Convolutional Neural Network-Based Automatic Analysis of Chest Radiographs for the Detection of COVID-19 Pneumonia: A Prioritizing Tool in the Emergency Department, Phase I Study and Preliminary "Real Life" Results.

The aim of our study is the development of an automatic tool for the prioritization of COVID-19 diagnostic workflow in the emergency department by analyzing chest X-rays (CXRs). The Convolutional Neural Network (CNN)-based method we propose has been tested retrospectively on a single-center set of 542 CXRs evaluated by experienced radiologists. The SARS-CoV-2 positive dataset (n = 234) consists of CXRs collected between March and April 2020, with the COVID-19 infection being confirmed by an RT-PCR test within 24 h. The SARS-CoV-2 negative dataset (n = 308) includes CXRs from 2019, therefore prior to the pandemic. For each image, the CNN computes COVID-19 risk indicators, identifying COVID-19 cases and prioritizing the urgent ones. After installing the software into the hospital RIS, a preliminary comparison between local daily COVID-19 cases and predicted risk indicators for 2918 CXRs in the same period was performed. Significant improvements were obtained for both prioritization and identification using the proposed method. Mean Average Precision (MAP) increased (p < 1.21 × 10-21 from 43.79% with random sorting to 71.75% with our method. CNN sensitivity was 78.23%, higher than radiologists' 61.1%; specificity was 64.20%. In the real-life setting, this method had a correlation of 0.873. The proposed CNN-based system effectively prioritizes CXRs according to COVID-19 risk in an experimental setting; preliminary real-life results revealed high concordance with local pandemic incidence.

Retrospective analysis of the application of CT scan in the emergency department to screen clinically asymptomatic COVID-19 before hospital admission.

BACKGROUND: The necessity to identify and isolate COVID-19 patients to avoid intrahospital cross infections is particularly felt as a challenge. Clinically occult SARS-CoV-2 infection among patients admitted to the hospital is always considered a risk during the pandemic. The aim of our study is to describe the application of CT scan to reveal unexpected COVID-19 in patients needing hospital admission. METHOD: In our emergency department, we prospectively enrolled adult patients needing hospital admission, without symptoms suspected of COVID-19, and showing negative reverse transcriptase-polymerase chain reaction (RT-PCR) swab test. CT scan was performed to diagnose clinically occult COVID-19 pneumonia. All the exams were read and discussed retrospectively by two expert radiologists and assigned to one of 4 exclusive diagnoses: typical (typCT), indeterminate (indCT), atypical (atyCT), negative (negCT). The clinical characteristics and final diagnoses were described and compared with the results of CT scans. RESULTS: From May 25 to August 18, 2020, we prospectively enrolled 197 patients. They showed 122 negCT, 52 atyCT, 22 indCT, and 1 typCT. Based on the CT imaging, the prevalence of suspected clinically occult COVID-19 pneumonia was 11.6% (23 patients). None had confirmation of SARS-CoV-2 infection after the hospital stay. Nineteen patients had negative serial RT-PCR while in 4 cases, the infection was excluded by clinical follow-up or appearance of positivity of RT-PCR after months. CONCLUSION: Our descriptive analysis confirms that CT scan cannot be considered a valid tool to screen clinically occult COVID-19, when the asymptomatic patients need hospitalization for other conditions. Application of personnel protections and distancing among patients remains the best strategies to limit the possibility of intrahospital cross-infections.

Adrenal Hyperplasia as Possible Predictor of Mortality in Patients Admitted for Suspected SARS-Cov-2 Infection: A Prospective Study

A large percentage of patients affected by SARS-CoV-2 disease (COVID) have associated comorbidities such as arterial hypertension, obesity, diabetes mellitus and thrombophilia. On the contrary, the prevalence in COVID patients of diseases of the adrenal glands has not been reported. Since the visualization of the adrenal glands is almost always available in chest CT performed in patients with suspected or confirmed SARS-CoV-2 infection, the evaluation of the frequency and characteristics of morphological disorders of the adrenal masses in such patients appears of interest. We carried out a prospective consecutive series of 402 patients (M 222, 55.2%;F 180, 44.8%) with a median age of 76 years (IQR 64–84 years), admitted in the emergency department for suspected SARS-CoV-2 infection. One hundred patients had a PCR-confirmed diagnosis of infection on a naso-pharyngeal swab (24.9%). All patients underwent a chest MDCT study including the adrenal region and clinical assessment of co-morbidities. Compared to subjects without confirmed disease, COVID patients had more frequently close contact with other positive subjects (24% vs 4.6%, p &lt;0.001), typical symptoms (68% vs 28.5%, p &lt;0.001), and suggestive chest CT findings (90% vs 31.1%, p &lt;0.001). We found altered adrenal morphology in 100 patients (24.9%): 62 subjects had adrenal hyperplasia, which was unilateral in 42 of them (67.7%) and bilateral in 20 (32.3%), while 38 patients had discrete adrenal nodules, unilateral in 34 of them (89.4%) and bilateral in 4 (10.6%). The median size of adrenal nodules was 16 mm (10–50 mm) with a median density of 10 HU (-41 - 42 HU). In 17 patients with adrenal hyperplasia, a previous CT was available for comparison: in all cases an increase in thickness was evident at admission (from 1 to 15 mm, with a median of 1.95 mm increase). COVID patients had a higher frequency of adrenal nodules (12% vs 8.6%, p=NS). Sixty-three patients (16%) died. They were older (80 vs 74 years, p = 0.001), had a higher frequency of adrenal hyperplasia (25% vs 14%, p = 0.03), more frequent active cancer disease (37% vs 19%, p = 0.003) and COVID (23% vs 13.2%, p = 0.02). In a multivariate model, adrenal hyperplasia is an independent risk factor for mortality (OR 2.52, 1.15–5.55, p=0.02), as well as age (OR 1.04, 1.01–1.07, p=0.005), active oncological disease (OR 3.06, 1.44–6.49, p=0.004), and COVID (OR 2.88, 1.38–6.01, p=0.005). This is the first study reporting the prevalence of morphological alterations of adrenal glands in suspected COVID patients. The frequency of discrete adrenal nodules (9.5%) is in line with the high prevalence of adrenal incidentalomas in elder subjects. The high frequency of adrenal hyperplasia associated with increased risk of mortality suggests that this may be the consequence of an exaggerated activation of the HPA axis due to a highly stressful condition.

