Diagnostic performance of standardized typical CT findings for COVID-19: a systematic review and meta-analysis.

OBJECTIVE: To meta-analyze diagnostic performance measures of standardized typical CT findings for COVID-19 and examine these measures by region and national income. METHODS: MEDLINE and Embase were searched from January 2020 to April 2022 for diagnostic studies using the Radiological Society of North America (RSNA) classification or the COVID-19 Reporting and Data System (CO-RADS) for COVID-19. Patient and study characteristics were extracted. We pooled the diagnostic performance of typical CT findings in the RSNA and CO-RADS systems and interobserver agreement. Meta-regression was performed to examine the effect of potential explanatory factors on the diagnostic performance of the typical CT findings. RESULTS: We included 42 diagnostic performance studies with 6777 PCR-positive and 9955 PCR-negative patients from 18 developing and 24 developed countries covering the Americas, Europe, Asia, and Africa. The pooled sensitivity was 70% (95% confidence interval [CI]: 65%, 74%; I2 = 92%), and the pooled specificity was 90% (95% CI 86%, 93%; I2 = 94%) for the typical CT findings of COVID-19. The sensitivity and specificity of the typical CT findings did not differ significantly by national income and the region of the study (p > 0.1, respectively). The pooled interobserver agreement from 19 studies was 0.72 (95% CI 0.63, 0.81; I2 = 99%) for the typical CT findings and 0.67 (95% CI 0.61, 0.74; I2 = 99%) for the overall CT classifications. CONCLUSION: The standardized typical CT findings for COVID-19 provided moderate sensitivity and high specificity globally, regardless of region and national income, and were highly reproducible between radiologists. CRITICAL RELEVANCE STATEMENT: Standardized typical CT findings for COVID-19 provided a reproducible high diagnostic accuracy globally. KEY POINTS: Standardized typical CT findings for COVID-19 provide high sensitivity and specificity. Typical CT findings show high diagnosability regardless of region or income. The interobserver agreement for typical findings of COVID-19 is substantial.

Detection of COVID Using Deep Learning: A Review

As we all are aware of the fact that India's population is increasing expeditiously, automatic diagnosis of diseases is now crucial topic in medical sciences. Coronavirus has expanded massively, and it is among the one of the most frightful and dangerous infection in latest years. The deadly virus was found in China first, and then, it mutated throughout the world. Hence, automated illness identification provides results that are uniform and quick, and thus, mortality rate can be reduced. Most of countries including ours (India) suffers from lack of testing kits whenever new wave of COVID hits. Therefore, many researchers worked on various deep learning based, machine learning-based approaches for diagnosis of this virus using X-rays and CT scans of lungs. So far, it has affected over 50.9 crore people and caused the deaths of 62.2 lakhs people. Here, in this study, comprehensive survey of fifteen studies is presented where various deep learning, and transfer learning approaches are compared for their efficiency and accuracy. The goal of study here is to inspect and analyse various deep learning models including transfer learning models used, also explore the datasets used, preprocessing techniques used, and compare these models to find which model provide us with optimal and best results. The study can help in smooth implementation of the suggested work in future which can be further, then fine-tuned to get the best results possible. Deep learning provides an easy solution to the COVID problem as they perform best in detection and evaluation. It is found during this study that CNN model hybridized with other models provide better accuracy then CNN alone. Ensemble learning methods also improves the accuracy. Also, before training any model dataset acquired need to be preprocessed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

[Recommendations for the management of COVID 19 patients regarding proarrhythmic effects of some current treatments, specifically if these patients suffer from arrhythmias, and for those receiving antiarrhythmic therapy.]

Recommendation provides information to employees of medical departments at any level and primarily primary care about the possible proarrhythmic and adverse effects of drugs used for the treatment of COVID-19 patients and the features of therapy for COVID-19 patients with heart rhythm and conduction disorders receiving permanent antiarrhythmic therapy.

