Chest CT in COVID-19 at the ED: Validation of the COVID-19 Reporting and Data System (CO-RADS) and CT Severity Score

Lieveld, Arthur W.E.; Azijli, Kaoutar; Teunissen, Bernd P.; Haaften, Rutger M van; Kootte, Ruud S.; Berk, Inge A.H. van den; Horst, Sabine Fiona Bianca van der; Gans, Carlijn de; Ven, Peter M. van de; Nanayakkara, Prabath W.B.

doi:10.1016/j.chest.2020.11.026

Cited by 94 publications

(118 citation statements)

References 36 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…For reference, we have also included the performance of the manually rated CO-RADS scoring system by a radiologist on the same test set, which had sensitivity/specificity of 74%/71%. The reported performance of CO-RADS in identifying COVID-19 (positive RT-PCR) is variable in literature with Bellini et al reporting sensitivity/specificity of 71.0%/81.0% [18], Lieveld et al reporting sensitivity/specificity of 89.4%/87.2% [19], and Prokop et al reporting sensitivity/specificity of 90%/82.8% [16].…”

Section: Discussionmentioning

confidence: 99%

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort

et al. 2021

View full text Add to dashboard Cite

Objectives To investigate machine learning classifiers and interpretable models using chest CT for detection of COVID-19 and differentiation from other pneumonias, interstitial lung disease (ILD) and normal CTs. Methods Our retrospective multi-institutional study obtained 2446 chest CTs from 16 institutions (including 1161 COVID-19 patients). Training/validation/testing cohorts included 1011/50/100 COVID-19, 388/16/33 ILD, 189/16/33 other pneumonias, and 559/17/34 normal (no pathologies) CTs. A metric-based approach for the classification of COVID-19 used interpretable features, relying on logistic regression and random forests. A deep learning–based classifier differentiated COVID-19 via 3D features extracted directly from CT attenuation and probability distribution of airspace opacities. Results Most discriminative features of COVID-19 are the percentage of airspace opacity and peripheral and basal predominant opacities, concordant with the typical characterization of COVID-19 in the literature. Unsupervised hierarchical clustering compares feature distribution across COVID-19 and control cohorts. The metrics-based classifier achieved AUC = 0.83, sensitivity = 0.74, and specificity = 0.79 versus respectively 0.93, 0.90, and 0.83 for the DL-based classifier. Most of ambiguity comes from non-COVID-19 pneumonia with manifestations that overlap with COVID-19, as well as mild COVID-19 cases. Non-COVID-19 classification performance is 91% for ILD, 64% for other pneumonias, and 94% for no pathologies, which demonstrates the robustness of our method against different compositions of control groups. Conclusions Our new method accurately discriminates COVID-19 from other types of pneumonia, ILD, and CTs with no pathologies, using quantitative imaging features derived from chest CT, while balancing interpretability of results and classification performance and, therefore, may be useful to facilitate diagnosis of COVID-19. Key Points • Unsupervised clustering reveals the key tomographic features including percent airspace opacity and peripheral and basal opacities most typical of COVID-19 relative to control groups. • COVID-19-positive CTs were compared with COVID-19-negative chest CTs (including a balanced distribution of non-COVID-19 pneumonia, ILD, and no pathologies). Classification accuracies for COVID-19, pneumonia, ILD, and CT scans with no pathologies are respectively 90%, 64%, 91%, and 94%. • Our deep learning (DL)–based classification method demonstrates an AUC of 0.93 (sensitivity 90%, specificity 83%). Machine learning methods applied to quantitative chest CT metrics can therefore improve diagnostic accuracy in suspected COVID-19, particularly in resource-constrained environments. Supplementary Information The online version contains supplementary material available at 10.1007/s00330-021-07937-3.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort

et al. 2021

View full text Add to dashboard Cite

show abstract

“…15 A CO-RADS score of $ 4 can be used to predict positive and negative RT-PCR results in high-prevalence settings, with a sensitivity of 89.4%, specificity of 87.2%, negative predictive value of 94.6%, and PPV of 76.4%, respectively. 16 It should be pointed out that these reporting and scoring systems have been used mainly as research tools and are used less commonly in clinical practice. Their value in clinical settings remains to be established.…”

