Diagnosis of COVID-19 in Patients with Negative Nasopharyngeal Swabs: Reliability of Radiological and Clinical Diagnosis and Accuracy Versus Serology

COVID-19 Diagnosis on Chest Radiographs with Enhanced Deep Neural Networks

The COVID-19 pandemic has caused a devastating impact on the social activity, economy and politics worldwide. Techniques to diagnose COVID-19 cases by examining anomalies in chest X-ray images are urgently needed. Inspired by the success of deep learning in various tasks, this paper evaluates the performance of four deep neural networks in detecting COVID-19 patients from their chest radiographs. The deep neural networks studied include VGG16, MobileNet, ResNet50 and DenseNet201. Preliminary experiments show that all deep neural networks perform promisingly, while DenseNet201 outshines other models. Nevertheless, the sensitivity rates of the models are below expectations, which can be attributed to several factors: limited publicly available COVID-19 images, imbalanced sample size for the COVID-19 class and non-COVID-19 class, overfitting or underfitting of the deep neural networks and that the feature extraction of pre-trained models does not adapt well to the COVID-19 detection task. To address these factors, several enhancements are proposed, including data augmentation, adjusted class weights, early stopping and fine-tuning, to improve the performance. Empirical results on DenseNet201 with these enhancements demonstrate outstanding performance with an accuracy of 0.999%, precision of 0.9899%, sensitivity of 0.98%, specificity of 0.9997% and F1-score of 0.9849% on the COVID-Xray-5k dataset.

Factors Associated with Delirium in COVID-19 Patients and Their Outcome: A Single-Center Cohort Study

Background: A significant proportion of patients with coronavirus disease 2019 (COVID-19) suffer from delirium during hospitalization. This single-center observational study investigates the occurrence of delirium, the associated risk factors and its impact on in-hospital mortality in an Italian cohort of COVID 19 inpatients. Methods: Data were collected in the COVID units of a general medical hospital in the South of Italy. Socio-demographic, clinical and pharmacological features were collected. Diagnosis of delirium was based on a two-step approach according to 4AT criteria and DSM5 criteria. Outcomes were: dates of hospital discharge, Intensive Care Unit (ICU) admission, or death, whichever came first. Univariable and multivariable proportional hazards Cox regression models were estimated, and risks were reported as hazard ratios (HR) along with their 95% confidence intervals (95% CI). Results: A total of 47/214 patients (22%) were diagnosed with delirium (21 hypoactive, 15 hyperactive, and 11 mixed). In the multivariable model, four independent variables were independently associated with the presence of delirium: dementia, followed by age at admission, C-reactive protein (CRP), and Glasgow Coma Scale. In turn, delirium was the strongest independent predictor of death/admission to ICU (composite outcome), followed by Charlson Index (not including dementia), CRP, and neutrophil-to-lymphocyte ratio. The probability of reaching the composite outcome was higher for patients with the hypoactive subtype than for those with the hyperactive subtype. Conclusions: Delirium was the strongest predictor of poor outcome in COVID-19 patients, especially in the hypoactive subtype. Several clinical features and inflammatory markers were associated with the increased risk of its occurrence. The early recognition of these factors may help clinicians to select patients who would benefit from both non-pharmacological and pharmacological interventions in order to prevent delirium, and in turn, reduce the risk of admission to ICU or death.

Low eGFR Is a Strong Predictor of Worse Outcome in Hospitalized COVID-19 Patients

BACKGROUND

The clinical course of COVID-19 is more severe in elderly patients with cardio-metabolic co-morbidities. Chronic kidney disease is considered an independent cardiovascular risk factor. We aimed to evaluate the impact of reduced eGFR on the composite outcome of admission to ICU and death in a sample of consecutive COVID-19 hospitalized patients.

METHODS

We retrospectively evaluated clinical records of a consecutive sample of hospitalized COVID-19 patients. A total of 231 patients were considered for statistical analysis. The whole sample was divided in two groups on the basis of eGFR value, e.g., ≥ or <60 mL/min/1.73 m². Patients with low eGFR were further divided among those with a history of chronic kidney disease (CKD) and those without (AKI, acute kidney injury). The primary outcome was a composite of admission to ICU or death, whichever occurred first. The single components were secondary outcomes.

RESULTS

Seventy-nine (34.2%) patients reached the composite outcome. A total of 64 patients (27.7%) died during hospitalization, and 41 (17.7%) were admitted to the ICU. A significantly higher number of events was present among patients with low eGFR (p < 0.0001). Age (p < 0.001), SpO2 (p < 0.001), previous anti-platelet treatment (p = 0.006), Charlson's Comorbidities Index (p < 0.001), serum creatinine (p < 0.001), eGFR (p = 0.003), low eGFR (p < 0.001), blood glucose levels (p < 0.001), and LDH (p = 0.003) were significantly associated with the main outcome in univariate analysis. Low eGFR (HR 1.64, 95% CI 1.02-2.63, p = 0.040) and age (HR per 5 years 1.22, 95% CI 1.10-1.36, p < 0.001) were significantly and independently associated with the main outcome in the multivariate model. Patients with AKI showed an increased hazard ratio to reach the combined outcome (p = 0.059), while those patients with both CKD had a significantly higher probability of developing the combined outcome (p < 0.001).

