Dataset Information

The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission.

ABSTRACT: Triage is crucial for patient's management and estimation of the required intensive care unit (ICU) beds is fundamental for health systems during the COVID-19 pandemic. We assessed whether chest computed tomography (CT) of COVID-19 pneumonia has an incremental role in predicting patient's admission to ICU. We performed volumetric and texture analysis of the areas of the affected lung in CT of 115 outpatients with COVID-19 infection presenting to the emergency room with dyspnea and unresponsive hypoxyemia. Admission blood laboratory including lymphocyte count, serum lactate dehydrogenase, D-dimer and C-reactive protein and the ratio between the arterial partial pressure of oxygen and inspired oxygen were collected. By calculating the areas under the receiver-operating characteristic curves (AUC), we compared the performance of blood laboratory-arterial gas analyses features alone and combined with the CT features in two hybrid models (Hybrid radiological and Hybrid radiomics)for predicting ICU admission. Following a machine learning approach, 63 patients were allocated to the training and 52 to the validation set. Twenty-nine (25%) of patients were admitted to ICU. The Hybrid radiological model comprising the lung %consolidation performed significantly (p = 0.04) better in predicting ICU admission in the validation (AUC = 0.82; 95% confidence interval 0.73-0.97) set than the blood laboratory-arterial gas analyses features alone (AUC = 0.71; 95% confidence interval 0.56-0.86). A risk calculator for ICU admission was derived and is available at: https://github.com/cgplab/covidapp . The volume of the consolidated lung in CT of patients with COVID-19 pneumonia has a mild but significant incremental value in predicting ICU admission.

SUBMITTER: Bartolucci M

PROVIDER: S-EPMC8329253 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BackgroundCOVID-19 pandemic has currently no vaccines. Thus, the only feasible solution for prevention relies on the detection of COVID-19-positive cases through quick and accurate testing. Since artificial intelligence (AI) offers the powerful mechanism to automatically extract the tissue features and characterise the disease, we therefore hypothesise that AI-based strategies can provide quick detection and classification, especially for radiological computed tomography (CT) lung scans.MethodologySix models, two traditional machine learning (ML)-based (k-NN and RF), two transfer learning (TL)-based (VGG19 and InceptionV3), and the last two were our custom-designed deep learning (DL) models (CNN and iCNN), were developed for classification between COVID pneumonia (CoP) and non-COVID pneumonia (NCoP). K10 cross-validation (90% training: 10% testing) protocol on an Italian cohort of 100 CoP and 30 NCoP patients was used for performance evaluation and bispectrum analysis for CT lung characterisation.ResultsUsing K10 protocol, our results showed the accuracy in the order of DL > TL > ML, ranging the six accuracies for k-NN, RF, VGG19, IV3, CNN, iCNN as 74.58 ± 2.44%, 96.84 ± 2.6, 94.84 ± 2.85%, 99.53 ± 0.75%, 99.53 ± 1.05%, and 99.69 ± 0.66%, respectively. The corresponding AUCs were 0.74, 0.94, 0.96, 0.99, 0.99, and 0.99 (p-values < 0.0001), respectively. Our Bispectrum-based characterisation system suggested CoP can be separated against NCoP using AI models. COVID risk severity stratification also showed a high correlation of 0.7270 (p < 0.0001) with clinical scores such as ground-glass opacities (GGO), further validating our AI models.ConclusionsWe prove our hypothesis by demonstrating that all the six AI models successfully classified CoP against NCoP due to the strong presence of contrasting features such as ground-glass opacities (GGO), consolidations, and pleural effusion in CoP patients. Further, our online system takes < 2 s for inference.

Dataset Information

The incremental value of computed tomography of COVID-19 pneumonia in predicting ICU admission.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets