Analysis of Diagnostic Modalities in Hospital-admitted Patients Evaluated for COVID-19.

BACKGROUND/AIM: To assess the diagnostic performance of reverse transcriptase polymerase chain reaction (RT-PCR), low-dose chest computed tomography (CT), and serological testing, alone and in combinations, as well as routine inflammatory markers in patients evaluated for COVID-19 during the first wave in early 2020. PATIENTS AND METHODS: We retrospectively analyzed data of all patients who were admitted to the emergency department due to fever and/or respiratory symptoms. CT scans were rated using the COVID-19 Reporting and Data System (CO-RADS) suspicion score. True disease status (COVID-19 - positive vs. negative) was adjudicated by two independent clinicians. Receiver-operating characteristic curves and areas under the curves were calculated for inflammatory markers. Sensitivities and specificities were calculated for RT-PCR, CT, and serology alone, as well as the combinations of RT-PCR+CT, RT-PCR+serology, CT+serology, and all three modalities. RESULTS: Of 221 patients with a median age of 72 years, 113 were classified as COVID-19 positive. Among 180 patients from which data on CT and RT-PCR were available, RT-PCR had the highest sensitivity to detect COVID-19 (0.87; 95%CI=0.78-0.93). Notably, the addition of CT in the analysis increased sensitivity to 0.89 (95%CI=0.8-0.94), but lowered specificity from 1 (95%CI=0.96-1) to 0.9 (95%CI=0.83-0.95). The combination of RT-PCR, CT and serology (n=60 patients with complete dataset) yielded a sensitivity of 0.83 (95%CI=0.61-0.94) and specificity of 0.86 (95%CI=0.72-0.93). CONCLUSION: RT-PCR was the best single test in patients evaluated for COVID-19. Conversely, the routine performance of chest CT adds little sensitivity and decreases specificity.

Detection and characterization of COVID-19 findings in chest CT: Feasibility and applicability of an AI-based software tool.

ABSTRACT: The COVID-19 pandemic has challenged institutions' diagnostic processes worldwide. The aim of this study was to assess the feasibility of an artificial intelligence (AI)-based software tool that automatically evaluates chest computed tomography for findings of suspected COVID-19.Two groups were retrospectively evaluated for COVID-19-associated ground glass opacities of the lungs (group A: real-time polymerase chain reaction positive COVID patients, n = 108; group B: asymptomatic pre-operative group, n = 88). The performance of an AI-based software assessment tool for detection of COVID-associated abnormalities was compared with human evaluation based on COVID-19 reporting and data system (CO-RADS) scores performed by 3 readers.All evaluated variables of the AI-based assessment showed significant differences between the 2 groups (P < .01). The inter-reader reliability of CO-RADS scoring was 0.87. The CO-RADS scores were substantially higher in group A (mean 4.28) than group B (mean 1.50). The difference between CO-RADS scoring and AI assessment was statistically significant for all variables but showed good correlation with the clinical context of the CO-RADS score. AI allowed to predict COVID positive cases with an accuracy of 0.94.The evaluated AI-based algorithm detects COVID-19-associated findings with high sensitivity and may support radiologic workflows during the pandemic.

Preoperative chest computed tomography in emergency surgery during COVID-19 pandemic.

BACKGROUND: The COVID-19 pandemic challenges the recommendations for patients' preoperative assessment for preventing severe acute respiratory syndrome coronavirus type 2 transmission and COVID-19-associated postoperative complications and morbidities. PURPOSE: To evaluate the contribution of chest computed tomography for preoperatively assessing patients who are not suspected of being infected with COVID-19 at the time of referral. METHODS: Candidates for emergency surgery screened via chest computed tomography from 8 to 27 April 2020 were retrospectively evaluated. Computed tomography images were analysed for the presence of COVID-19-associated intrapulmonary changes. When applicable, laboratory and recorded clinical symptoms were extracted. RESULTS: Eighty-eight patients underwent preoperative chest computed tomography; 24% were rated as moderately suspicious and 11% as highly suspicious on computed tomography. Subsequent reverse transcription polymerase chain reaction (RT-PCR) was performed for seven patients, all of whom tested negative for COVID-19. Seven patients showed COVID-19-associated clinical symptoms, and most were classified as being mildly to moderately severe as per the clinical classification grading system. Only one case was severe. Four cases underwent RT-PCR with negative results. CONCLUSION: In a cohort without clinical suspicion of COVID-19 infection upon referral, preoperative computed tomography during the COVID-19 pandemic can yield a high suspicion of infection, even if the patient lacks clinical symptoms and is RT-PCR-negative. No recommendations can be made based on our results but contribute to the debate.

Prediction of Patient Management in COVID-19 Using Deep Learning-Based Fully Automated Extraction of Cardiothoracic CT Metrics and Laboratory Findings.

OBJECTIVE: To extract pulmonary and cardiovascular metrics from chest CTs of patients with coronavirus disease 2019 (COVID-19) using a fully automated deep learning-based approach and assess their potential to predict patient management. MATERIALS AND METHODS: All initial chest CTs of patients who tested positive for severe acute respiratory syndrome coronavirus 2 at our emergency department between March 25 and April 25, 2020, were identified (n = 120). Three patient management groups were defined: group 1 (outpatient), group 2 (general ward), and group 3 (intensive care unit [ICU]). Multiple pulmonary and cardiovascular metrics were extracted from the chest CT images using deep learning. Additionally, six laboratory findings indicating inflammation and cellular damage were considered. Differences in CT metrics, laboratory findings, and demographics between the patient management groups were assessed. The potential of these parameters to predict patients' needs for intensive care (yes/no) was analyzed using logistic regression and receiver operating characteristic curves. Internal and external validity were assessed using 109 independent chest CT scans. RESULTS: While demographic parameters alone (sex and age) were not sufficient to predict ICU management status, both CT metrics alone (including both pulmonary and cardiovascular metrics; area under the curve [AUC] = 0.88; 95% confidence interval [CI] = 0.79-0.97) and laboratory findings alone (C-reactive protein, lactate dehydrogenase, white blood cell count, and albumin; AUC = 0.86; 95% CI = 0.77-0.94) were good classifiers. Excellent performance was achieved by a combination of demographic parameters, CT metrics, and laboratory findings (AUC = 0.91; 95% CI = 0.85-0.98). Application of a model that combined both pulmonary CT metrics and demographic parameters on a dataset from another hospital indicated its external validity (AUC = 0.77; 95% CI = 0.66-0.88). CONCLUSION: Chest CT of patients with COVID-19 contains valuable information that can be accessed using automated image analysis. These metrics are useful for the prediction of patient management.