Dataset Information

Radiomics-based model for accurately distinguishing between severe acute respiratory syndrome associated coronavirus 2 (SARS-CoV-2) and influenza A infected pneumonia.

ABSTRACT: Clinicians have been faced with the challenge of differentiating between severe acute respiratory syndrome associated coronavirus 2 (SARS-CoV-2) infected pneumonia (NCP) and influenza A infected pneumonia (IAP), a seasonal disease that coincided with the outbreak. We aim to develop a machine-learning algorithm based on radiomics to distinguish NCP from IAP by texture analysis based on computed tomography (CT) imaging. Forty-one NCP and 37 IAP patients admitted from January to February 6, 2019 admitted to two hospitals in Wenzhou, China. All patients had undergone chest CT examination and blood routine tests prior to receiving medical treatment. NCP was diagnosed by real-time RT-PCR assays. Eight of 56 radiomic features extracted by LIFEx were selected by least absolute shrinkage and selection operator regression to develop a radiomics score and subsequently constructed into a nomogram to predict NCP with area under the operating characteristics curve of 0.87 (95% confidence interval: 0.77-0.93). The nomogram also showed excellent calibration with Hosmer-Lemeshow test yielding a nonsignificant statistic (P = .904). The novel nomogram may efficiently distinguish between NCP and IAP patients. The nomogram may be incorporated to existing diagnostic algorithm to effectively stratify suspected patients for SARS-CoV-2 pneumonia.

SUBMITTER: Zeng QQ

PROVIDER: S-EPMC7436469 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectivesAsymptomatic and symptomatic patients may transmit severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), but their clinical features and immune responses remain largely unclear. We aimed to characterise the clinical features and immune responses of asymptomatic and symptomatic patients infected with SARS-CoV-2.MethodsWe collected clinical, laboratory and epidemiological records of patients hospitalised in a coronavirus field hospital in Wuhan. We performed qualitative detection of anti-SARS-CoV-2 immunoglobulin M (IgM) and immunoglobulin G (IgG) using archived blood samples.ResultsOf 214 patients with SARS-CoV-2, 26 (12%) were asymptomatic at hospital admission and during hospitalisation. Most asymptomatic patients were ≤ 60 years (96%) and females (65%) and had few comorbidities (< 16%). Serum levels of white and red blood cells were higher in asymptomatic than in symptomatic patients (P-values < 0.05). During hospitalisation, IgG seroconversion was commonly observed in both asymptomatic and symptomatic patients (85% versus 94%, P-value = 0.07); in contrast, IgM seroconversion was less common in asymptomatic than in symptomatic patients (31% versus 74%, P-value < 0.001). The median time from the first virus-positive screening to IgG or IgM seroconversion was significantly shorter in asymptomatic than in symptomatic patients (median: 7 versus 14 days, P-value < 0.01). Furthermore, IgG/IgM seroconversion rates increased concomitantly with the clearance of SARS-CoV-2 in both asymptomatic and symptomatic patients. At the time of virus clearance, IgG/IgM titres and plasma neutralisation capacity were significantly lower in recovered asymptomatic than in recovered symptomatic patients (P-values < 0.01).ConclusionAsymptomatic and symptomatic patients exhibited different kinetics of IgG/IgM responses to SARS-CoV-2. Asymptomatic patients may transmit SARS-CoV-2, highlighting the importance of early diagnosis and treatment.

Project description:ObjectivesTo develop and validate a radiomics model for predicting 2019 novel coronavirus (COVID-19) pneumonia.MethodsFor this retrospective study, a radiomics model was developed on the basis of a training set consisting of 136 patients with COVID-19 pneumonia and 103 patients with other types of viral pneumonia. Radiomics features were extracted from the lung parenchyma window. A radiomics signature was built on the basis of reproducible features, using the least absolute shrinkage and selection operator method (LASSO). Multivariable logistic regression model was adopted to establish a radiomics nomogram. Nomogram performance was determined by its discrimination, calibration, and clinical usefulness. The model was validated in 90 consecutive patients, of which 56 patients had COVID-19 pneumonia and 34 patients had other types of viral pneumonia.ResultsThe radiomics signature, consisting of 3 selected features, was significantly associated with COVID-19 pneumonia (p < 0.05) in both training and validation sets. The multivariable logistic regression model included the radiomics signature and distribution; maximum lesion, hilar, and mediastinal lymph node enlargement; and pleural effusion. The individualized prediction nomogram showed good discrimination in the training sample (area under the receiver operating characteristic curve [AUC], 0.959; 95% confidence interval [CI], 0.933-0.985) and in the validation sample (AUC, 0.955; 95% CI, 0.899-0.995) and good calibration. The mixed model achieved better predictive efficacy than the clinical model. Decision curve analysis demonstrated that the radiomics nomogram was clinically useful.ConclusionsThe radiomics model derived has good performance for predicting COVID-19 pneumonia and may help in clinical decision-making.Key points• A radiomics model showed good performance for prediction 2019 novel coronavirus pneumonia and favorable discrimination for other types of pneumonia on CT images. • A central or peripheral distribution, a maximum lesion range > 10 cm, the involvement of all five lobes, hilar and mediastinal lymph node enlargement, and no pleural effusion is associated with an increased risk of 2019 novel coronavirus pneumonia. • A radiomics model was superior to a clinical model in predicting 2019 novel coronavirus pneumonia.

Project description:BackgroundThe role of SARS-Cov-2-infected persons who develop symptoms after testing (presymptomatics) or not at all (asymptomatics) in the pandemic spread is unknown.ObjectivesTo determine infectiousness and probable contribution of asymptomatic persons (at the time of testing) to pandemic SARS-CoV-2 spread.Data sourcesLitCovid, medRxiv, Google Scholar, and WHO Covid-19 databases (to 31 March 2021) and references in included studies.Study eligibility criteriaStudies with a proven or hypothesized transmission chain based either on serial PCR cycle threshold readings and/or viral culture and/or gene sequencing, with adequate follow-up.ParticipantsPeople exposed to SARS-CoV-2 within 2-14 days to index asymptomatic (at time of observation) infected individuals.InterventionsReliability of symptom and signs was assessed within contemporary knowledge; transmission likelihood was assessed using adapted causality criteria.MethodsSystematic review. We contacted all included studies' corresponding authors requesting further details.ResultsWe included 18 studies from a diverse setting with substantial methodological variation (this field lacks standardized methodology). At initial testing, prevalence of asymptomatic cases was 12.5-100%. Of these, 6-100% were later determined to be presymptomatic, this proportion varying according to setting, methods of case ascertainment and population. Nursing/care home facilities reported high rates of presymptomatic: 50-100% (n = 3 studies). Fourteen studies were classified as high risk of, and four studies as at moderate risk of symptom ascertainment bias. High-risk studies may be less likely to distinguish between presymptomatic and asymptomatic cases. Six asymptomatic studies and four presymptomatic studies reported culturing infectious virus; data were too sparse to determine infectiousness duration. Three studies provided evidence of possible and three of probable/likely asymptomatic transmission; five studies provided possible and two probable/likely presymptomatic SARS-CoV-2 transmission.ConclusionHigh-quality studies provide probable evidence of SARS-CoV-2 transmission from presymptomatic and asymptomatic individuals, with highly variable estimated transmission rates.

Dataset Information

Radiomics-based model for accurately distinguishing between severe acute respiratory syndrome associated coronavirus 2 (SARS-CoV-2) and influenza A infected pneumonia.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets