Inter-rater reliability and prognostic value of baseline Radiographic Assessment of Lung Edema (RALE) scores in observational cohort studies of inpatients with COVID-19.

OBJECTIVES: To reliably quantify the radiographic severity of COVID-19 pneumonia with the Radiographic Assessment of Lung Edema (RALE) score on clinical chest X-rays among inpatients and examine the prognostic value of baseline RALE scores on COVID-19 clinical outcomes. SETTING: Hospitalised patients with COVID-19 in dedicated wards and intensive care units from two different hospital systems. PARTICIPANTS: 425 patients with COVID-19 in a discovery data set and 415 patients in a validation data set. PRIMARY AND SECONDARY OUTCOMES: We measured inter-rater reliability for RALE score annotations by different reviewers and examined for associations of consensus RALE scores with the level of respiratory support, demographics, physiologic variables, applied therapies, plasma host-response biomarkers, SARS-CoV-2 RNA load and clinical outcomes. RESULTS: Inter-rater agreement for RALE scores improved from fair to excellent following reviewer training and feedback (intraclass correlation coefficient of 0.85 vs 0.93, respectively). In the discovery cohort, the required level of respiratory support at the time of CXR acquisition (supplemental oxygen or non-invasive ventilation (n=178); invasive-mechanical ventilation (n=234), extracorporeal membrane oxygenation (n=13)) was significantly associated with RALE scores (median (IQR): 20.0 (14.1-26.7), 26.0 (20.5-34.0) and 44.5 (34.5-48.0), respectively, p<0.0001). Among invasively ventilated patients, RALE scores were significantly associated with worse respiratory mechanics (plateau and driving pressure) and gas exchange metrics (PaO2/FiO2 and ventilatory ratio), as well as higher plasma levels of IL-6, soluble receptor of advanced glycation end-products and soluble tumour necrosis factor receptor 1 (p<0.05). RALE scores were independently associated with 90-day survival in a multivariate Cox proportional hazards model (adjusted HR 1.04 (1.02-1.07), p=0.002). We replicated the significant associations of RALE scores with baseline disease severity and mortality in the independent validation data set. CONCLUSIONS: With a reproducible method to measure radiographic severity in COVID-19, we found significant associations with clinical and physiologic severity, host inflammation and clinical outcomes. The incorporation of radiographic severity assessments in clinical decision-making may provide important guidance for prognostication and treatment allocation in COVID-19.

Evaluation of Pulmonary Edema Using Ultrasound Imaging in Patients With COVID-19 Pneumonia Based on a Non-local Channel Attention ResNet.

Recent research has revealed that COVID-19 pneumonia is often accompanied by pulmonary edema. Pulmonary edema is a manifestation of acute lung injury (ALI), and may progress to hypoxemia and potentially acute respiratory distress syndrome (ARDS), which have higher mortality. Precise classification of the degree of pulmonary edema in patients is of great significance in choosing a treatment plan and improving the chance of survival. Here we propose a deep learning neural network named Non-local Channel Attention ResNet to analyze the lung ultrasound images and automatically score the degree of pulmonary edema of patients with COVID-19 pneumonia. The proposed method was designed by combining the ResNet with the non-local module and the channel attention mechanism. The non-local module was used to extract the information on characteristics of A-lines and B-lines, on the basis of which the degree of pulmonary edema could be defined. The channel attention mechanism was used to assign weights to decisive channels. The data set contains 2220 lung ultrasound images provided by Huoshenshan Hospital, Wuhan, China, of which 2062 effective images with accurate scores assigned by two experienced clinicians were used in the experiment. The experimental results indicated that our method achieved high accuracy in classifying the degree of pulmonary edema in patients with COVID-19 pneumonia by comparison with previous deep learning methods, indicating its potential to monitor patients with COVID-19 pneumonia.

Development of computer-aided model to differentiate COVID-19 from pulmonary edema in lung CT scan: EDECOVID-net.

The efforts made to prevent the spread of COVID-19 face specific challenges in diagnosing COVID-19 patients and differentiating them from patients with pulmonary edema. Although systemically administered pulmonary vasodilators and acetazolamide are of great benefit for treating pulmonary edema, they should not be used to treat COVID-19 as they carry the risk of several adverse consequences, including worsening the matching of ventilation and perfusion, impaired carbon dioxide transport, systemic hypotension, and increased work of breathing. This study proposes a machine learning-based method (EDECOVID-net) that automatically differentiates the COVID-19 symptoms from pulmonary edema in lung CT scans using radiomic features. To the best of our knowledge, EDECOVID-net is the first method to differentiate COVID-19 from pulmonary edema and a helpful tool for diagnosing COVID-19 at early stages. The EDECOVID-net has been proposed as a new machine learning-based method with some advantages, such as having simple structure and few mathematical calculations. In total, 13 717 imaging patches, including 5759 COVID-19 and 7958 edema images, were extracted using a CT incision by a specialist radiologist. The EDECOVID-net can distinguish the patients with COVID-19 from those with pulmonary edema with an accuracy of 0.98. In addition, the accuracy of the EDECOVID-net algorithm is compared with other machine learning methods, such as VGG-16 (Acc = 0.94), VGG-19 (Acc = 0.96), Xception (Acc = 0.95), ResNet101 (Acc = 0.97), and DenseNet20l (Acc = 0.97).

Development of an Image-Based HCS-Compatible Method for Endothelial Barrier Function Assessment.

The recent renascence of phenotypic drug discovery (PDD) is catalyzed by its ability to identify first-in-class drugs and deliver results when the exact molecular mechanism is partially obscure. Acute respiratory distress syndrome (ARDS) is a severe, life-threatening condition with a high mortality rate that has increased in frequency due to the COVID-19 pandemic. Despite decades of laboratory and clinical study, no efficient pharmacological therapy for ARDS has been found. An increase in endothelial permeability is the primary event in ARDS onset, causing the development of pulmonary edema that leads to respiratory failure. Currently, the detailed molecular mechanisms regulating endothelial permeability are poorly understood. Therefore, the use of the PDD approach in the search for efficient ARDS treatment can be more productive than classic target-based drug discovery (TDD), but its use requires a new cell-based assay compatible with high-throughput (HTS) and high-content (HCS) screening. Here we report the development of a new plate-based image cytometry method to measure endothelial barrier function. The incorporation of image cytometry in combination with digital image analysis substantially decreases assay variability and increases the signal window. This new method simultaneously allows for rapid measurement of cell monolayer permeability and cytological analysis. The time-course of permeability increase in human pulmonary artery endothelial cells (HPAECs) in response to the thrombin and tumor necrosis factor α treatment correlates with previously published data obtained by transendothelial resistance (TER) measurements. Furthermore, the proposed image cytometry method can be easily adapted for HTS/HCS applications.

Development of a convolutional neural network to differentiate among the etiology of similar appearing pathological B lines on lung ultrasound: a deep learning study.

OBJECTIVES: Lung ultrasound (LUS) is a portable, low-cost respiratory imaging tool but is challenged by user dependence and lack of diagnostic specificity. It is unknown whether the advantages of LUS implementation could be paired with deep learning (DL) techniques to match or exceed human-level, diagnostic specificity among similar appearing, pathological LUS images. DESIGN: A convolutional neural network (CNN) was trained on LUS images with B lines of different aetiologies. CNN diagnostic performance, as validated using a 10% data holdback set, was compared with surveyed LUS-competent physicians. SETTING: Two tertiary Canadian hospitals. PARTICIPANTS: 612 LUS videos (121 381 frames) of B lines from 243 distinct patients with either (1) COVID-19 (COVID), non-COVID acute respiratory distress syndrome (NCOVID) or (3) hydrostatic pulmonary edema (HPE). RESULTS: The trained CNN performance on the independent dataset showed an ability to discriminate between COVID (area under the receiver operating characteristic curve (AUC) 1.0), NCOVID (AUC 0.934) and HPE (AUC 1.0) pathologies. This was significantly better than physician ability (AUCs of 0.697, 0.704, 0.967 for the COVID, NCOVID and HPE classes, respectively), p<0.01. CONCLUSIONS: A DL model can distinguish similar appearing LUS pathology, including COVID-19, that cannot be distinguished by humans. The performance gap between humans and the model suggests that subvisible biomarkers within ultrasound images could exist and multicentre research is merited.

New Mexico's COVID-19 Experience.

ABSTRACT: The 2019 novel coronavirus disease (COVID-19) has spread worldwide, infiltrating, infecting, and devastating communities in all locations of varying demographics. An overwhelming majority of published literature on the pathologic findings associated with COVID-19 is either from living clinical cohorts or from autopsy findings of those who died in a medical care setting, which can confound pure disease pathology. A relatively low initial infection rate paired with a high biosafety level enabled the New Mexico Office of the Medical Investigator to conduct full autopsy examinations on suspected COVID-19-related deaths. Full autopsy examination on the first 20 severe acute respiratory syndrome coronavirus 2-positive decedents revealed that some extent of diffuse alveolar damage in every death due to COVID-19 played some role. The average decedent was middle-aged, male, American Indian, and overweight with comorbidities that included diabetes, ethanolism, and atherosclerotic and/or hypertensive cardiovascular disease. Macroscopic thrombotic events were seen in 35% of cases consisting of pulmonary thromboemboli and coronary artery thrombi. In 2 cases, severe bacterial coinfections were seen in the lungs. Those determined to die with but not of severe acute respiratory syndrome coronavirus 2 infection had unremarkable lung findings.

[Differential diagnosis of high altitude pulmonary edema and COVID-19 with computed tomography feature].

To investigate the computed tomography (CT) characteristics and differential diagnosis of high altitude pulmonary edema (HAPE) and COVID-19, CT findings of 52 cases of HAPE confirmed in Medical Station of Sanshili Barracks, PLA 950 Hospital from May 1, 2020 to May 30, 2020 were collected retrospectively. The size, number, location, distribution, density and morphology of the pulmonary lesions of these CT data were analyzed and compared with some already existed COVID-19 CT images which come from two files, "Radiological diagnosis of COVID-19: expert recommendation from the Chinese Society of Radiology (First edition)" and "A rapid advice guideline for the diagnosis and treatment of 2019 novel corona-virus (2019-nCoV) infected pneumonia (standard version)". The simple or multiple ground-glass opacity (GGO) lesions are located both in the HAPE and COVID-19 at the early stage, but only the thickening of interlobular septa, called "crazy paving pattern" belongs to COVID-19. At the next period, some increased cloudy shadows are located in HAPE, while lesions of COVID-19 are more likely to develop parallel to the direction of the pleura, and some of the lesions show the bronchial inflation. At the most serious stage, both the shadows in HAPE and COVID-19 become white, but the lesions of HAPE in the right lung are more serious than that of left lung. In summary, some cloudy shadows are the feature of HAPE CT image, and "crazy paving pattern" and "pleural parallel sign" belong to the COVID-19 CT, which can be used for differential diagnosis.

Differential Diagnosis of Negative Pressure Pulmonary Edema During COVID-19 Pandemic.

ABSTRACT: Negative pressure pulmonary edema (NPPE) is a form of noncardiogenic pulmonary edema that typically occurs in response to an upper airway obstruction, where patients generate high negative intrathoracic pressures, leading to a pulmonary edema especially in the postoperative period. Here, we report a case of NPPE following general anesthesia that can easily be misdiagnosed as COVID-19 both radiologically and clinically during this pandemic. Twenty-year-old male was presented with sudden onset respiratory distress, tachypnea, and cyanosis just after the rhinoplasty surgery under general anesthesia. Chest radiography and thoracic computed tomography scans revealed the bilateral patchy alveolar opacities with decreased vascular clarity that looks similar to COVID-19 radiology. Negative pressure pulmonary edema is a sudden onset and life-threatening complication following general anesthesia particularly after head and neck surgery in young healthy individuals. It is a clinical condition that cannot be diagnosed unless it comes to mind. While both NPPE and COVID-19 cause hypoxemia and respiratory distress, as well as ground-glass opacities in the chest computed tomography, those opacities in NPPE appear mostly in central areas, whereas those opacities are mostly seen in peripheral areas in COVID-19. Furthermore, while NPPE cause decreased vascular clarity, COVID-19 causes vascular dilatations in the areas of opacities. Those differences together with medical history of the patient is crucial to differentiate these 2 similar identities. Negative pressure pulmonary edema requires an immediate recognition and intervention, therefore, we would like to raise the awareness of clinicians for such condition to avoid possible mistakes during the pandemic situation.

COVID-19 in patients with heart failure: the new and the old epidemic.

Severe acute respiratory syndrome coronavirus-2 (SARS-CoV-2) has spread in nearly 200 countries in less than 4 months since its first identification; accordingly, the coronavirus disease 2019 (COVID 2019) has affirmed itself as a clinical challenge. The prevalence of pre-existing cardiovascular diseases in patients with COVID19 is high and this dreadful combination dictates poor prognosis along with the higher risk of intensive care mortality. In the setting of chronic heart failure, SARS-CoV-2 can be responsible for myocardial injury and acute decompensation through various mechanisms. Given the clinical and epidemiological complexity of COVID-19, patiens with heart failure may require particular care since the viral infection has been identified, considering an adequate re-evaluation of medical therapy and a careful monitoring during ventilation.