Section: Q6mentioning

confidence: 99%

The Usefulness of Chest CT Imaging in Patients With Suspected or Diagnosed COVID-19

Machnicki

Patel

Singh

et al. 2021

Chest

View full text Add to dashboard Cite

The COVID-19 pandemic has had devastating medical and economic consequences globally. The severity of COVID-19 is related, in a large measure, to the extent of pulmonary involvement. The role of chest CT in the management of patients with COVID-19 has evolved since the onset of the pandemic. Specifically, the description of CT findings, use of CT chest in various acute and subacute settings and its usefulness in predicting chronic disease have been better defined. We performed a review of published data on CT scans in COVID-19 patients. A summary of the range of imaging findings, from typical to less common abnormalities is provided. Familiarity with these findings may facilitate in the diagnosis and management of this disease. A comparison of sensitivity and specificity of CT chest with RT-PCR testing highlights the potential role of CT imaging in difficult to diagnose cases of Covid-19. The utility of CT imaging to assess prognosis, guide management, and identify acute pulmonary complications associated with SARS-COV-2 is highlighted. Beyond the acute stage, it is important for clinicians to recognize pulmonary parenchymal abnormalities, progressive fibrotic lung disease and vascular changes that may be responsible for persistent respiratory symptoms. A large collection of multi institutional images has been included to elucidate the CT findings described.

show abstract

“…Ran Yang study revealed CT index correlated with severity of inflammation with 83% specificity and 94% sensitivity. 4 Mathias Prokop etal., proposed CO-RADS score offers a five-point scale of suspicion for pulmonary involvement of COVID-19 at chest CT. 5 Same view is endorsed by Lieveld, et al, 6 Egyptian study of Mona A. F. Hafez et al, reiterated same fact. 7 72% of our patients died within first five days.…”

Section: Discussionmentioning

confidence: 86%

Clinical and radiological parameters among COVID deaths in a tertiary care COVID hospital

Rachakonda¹,

Nagasre²,

Bolleddu³

et al. 2021

IJIRM

View full text Add to dashboard Cite

Background: A total of 10682 patients were admitted in our tertiary care COVID hospital from April 2020 to January 2021. 419 patients died with a mortality rate of 3.92%. We have analysed 241 deaths that have taken place till 10 th September 2020. Methodology: We studied the history, symptomatology, HRCT chest, comorbidities, duration of hospital stay and special drugs administered along with the type of oxygen therapy. Results: 88% of patients have more than 30% lung burden by HRCT. All the patients have a CO-RADS score of 4 or more. 81% of the patients have CT severity index of 15/25 or more. The CO-RADS classification is a standardized reporting system for patients with suspected COVID-19 infection developed for a moderate to high prevalence setting. 71% of patients expired within first five days of admission. 23% of patients died in 5 to 10 days of admission. 80% of patients presenting with < 80% SPO 2 died in first five days. 77% of patients have single or multiple comorbidities. 23% of patients did not have any comorbidities. 34% of patients gave history of alcohol intake 41.9% have history of smoking. 38% of patients gave past history of lung disease. Shortness of breath, generalized weakness and cough were the common symptoms. Loss of smell was seen in 22% and loss of taste was seen in 25%. 81% of patients had more than 5 days of symptoms before admission. 19% had less than 5 days of symptoms. 73% of patients presented with Modified Medical research Council Scale Grade 3 or 4 breathlessness. Patients required oxygen in multiple forms. Only 5% of patients were put on mechanical ventilator. Remdesivir was given in 96% of patients. Anti IL6 Tocilizumab was given in 25%. Plasma therapy was given in 5%. Conclusions: Patients dying of COVID-19 disease had significant CT scan changes suggestive of corona disease. Past history of lung disease was seen in only a third. Shortness of breath was the commonest symptom and majority of the patients presented with SPO 2 of <90% and moderate to severe breathlessness.

show abstract

Chest CT in COVID-19 at the ED: Validation of the COVID-19 Reporting and Data System (CO-RADS) and CT Severity Score

Cited by 94 publications

References 36 publications

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort

Machine learning automatically detects COVID-19 using chest CTs in a large multicenter cohort

The Usefulness of Chest CT Imaging in Patients With Suspected or Diagnosed COVID-19

Clinical and radiological parameters among COVID deaths in a tertiary care COVID hospital

Contact Info

Product

Resources

About