Dataset Information

An overview of the National COVID-19 Chest Imaging Database: data quality and cohort analysis.

ABSTRACT:

Background

The National COVID-19 Chest Imaging Database (NCCID) is a centralized database containing mainly chest X-rays and computed tomography scans from patients across the UK. The objective of the initiative is to support a better understanding of the coronavirus SARS-CoV-2 disease (COVID-19) and the development of machine learning technologies that will improve care for patients hospitalized with a severe COVID-19 infection. This article introduces the training dataset, including a snapshot analysis covering the completeness of clinical data, and availability of image data for the various use-cases (diagnosis, prognosis, longitudinal risk). An additional cohort analysis measures how well the NCCID represents the wider COVID-19-affected UK population in terms of geographic, demographic, and temporal coverage.

Findings

The NCCID offers high-quality DICOM images acquired across a variety of imaging machinery; multiple time points including historical images are available for a subset of patients. This volume and variety make the database well suited to development of diagnostic/prognostic models for COVID-associated respiratory conditions. Historical images and clinical data may aid long-term risk stratification, particularly as availability of comorbidity data increases through linkage to other resources. The cohort analysis revealed good alignment to general UK COVID-19 statistics for some categories, e.g., sex, whilst identifying areas for improvements to data collection methods, particularly geographic coverage.

Conclusion

The NCCID is a growing resource that provides researchers with a large, high-quality database that can be leveraged both to support the response to the COVID-19 pandemic and as a test bed for building clinically viable medical imaging models.

SUBMITTER: Cushnan D

PROVIDER: S-EPMC8633457 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Chest computed tomography (CT) is frequently used in diagnosing coronavirus disease 2019 (COVID-19) for detecting abnormal changes in the lungs and monitoring disease progression during the treatment process. Furthermore, CT imaging appearances are correlated with patients presenting with different clinical scenarios, such as early versus advanced stages, asymptomatic versus symptomatic patients, and severe versus nonsevere situations. However, its role as a screening and diagnostic tool in COVID-19 remains to be clarified. This article provides a systematic review and meta-analysis of the current literature on chest CT imaging findings with the aim of highlighting the contribution and judicious use of CT in the diagnosis of COVID-19. A search of PubMed/Medline, Web of Science, ScienceDirect, Google Scholar and Scopus was performed to identify studies reporting chest imaging findings in COVID-19. Chest imaging abnormalities associated with COVID-19 were extracted from the eligible studies and diagnostic value of CT in detecting these abnormal changes was compared between studies consisting of both COVID-19 and non-COVID-19 patients. A random-effects model was used to perform meta-analysis for calculation of pooled mean values and 95% confidence intervals (95% CI) of abnormal imaging findings. Fifty-five studies met the selection criteria and were included in the analysis. Pulmonary lesions more often involved bilateral lungs (78%, 95% CI: 45-100%) and were more likely to have a peripheral (65.35%, 95% CI: 25.93-100%) and peripheral plus central distribution (31.12%, 95% CI: 1.96-74.07%), but less likely to have a central distribution (3.57%, 95% CI: 0.99-9.80%). Ground glass opacities (GGO) (58.05%, 95% CI: 16.67-100%), consolidation (44.18%, 95% CI: 1.61-71.46%) and GGO plus consolidation (52.99%, 95% CI: 19.05-76.79%) were the most common findings reported in 94.5% (52/55) of the studies, followed by air bronchogram (42.50%, 95% CI: 7.78-80.39%), linear opacities (41.29%, 95% CI: 7.44-65.06%), crazy-paving pattern (23.57%, 95% CI: 3.13-91.67%) and interlobular septal thickening (22.91%, 95% CI: 0.90-80.49%). CT has low specificity in differentiating pneumonia-related lung changes due to significant overlap between COVID-19 and non-COVID-19 patients with no significant differences in most of the imaging findings between these two groups (P>0.05). Furthermore, normal CT (13.31%, 95% CI: 0.74-38.36%) was reported in 26 (47.3%) studies. Despite widespread use of CT in the diagnosis of COVID-19 patients based on the current literature, CT findings are not pathognomonic as it lacks specificity in differentiating imaging appearances caused by different types of pneumonia. Further, there is a relatively high percentage of normal CT scans. Use of CT as a first-line diagnostic or screening tool in COVID-19 is not recommended.