CONCLUSIONS

Patients with reduced eGFR at admission should be considered at high risk for clinical deterioration and death, requiring the best supportive treatment in order to prevent the worst outcome.

Lung Ultrasound in the Diagnosis of COVID-19 Pneumonia: Not Always and Not Only What Is COVID-19 "Glitters"

Background: In the current coronavirus disease-2019 (COVID-19) pandemic, lung ultrasound (LUS) has been extensively employed to evaluate lung involvement and proposed as a useful screening tool for early diagnosis in the emergency department (ED), prehospitalization triage, and treatment monitoring of COVID-19 pneumonia. However, the actual effectiveness of LUS in characterizing lung involvement in COVID-19 is still unclear. Our aim was to evaluate LUS diagnostic performance in assessing or ruling out COVID-19 pneumonia when compared with chest CT (gold standard) in a population of SARS-CoV-2-infected patients. Methods: A total of 260 consecutive RT-PCR confirmed SARS-CoV-2-infected patients were included in the study. All the patients underwent both chest CT scan and concurrent LUS at admission, within the first 6-12 h of hospital stay. Results: Chest CT scan was considered positive when showing a "typical" or "indeterminate" pattern for COVID-19, according to the RSNA classification system. Disease prevalence for COVID-19 pneumonia was 90.77%. LUS demonstrated a sensitivity of 56.78% in detecting lung alteration. The concordance rate for the assessment of abnormalities by both methods increased in the case of peripheral distribution and middle-lower lung location of lesions and in cases of more severe lung involvement. A total of nine patients had a "false-positive" LUS examination. Alternative diagnosis included chronic heart disease (six cases), bronchiectasis (two cases), and subpleural emphysema (one case). LUS specificity was 62.50%. Collateral findings indicative of overlapping conditions at chest CT were recorded also in patients with COVID-19 pneumonia and appeared distributed with increasing frequency passing from the group with mild disease (17 cases) to that with severe disease (40 cases). Conclusions: LUS does not seem to be an adequate tool for screening purposes in the ED, due to the risk of missing some lesions and/or to underestimate the actual extent of the disease. Furthermore, the not specificity of LUS implies the possibility to erroneously classify pre-existing or overlapping conditions as COVID-19 pneumonia. It seems more safe to integrate a positive LUS examination with clinical, epidemiological, laboratory, and radiologic findings to suggest a "virosis." Viral testing confirmation is always required.

A "Galactic" Chest X-ray

Clinical manifestations accompanying respiratory failure with insidious and rapidly progressive onset are often non-specific. Symptoms such as a cough, dyspnea, and fever are common to a large number of inflammatory, infectious, or neoplastic diseases. During the COVID-19 pandemic it is essential to limit the use of hospital services and inappropriate diagnostic techniques. A particular radiological pattern can orient the clinical and laboratory scenario and guide the diagnostic workup. A 58-year-old woman was admitted to our COVID-19 unit for suspected coronavirus infection. She was complaining of worsening dyspnea, tachycardia, and low grade fever. A chest X-ray showed diffuse, alveolar, and interstitial lung involvement with micronodules tending to coalescence. This radiographic pattern known as "galaxy sign", consistent with diffuse, coalescing nodular miliary pulmonary involvement, simulating a non-specific alveolar opacification of the lungs is typical of a few pneumological differential diagnoses, represented by sarcoidosis, tuberculosis, pneumoconiosis, and metastatic lesions, and virtually excludes an interstitial viral pneumonitis. The use of endoscopic techniques can, in such cases, confirm the clinical suspicion for initiating appropriate targeted therapies.

Low Sensitivity of Admission Lung US Compared to Chest CT for Diagnosis of Lung Involvement in a Cohort of 82 Patients with COVID-19 Pneumonia

Background and Objectives: The potential role of lung ultrasound (LUS) in characterizing lung involvement in Coronavirus disease 2019 (COVID-19) is still debated. The aim of the study was to estimate sensitivity of admission LUS for the detection of SARS-CoV-2 lung involvement using Chest-CT (Computed Tomography) as reference standard in order to assess LUS usefulness in ruling out COVID-19 pneumonia in the Emergency Department (ED). Methods: Eighty-two patients with confirmed COVID-19 and signs of lung involvement on Chest-CT were consecutively admitted to our hospital and recruited in the study. Chest-CT and LUS examination were concurrently performed within the first 6-12h from admission. Sensitivity of LUS was calculated using CT findings as a reference standard. Results: Global LUS sensitivity in detecting COVID-19 pulmonary lesions was 52%. LUS sensitivity ranged from 8% in case of focal and sporadic ground-glass opacities (mild disease), to 52% for a crazy-paving pattern (moderate disease) and up to 100% in case of extensive subpleural consolidations (severe disease), although LUS was not always able to detect all the consolidations assessed at Chest-CT. LUS sensitivity was higher in detecting a typical Chest-CT pattern (60%) and abnormalities showing a middle-lower zone predominance (79%). Conclusions: As admission LUS may result falsely negative in most cases, it should not be considered as a reliable imaging tool in ruling out COVID-19 pneumonia in patients presenting in ED. It may at least represent an expanded clinical evaluation that needs integration with other diagnostic tests (e.g., nasopharyngeal swab, Chest-CT).