Detection of COVID Using Deep Learning: A Review

As we all are aware of the fact that India's population is increasing expeditiously, automatic diagnosis of diseases is now crucial topic in medical sciences. Coronavirus has expanded massively, and it is among the one of the most frightful and dangerous infection in latest years. The deadly virus was found in China first, and then, it mutated throughout the world. Hence, automated illness identification provides results that are uniform and quick, and thus, mortality rate can be reduced. Most of countries including ours (India) suffers from lack of testing kits whenever new wave of COVID hits. Therefore, many researchers worked on various deep learning based, machine learning-based approaches for diagnosis of this virus using X-rays and CT scans of lungs. So far, it has affected over 50.9 crore people and caused the deaths of 62.2 lakhs people. Here, in this study, comprehensive survey of fifteen studies is presented where various deep learning, and transfer learning approaches are compared for their efficiency and accuracy. The goal of study here is to inspect and analyse various deep learning models including transfer learning models used, also explore the datasets used, preprocessing techniques used, and compare these models to find which model provide us with optimal and best results. The study can help in smooth implementation of the suggested work in future which can be further, then fine-tuned to get the best results possible. Deep learning provides an easy solution to the COVID problem as they perform best in detection and evaluation. It is found during this study that CNN model hybridized with other models provide better accuracy then CNN alone. Ensemble learning methods also improves the accuracy. Also, before training any model dataset acquired need to be preprocessed. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Chest CT Findings of COVID-19 Patients with Mild Clinical Symptoms at a Single Hospital in Korea.

Purpose: To retrospectively evaluate the chest computed tomography (CT) findings of coronavirus disease 2019 (COVID-19) in patients with mild clinical symptoms at a single hospital in South Korea. Materials and Methods: CT scans of 87 COVID-19 patients [43 men and 44 women; median age: 41 years (interquartile range: 26.1-51.0 years)] with mild clinical symptoms (fever < 38℃ and no dyspnea) were evaluated. Results: CT findings were normal in 39 (44.8%) and abnormal in 48 (55.2%) patients. Among the 48 patients with lung opacities, 17 (35.4%) had unilateral disease and 31 (64.6%) had bilateral disease. One (2.1%) patient showed subpleural distribution, 9 (18.8%) showed peribronchovascular distribution, and 38 (79.2%) showed subpleural and peribronchovascular distributions. Twenty-two (45.8%) patients had pure ground-glass opacities (GGOs) with no consolidation, 17 (35.4%) had mixed opacities dominated by GGOs, and 9 (18.8%) had mixed opacities dominated by consolidation. No patients demonstrated consolidation without GGOs. Conclusion: The most common CT finding of COVID-19 in patients with mild clinical symptoms was bilateral multiple GGO-dominant lesions with subpleural and peribronchovascular distribution and lower lung predilection. The initial chest CT of almost half of COVID-19 patients with mild clinical symptoms showed no lung parenchymal lesions. Compared to relatively severe cases, mild cases were more likely to manifest as unilateral disease with pure GGOs or GGO-dominant mixed opacities and less likely to show air bronchogram.

Embracing the Power of Show-Me ECHO Learning Communities to Transform Clinical Practice in Missouri

Show-Me ECHO, a state-funded project, provides access to education within a community of learners in order to optimize healthcare for the citizens of Missouri. Through videoconferencing and case-based review, ECHO shifts professional development from learning about medical problems in isolation to experiential learning as part of a multidisciplinary team. The establishment of a statewide COVID-19 ECHO is allowing a rapid response to this novel, unprecedented, and unanticipated health care crisis. There are many ongoing opportunities for clinicians from across the state to join a Show-Me ECHO learning community as a means to elevate their practice and improve ability to respond amidst a constantly evolving health care environment. Copyright 2020 by the Missouri State Medical Association.

COV-ELM classifier: An extreme learning machine based identification of COVID-19 using chest X-ray images

Coronaviruses constitute a family of viruses that gives rise to respiratory diseases. COVID-19 is an infectious disease caused by a newly discovered coronavirus also termed Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). As COVID-19 is highly contagious, early diagnosis of COVID-19 is crucial for an effective treatment strategy. However, the reverse transcription-polymerase chain reaction (RT-PCR) test which is considered to be a gold standard in the diagnosis of COVID-19 suffers from a high false-negative rate. Therefore, the research community is exploring alternative diagnostic mechanisms. Chest X-ray (CXR) image analysis has emerged as a feasible and effective diagnostic technique towards this objective. In this work, we propose the COVID-19 classification problem as a three-class classification problem to distinguish between COVID-19, normal, and pneumonia classes. We propose a three-stage framework, named COV-ELM based on extreme learning machine (ELM). Our dataset comprises CXR images in a frontal view, namely Posteroanterior (PA) and Erect anteroposterior (AP). Stage one deals with preprocessing and transformation while stage two deals with feature extraction. These extracted features are passed as an input to the ELM at the third stage, resulting in the identification of COVID-19. The choice of ELM in this work has been motivated by its faster convergence, better generalization capability, and shorter training time in comparison to the conventional gradient-based learning algorithms. As bigger and diverse datasets become available, ELM can be quickly retrained as compared to its gradient-based competitor models. We use 10-fold cross-validation to evaluate the results of COV-ELM. The proposed model achieved a macro average F1-score of 0.95 and the overall sensitivity of 0.94 +/- 0.02 at a 95% confidence interval. When compared to state-of-the-art machine learning algorithms, the COV-ELM is found to outperform its competitors in this three-class classification scenario. Further, LIME has been integrated with the proposed COV-ELM model to generate annotated CXR images. The annotations are based on the superpixels that have contributed to distinguish between the different classes. It was observed that the superpixels correspond to the regions of the human lungs that are clinically observed in COVID-19 and Pneumonia cases.