Emergency room comprehensive assessment of demographic, radiological, laboratory and clinical data of patients with COVID-19: determination of its prognostic value for in-hospital mortality.

Mortality risk in COVID-19 patients is determined by several factors. The aim of our study was to adopt an integrated approach based on clinical, laboratory and chest x-ray (CXR) findings collected at the patient's admission to Emergency Room (ER) to identify prognostic factors. Retrospective study on 346 consecutive patients admitted to the ER of two North-Western Italy hospitals between March 9 and April 10, 2020 with clinical suspicion of COVID-19 confirmed by reverse transcriptase-polymerase reaction chain test (RT-PCR), CXR performed within 24 h (analyzed with two different scores) and recorded prognosis. Clinical and laboratory data were collected. Statistical analysis on the features of 83 in-hospital dead vs 263 recovered patients was performed with univariate (uBLR), multivariate binary logistic regression (mBLR) and ROC curve analysis. uBLR identified significant differences for several variables, most of them intertwined by multiple correlations. mBLR recognized as significant independent predictors for in-hospital mortality age > 75 years, C-reactive protein (CRP) > 60 mg/L, PaO2/FiO2 ratio (P/F) < 250 and CXR "Brixia score" > 7. Among the patients with at least two predictors, the in-hospital mortality rate was 58% against 6% for others [p < 0.0001; RR = 7.6 (4.4-13)]. Patients over 75 years had three other predictors in 35% cases against 10% for others [p < 0.0001, RR = 3.5 (1.9-6.4)]. The greatest risk of death from COVID-19 was age above 75 years, worsened by elevated CRP and CXR score and reduced P/F. Prompt determination of these data at admission to the emergency department could improve COVID-19 pretreatment risk stratification.

Baseline chest X-ray in coronavirus disease 19 (COVID-19) patients: association with clinical and laboratory data.

PURPOSE: To assess the reliability of CXR and to describe CXR findings and clinical and laboratory characteristics associated with positive and negative CXR. METHODS: Retrospective two-center study on consecutive patients admitted to the emergency department of two north-western Italian hospitals in March 2020 with clinical suspicion of COVID-19 confirmed by RT-PCR and who underwent CXR within 24 h of the swab execution. 260 patients (61% male, 62.8 ± 15.8 year) were enrolled. CXRs were rated as positive (CXR+) or negative (CXR-), and features reported included presence and distribution of airspace opacities, pleural effusion and reduction in lung volumes. Clinical and laboratory data were collected. Statistical analysis was performed with nonparametric tests, binary logistic regression (BLR) and ROC curve analysis. RESULTS: Sensitivity of CXR was 61.1% (95%CI 55-67%) with a typical presence of bilateral (62.3%) airspace opacification, more often with a lower zone (88.7%) and peripheral (43.4%) distribution. At univariate analysis, several factors were found to differ significantly between CXR+ and CXR-. The BLR confirmed as significant predictors only lactate dehydrogenase (LDH), C-reactive protein (CRP) and interval between the onset of symptoms and the execution of CXR. The ROC curve procedure determined that CRX+ was associated with LDH > 500 UI/L (AUC = 0.878), CRP > 30 mg/L (AUC = 0.830) and interval between the onset of symptoms and the execution of CXR > 4 days (AUC = 0.75). The presence of two out of three of the above-mentioned predictors resulted in CXR+ in 92.5% of cases, whereas their absence in 7.4%. CONCLUSION: CXR has a low sensitivity. LDH, CRP and interval between the onset of symptoms and the execution of CXR are major predictors for a positive CXR.