and population behavior that contribute to the spread of the virus. In contrast, vaccines have proven effective in containing the severe disease. In the future, approaches to hospitalized patients are necessary to better understand the impacts of COVID-19.

Clinical and social importance of stool RT-PCR: a follow-up test for COVID-19 and long COVID-19

Clinical and social importance of stool RT-PCR: a follow-up test for COVID-19 and long COVID-19

Economic benefits of COVID-19 screening tests

Economic benefits of COVID-19 screening tests

The association between tobacco use and COVID-19 diagnoses in three Nordic countries: a pooled analysis.

Previous research has suggested an unexpected negative association between smoking and susceptibility to COVID-19. This study, drawing on population-based data from three Nordic countries-Sweden, Norway, and Finland-aims to investigate this association further, capitalizing on diversity introduced by different containment measures. The objective of this research was to examine the association between cigarette smoking and snus (smokeless tobacco) use and the risk of confirmed COVID-19 infection. A pooled analysis integrating original data from 547,685 participants across three countries. We used a multiple imputation approach based on conditional probabilities to impute the systematically missing covariates. The associations between tobacco use and COVID-19 infection were assessed, controlling for potential confounding factors. Current cigarette smokers had a lower risk of a confirmed COVID-19 case, whereas there was an increased risk among snus users. Our sensitivity analysis confirmed that the associations between tobacco use and COVID-19 infection risk are robust, remaining consistent regardless of whether covariate imputation was applied. Findings support a negative association between smoking and SARS-CoV-2 infection, but not the hypothesis that nicotine may be protective against the risk of contracting SARS-CoV-2 infection.

Are covid-19 tests still working?

Are covid-19 tests still working?

Understanding hospital rehabilitation using electronic health records in patients with and without COVID-19

BackgroundMany hospitalised patients require rehabilitation during recovery from acute illness. We use routine data from Electronic Health Records (EHR) to report the quantity and intensity of rehabilitation required to achieve hospital discharge, comparing patients with and without COVID-19.MethodsWe performed a retrospective cohort study of consecutive adults in whom COVID-19 testing was undertaken between March 2020 and August 2021 across three acute hospitals in Scotland. We defined rehabilitation contacts (physiotherapy, occupational therapy, dietetics and speech and language therapy) from timestamped EHR data and determined contact time from a linked workforce planning dataset. Our aim was to clarify rehabilitation required to achieve hospital discharge and so we excluded patients who died during their admission, and those who did not require rehabilitation (fewer than two specialist contacts). The primary outcome was total rehabilitation time. Secondary outcomes included the number of contacts, admission to first contact, and rehabilitation minutes per day. A multivariate regression analysis for identifying patient characteristics associated with rehabilitation time included age, sex, comorbidities, and socioeconomic status.ResultsWe included 11,591 consecutive unique patient admissions (76 [63,85] years old, 56% female), of which 651 (6%) were with COVID-19, and 10,940 (94%) were admissions with negative testing. There were 128,646 rehabilitation contacts. Patients with COVID-19 received more than double the rehabilitation time compared to those without (365 [165, 772] vs 170 [95, 350] mins, p<0.001), and this was delivered over more specialist contacts (12 [6, 25] vs 6 [3, 11], p<0.001). Admission to first rehabilitation contact was later in patients with COVID-19 (3 [1, 5] vs 2 [1, 4] days from admission). Overall, patients with COVID-19 received fewer minutes of rehabilitation per day of admission (14.1 [9.8, 18.7] vs 15.6 [10.6, 21.3], p<0.001). In our regression analyses, older age and COVID-19 were associated with increased rehabilitation time.ConclusionsPatients with COVID received more rehabilitation contact time than those without COVID, but this was delivered less intensively and was commenced later in an admission. Rehabilitation data derived from the EHR represents a novel measure of delivered hospital care.

The Current Status of OCT and OCTA Imaging for the Diagnosis of Long COVID

The Current Status of OCT and OCTA Imaging for the Diagnosis of Long COVID

Deployment of mobile application using a novel CNN model for the detection of COVID-19 thoracic disease

In January 2021 and January 2022, COVID-19 caused roughly 13,000 and 6,000 deaths respectively per day. In August 2022, 26,000 deaths per day were estimated to be caused by COVID-19, followed by 13,000 deaths per day in February 2024. The timely identification and treatment of malignant diseases can potentially lower the mortality rate. Nonetheless, the use of manual methods for diagnosing these conditions requires a meticulous and comprehensive examination, making it susceptible to errors, burdensome for healthcare professionals, and time-intensive. Hence, the objective of this study is to design and deploy a novel deep-learning model for the detection of COVID-19 thoracic diseases. A Convolutional Neural Network (CNN) with less trainable parameters was implemented. This proposed model was deployed on a mobile device using Android Studio and Flutter for the detection of COVID-19 thoracic diseases. Specificity, accuracy, precision, sensitivity, f1-score, ROC, and PR curves were used to evaluate the model's performance. Moreover, the carbon footprint as well as how responsible the proposed model is according to Responsible AI rules was also assessed. The model's evaluation results show an overall accuracy of 93.27 %, specificity of 97.33 %, precision of 93.75 %, sensitivity of 94.42 %, F1-Score of 94.06 %, ROC rate of 98.0 %, PR rate of 96.8 %. The evaluation of the mobile application shows higher generalizability on the COVID-19 dataset. Also, the overall FACETS Score representing responsible AI is 83 % and the carbon footprint (representing the amount of carbon emission emitted into the environment during model training and testing) of 416.73 g with equivalent tree months of 0.45 was obtained. This application with better performance and a low carbon footprint was deployed using Android Studio and Flutter and can assist physicians in the diagnosis of COVID-19 and related diseases.