Late bilateral vocal cord palsy following endotracheal intubation due to COVID-19 pneumonia.

Vocal cord paralysis is a rare but severe complication after orotracheal intubation. The most common cause is traumatic, due to compression of the recurrent laryngeal nerve between the orotracheal tube cuff and the thyroid cartilage. Other possible causes are direct damage to the vocal cords during intubation, dislocation of the arytenoid cartilages, or infections, especially viral infections. It is usually due to a recurrent laryngeal nerve neuropraxia, and the course is benign in most patients. We present the case of a man who developed late bilateral vocal cord paralysis after pneumonia complicated with respiratory distress due to SARS-CoV-2 that required orotracheal intubation for 11 days. He presented symptoms of dyspnea 20 days after discharge from hospital with subsequent development of stridor, requiring a tracheostomy. Due to the temporal evolution, a possible contribution of the SARS-CoV-2 infection to the picture is pointed out.

An approach to categorize chest X-ray images using sparse categorical cross entropy

The Coronavirus disease (COVID-19) pandemic is the most recent threat to global health. Reverse transcription-polymerase chain reaction (RT-PCR) testing, computed tomography (CT) scans, and chest X-ray (CXR) images are being used to identify Coronavirus, one of the most serious community viruses of the twenty-first century. Because CT scans and RT-PCR analyses are not available in most health divisions, CXR images are typically the most time-saving and cost-effective tool for physicians in making decisions. Artificial intelligence and machine learning have become increasingly popular because of recent technical advancements. The goal of this project is to combine machine learning, deep learning, and the health-care sector to create a categorization technique for detecting the Coronavirus and other respiratory disorders. The three conditions evaluated in this study were COVID-19, viral Pneumonia, and normal lungs. Using X-ray pictures, this research developed a sparse categorical cross-entropy technique for recognizing all three categories. The proposed model had a training accuracy of 91% and a training loss of 0.63, as well as a validation accuracy of 81% and a validation loss of 0.7108. © 2021 Institute of Advanced Engineering and Science. All rights reserved.

Survival in influenza virus-related pneumonia by viral subtype: 2016-2020.

BACKGROUND: Influenza remains a common cause of morbidity and mortality worldwide, and viral subtype-related differences in disease outcomes have been documented. OBJECTIVE: To characterize the survival experience of adult inpatients with influenza virus-associated pneumonia by viral subtype during five consecutive flu seasons. METHOD: We performed a retrospective cohort study; data from 4,678 adults were analyzed using the Kaplan-Meier method. A multivariate Cox proportional hazard regression model was fitted. RESULTS: The overall in-hospital mortality rate was 25.0 per 1,000 hospital days. The survival probabilities from pneumonia patients went from 93.4% (95% CI 92.6-94.1%) by day three to 43.3% (95% CI 39.2-47.4%) by day 30 from hospital admission. In general, the lowest survival rates were observed in patients with AH1N1 infection. In multiple models, after adjusting for comorbidities and when compared with A non-subtyped virus, pneumonia patients with AH3N2 or B strains had a significantly decreased risk of a non-favorable disease outcome. The association of other strains was not significant. CONCLUSIONS: Our findings suggest that the survival of inpatients with influenza virus-associated pneumonia varies according to the pathogenic viral subtype; the lowest survival rates were observed in patients with AH1N1 infection. This effect was independent of the patients' gender, age, and the analyzed underlying health conditions.

Surveillance for Pressure Injuries on Admission to Inpatient Rehabilitation Hospitals During the COVID-19 Pandemic.

