ABSTRACT
OBJECTIVES: While chest radiograph (CXR) is the first-line imaging investigation in patients with respiratory symptoms, differentiating COVID-19 from other respiratory infections on CXR remains challenging. We developed and validated an AI system for COVID-19 detection on presenting CXR. METHODS: A deep learning model (RadGenX), trained on 168,850 CXRs, was validated on a large international test set of presenting CXRs of symptomatic patients from 9 study sites (US, Italy, and Hong Kong SAR) and 2 public datasets from the US and Europe. Performance was measured by area under the receiver operator characteristic curve (AUC). Bootstrapped simulations were performed to assess performance across a range of potential COVID-19 disease prevalence values (3.33 to 33.3%). Comparison against international radiologists was performed on an independent test set of 852 cases. RESULTS: RadGenX achieved an AUC of 0.89 on 4-fold cross-validation and an AUC of 0.79 (95%CI 0.78-0.80) on an independent test cohort of 5,894 patients. Delong's test showed statistical differences in model performance across patients from different regions (p < 0.01), disease severity (p < 0.001), gender (p < 0.001), and age (p = 0.03). Prevalence simulations showed the negative predictive value increases from 86.1% at 33.3% prevalence, to greater than 98.5% at any prevalence below 4.5%. Compared with radiologists, McNemar's test showed the model has higher sensitivity (p < 0.001) but lower specificity (p < 0.001). CONCLUSION: An AI model that predicts COVID-19 infection on CXR in symptomatic patients was validated on a large international cohort providing valuable context on testing and performance expectations for AI systems that perform COVID-19 prediction on CXR. KEY POINTS: ⢠An AI model developed using CXRs to detect COVID-19 was validated in a large multi-center cohort of 5,894 patients from 9 prospectively recruited sites and 2 public datasets. ⢠Differences in AI model performance were seen across region, disease severity, gender, and age. ⢠Prevalence simulations on the international test set demonstrate the model's NPV is greater than 98.5% at any prevalence below 4.5%.
ABSTRACT
Objective: To investigate the contamination status of SARS-CoV-2 in imported frozen seafood from a Russia cargo ship in Qingdao and to analyze the risk factors for infection in local stevedores. Methods: The method of "two-stage, full coverage and mixed sampling" was used to collect the seafood packaging samples for the nucleic acid detection of SARS-CoV-2 by real-time fluorescent quantitative RT-PCR. A unified questionnaire was designed to investigate 71 stevedores in two shifts through telephone interview. The stevedores were divided into two groups, with 23 in the shit with two infections was group A and 48 in the shift without infection was group B. Software Epi Info7.2 was used to identify the risk factors for SARS-CoV-2 infections in the stevedores. Results: In the frozen seafood from a Russia cargo ship, the total positive rate of SARS-CoV-2 nucleic acid in the frozen seafood was 11.53% (106/919). The positive rate of SARS-CoV-2 nucleic acid in the frozen seafood unloaded by group A (14.29%,70/490) was significantly higher than that in the frozen seafood unloaded by group B (8.39%,36/429)(χ2=7.79,P=0.01) and the viral loads detected in the frozen seafood unloaded by group A were higher than those detected in the frozen seafood unloaded by group B. The scores of personal protection and behaviors in the stevedores in group A were significantly lower than those in group B (P<0.05), and toilet use, smoking and improper hand washing before meals were the risk factors for the infection. Conclusions: The imported frozen seafood was contaminated by SARS-CoV-2 and the contamination distribution was uneven. Supervision and management of personal occupational protection and behaviors of workers engaged in imported frozen food transportation should be strengthened. It is suggested that a closed-loop monitoring and management system for the whole process of "fishing-transport- loading/unloading" should be established by marine fishery authority.