OBJECTIVE: To determine if the incidence of pressure injuries (PIs) on admission to an inpatient rehabilitation hospital (IRH) system of care was increased during the early coronavirus disease 2019 (COVID-19) pandemic period. DESIGN: Retrospective survey chart review of consecutive cohorts. Admissions to 4 acute IRHs within 1 system of care over the first consecutive 6-week period of admitting patients positive for COVID-19 during the initial peak of the COVID-19 pandemic, April 1-May 9, 2020. A comparison was made with the pre-COVID-19 period, January 1-February 19, 2020. SETTING: Four acute IRHs with admissions on a referral basis from acute care hospitals. PARTICIPANTS: A consecutive sample (N=1125) of pre-COVID-19 admissions (n=768) and COVID-19 period admissions (n=357), including persons who were COVID-19-positive (n=161) and COVID-19-negative (n=196). MAIN OUTCOME MEASURES: Incidence of PIs on admission to IRH. RESULTS: Prevalence of PIs on admission during the COVID-19 pandemic was increased when compared with the pre-COVID-19 period by 14.9% (P<.001). There was no difference in the prevalence of PIs in the COVID-19 period between patients who were COVID-19-positive and COVID-19-negative (35.4% vs 35.7%). The severity of PIs, measured by the wound stage of the most severe PI the patient presented with, worsened during the COVID-19 period compared with pre-COVID-19 (χ2 32.04%, P<.001). The length of stay in the acute care hospital before transfer to the IRH during COVID-19 was greater than pre-COVID-19 by 10.9% (P<.001). CONCLUSIONS: During the early part of the COVID-19 pandemic time frame, there was an increase in the prevalence and severity of PIs noted on admission to our IRHs. This may represent the significant burden placed on the health care system by the pandemic, affecting all patients regardless of COVID-19 status. This information is important to help all facilities remain vigilant to prevent PIs as the pandemic continues and potential future pandemics that place strain on medical resources.

Clinical trials on drug repositioning for COVID-19 treatment.

The World Health Organization (WHO) was informed on December 2019 about a coronavirus pneumonia outbreak in Wuhan, Hubei province (China). Subsequently, on March 12, 2020, 125,048 cases and 4,614 deaths were reported. Coronavirus is an enveloped RNA virus, from the genus Betacoronavirus, that is distributed in birds, humans, and other mammals. WHO has named the novel coronavirus disease as COVID-19. More than 80 clinical trials have been launched to test coronavirus treatment, including some drug repurposing or repositioning for COVID-19. Hence, we performed a search in March 2020 of the clinicaltrials.gov database. The eligibility criteria for the retrieved studies were: contain a clinicaltrials.gov base identifier number; describe the number of participants and the period for the study; describe the participants' clinical conditions; and utilize interventions with medicines already studied or approved for any other disease in patients infected with the novel coronavirus SARS-CoV-2 (2019-nCoV). It is essential to emphasize that this article only captured trials listed in the clinicaltrials.gov database. We identified 24 clinical trials, involving more than 20 medicines, such as human immunoglobulin, interferons, chloroquine, hydroxychloroquine, arbidol, remdesivir, favipiravir, lopinavir, ritonavir, oseltamivir, methylprednisolone, bevacizumab, and traditional Chinese medicines (TCM). Although drug repurposing has some limitations, repositioning clinical trials may represent an attractive strategy because they facilitate the discovery of new classes of medicines; they have lower costs and take less time to reach the market; and there are existing pharmaceutical supply chains for formulation and distribution.

En diciembre de 2019 fue informado a la Organización Mundial de la Salud (OMS) un brote de neumonía por coronavirus en Wuhan, provincia de Hubei, China. Al 12 de marzo de 2020, se habían notificado 125 048 casos y 4 614 muertes. El coronavirus es un virus ARN envuelto del género Betacoronavirus distribuido en aves, seres humanos y otros mamíferos. La OMS ha denominado a la nueva enfermedad por coronavirus COVID-19. Se han puesto en marcha más de 80 ensayos clínicos para evaluar un tratamiento para el coronavirus, que incluyen algunos ensayos de reposicionamiento de medicamentos para la COVID-19. En marzo de 2020 se llevó a cabo una búsqueda de los ensayos clínicos registrados en la base de datos clinicaltrials.gov. Los criterios de elegibilidad para los estudios recuperados fueron tener un número de identificación de la base de datos clinicaltrials.gov; describir el número de participantes y el período del estudio; describir las condiciones clínicas de los participantes; y emplear intervenciones con medicamentos ya estudiados o aprobados para cualquier otra enfermedad en pacientes infectados con el nuevo coronavirus SARS-CoV-2 (2019-nCoV). Es esencial destacar que este artículo solo recoge los ensayos que figuran en la base de datos clinicaltrials. gov. Se identificaron 24 ensayos clínicos relacionados con más de 20 medicamentos, como inmunoglobulina humana, interferones, cloroquina, hidroxicloroquina, arbidol, remdesivir, favipiravir, lopinavir, ritonavir, oseltamivir, metilprednisolona, bevacizumab y medicina tradicional china. Aunque el reposicionamiento de medicamentos tiene algunas limitaciones, el reposicionamiento de los ensayos clínicos puede representar una estrategia atractiva porque facilita el descubrimiento de nuevas clases de medicamentos; estos tienen costos más bajos y tardan menos en llegar al mercado; y existen cadenas de suministro farmacéutico que apoyan la formulación y la distribución.

A Organização Mundial da Saúde (OMS) foi informada, em dezembro de 2019, sobre um surto de pneumonia por coronavírus em Wuhan, província de Hubei (China). Posteriormente, em 12 de março de 2020, 125 048 casos e 4 614 mortes haviam sido registrados. O coronavírus é um vírus RNA envelopado do gênero Betacoronavírus, distribuído em aves e em humanos e outros mamíferos. A OMS designou a nova doença por coronavírus como COVID-19. Mais de 80 ensaios clínicos foram iniciados para testar tratamentos para o coronavírus, incluindo alguns de reposicionamento de medicamentos para o COVID-19. Assim, em março de 2020 realizou-se uma busca na base de dados clinicaltrials.gov. Os critérios de elegibilidade para os estudos recuperados foram: conter o número identificador da base de dados clinicaltrials.gov; descrever o número de participantes e o período do estudo; descrever as condições clínicas dos participantes; e utilizar intervenções para tratamento de doentes infectados com o novo coronavírus SARS-CoV-2 (2019-nCoV) com medicamentos já estudados ou aprovados para qualquer outra doença. É essencial salientar que este artigo apenas capturou ensaios listados na base de dados clinicaltrials.gov. Foram identificados 24 ensaios clínicos envolvendo mais de 20 medicamentos, tais como imunoglobulina humana, interferons, cloroquina, hidroxicloroquina, arbidol, remdesivir, favipiravir, lopinavir, ritonavir, oseltamivir, metilprednisolona, bevacizumabe e medicamentos chineses tradicionais. Embora o reposicionamento de medicamentos tenha algumas limitações, os ensaios clínicos de reposicionamento podem representar uma estratégia atraente, porque facilitam a descoberta de novas classes de medicamentos, têm custos mais baixos, levam menos tempo para chegar ao mercado e se beneficiam de cadeias de fornecimento farmacêutico já existentes para formulação e distribuição.

Protective ventilation and outcomes of critically ill patients with COVID-19: a cohort study.

BACKGROUND: Approximately 5% of COVID-19 patients develop respiratory failure and need ventilatory support, yet little is known about the impact of mechanical ventilation strategy in COVID-19. Our objective was to describe baseline characteristics, ventilatory parameters, and outcomes of critically ill patients in the largest referral center for COVID-19 in Sao Paulo, Brazil, during the first surge of the pandemic. METHODS: This cohort included COVID-19 patients admitted to the intensive care units (ICUs) of an academic hospital with 94 ICU beds, a number expanded to 300 during the pandemic as part of a state preparedness plan. Data included demographics, advanced life support therapies, and ventilator parameters. The main outcome was 28-day survival. We used a multivariate Cox model to test the association between protective ventilation and survival, adjusting for PF ratio, pH, compliance, and PEEP. RESULTS: We included 1503 patients from March 30 to June 30, 2020. The mean age was 60 ± 15 years, and 59% were male. During 28-day follow-up, 1180 (79%) patients needed invasive ventilation and 666 (44%) died. For the 984 patients who were receiving mechanical ventilation in the first 24 h of ICU stay, mean tidal volume was 6.5 ± 1.3 mL/kg of ideal body weight, plateau pressure was 24 ± 5 cmH2O, respiratory system compliance was 31.9 (24.4-40.9) mL/cmH2O, and 82% of patients were ventilated with protective ventilation. Noninvasive ventilation was used in 21% of patients, and prone, in 36%. Compliance was associated with survival and did not show a bimodal pattern that would support the presence of two phenotypes. In the multivariable model, protective ventilation (aHR 0.73 [95%CI 0.57-0.94]), adjusted for PF ratio, compliance, PEEP, and arterial pH, was independently associated with survival. CONCLUSIONS: During the peak of the epidemic in Sao Paulo, critically ill patients with COVID-19 often required mechanical ventilation and mortality was high. Our findings revealed an association between mechanical ventilation strategy and mortality, highlighting the importance of protective ventilation for patients with COVID-19.