Dataset Information

Predicting clinical outcomes in COVID-19 using radiomics on chest radiographs.

ABSTRACT:

Objectives

For optimal utilization of healthcare resources, there is a critical need for early identification of COVID-19 patients at risk of poor prognosis as defined by the need for intensive unit care and mechanical ventilation. We tested the feasibility of chest X-ray (CXR)-based radiomics metrics to develop machine-learning algorithms for predicting patients with poor outcomes.

Methods

In this Institutional Review Board (IRB) approved, Health Insurance Portability and Accountability Act (HIPAA) compliant, retrospective study, we evaluated CXRs performed around the time of admission from 167 COVID-19 patients. Of the 167 patients, 68 (40.72%) required intensive care during their stay, 45 (26.95%) required intubation, and 25 (14.97%) died. Lung opacities were manually segmented using ITK-SNAP (open-source software). CaPTk (open-source software) was used to perform 2D radiomics analysis.

Results

Of all the algorithms considered, the AdaBoost classifier performed the best with AUC = 0.72 to predict the need for intubation, AUC = 0.71 to predict death, and AUC = 0.61 to predict the need for admission to the intensive care unit (ICU). AdaBoost had similar performance with ElasticNet in predicting the need for admission to ICU. Analysis of the key radiomic metrics that drive model prediction and performance showed the importance of first-order texture metrics compared to other radiomics panel metrics. Using a Venn-diagram analysis, two first-order texture metrics and one second-order texture metric that consistently played an important role in driving model performance in all three outcome predictions were identified.

Conclusions

Considering the quantitative nature and reliability of radiomic metrics, they can be used prospectively as prognostic markers to individualize treatment plans for COVID-19 patients and also assist with healthcare resource management.

Advances in knowledge

We report on the performance of CXR-based imaging metrics extracted from RT-PCR positive COVID-19 patients at admission to develop machine-learning algorithms for predicting the need for ICU, the need for intubation, and mortality, respectively.

SUBMITTER: Varghese BA

PROVIDER: S-EPMC9328073 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting clinical outcomes in COVID-19 using radiomics on chest radiographs.

Varghese Bino Abel BA Shin Heeseop H Desai Bhushan B Gholamrezanezhad Ali A Lei Xiaomeng X Perkins Melissa M Oberai Assad A Nanda Neha N Cen Steven S Duddalwar Vinay V

The British journal of radiology 20210914 1126

<h4>Objectives</h4>For optimal utilization of healthcare resources, there is a critical need for early identification of COVID-19 patients at risk of poor prognosis as defined by the need for intensive unit care and mechanical ventilation. We tested the feasibility of chest X-ray (CXR)-based radiomics metrics to develop machine-learning algorithms for predicting patients with poor outcomes.<h4>Methods</h4>In this Institutional Review Board (IRB) approved, Health Insurance Portability and Account ...[more]

PMID: 34520246

Similar Datasets

Project description:ObjectiveTo evaluate whether the initial chest X-ray (CXR) severity assessed by an AI system may have prognostic utility in patients with COVID-19.MethodsThis retrospective single-center study included adult patients presenting to the emergency department (ED) between February 25 and April 9, 2020, with SARS-CoV-2 infection confirmed on real-time reverse transcriptase polymerase chain reaction (RT-PCR). Initial CXRs obtained on ED presentation were evaluated by a deep learning artificial intelligence (AI) system and compared with the Radiographic Assessment of Lung Edema (RALE) score, calculated by two experienced radiologists. Death and critical COVID-19 (admission to intensive care unit (ICU) or deaths occurring before ICU admission) were identified as clinical outcomes. Independent predictors of adverse outcomes were evaluated by multivariate analyses.ResultsSix hundred ninety-seven 697 patients were included in the study: 465 males (66.7%), median age of 62 years (IQR 52-75). Multivariate analyses adjusting for demographics and comorbidities showed that an AI system-based score ≥ 30 on the initial CXR was an independent predictor both for mortality (HR 2.60 (95% CI 1.69 - 3.99; p < 0.001)) and critical COVID-19 (HR 3.40 (95% CI 2.35-4.94; p < 0.001)). Other independent predictors were RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.ConclusionAI- and radiologist-assessed disease severity scores on CXRs obtained on ED presentation were independent and comparable predictors of adverse outcomes in patients with COVID-19.Trial registrationClinicalTrials.gov NCT04318366 ( https://clinicaltrials.gov/ct2/show/NCT04318366 ).Key points• AI system-based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients. • Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease. • The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.

Project description:IntroductionPulmonary opacities in COVID-19 increase throughout the illness and peak after ten days. The radiological literature mainly focuses on CT findings. The purpose of this study was to assess the diagnostic and prognostic value of chest radiographs (CXR) for coronavirus disease 2019 (COVID-19) at presentation.MethodsWe retrospectively identified consecutive reverse transcription polymerase reaction-confirmed COVID-19 patients (n = 104, 75% men) and patients (n = 75, 51% men) with repeated negative severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) tests. Two radiologists blindly and independently reviewed the CXRs, documented findings, assigned radiographic assessment of lung edema (RALE) scores, and predicted the patients' COVID-19 status. We calculated interobserver reliability. The score use for diagnosis and prognosis of COVID-19 was evaluated with the area under the receiver operating characteristic curve.ResultsThe overall RALE score failed to identify COVID-19 patients at presentation. However, the score was inversely correlated with a COVID-19 diagnosis within ≤2 days, and a positive correlation was found six days after symptom onset.Interobserver agreement with regard to separating normal from abnormal CXRs was moderate (k = 0.408) with low specificity (25% and 27%). Definite pleural effusion had almost perfect agreement (k = 0.833) and substantially reduced the odds of a COVID-19 diagnosis. Disease distribution and experts' opinion on COVID-19 status had only fair interobserver agreement. The RALE score interobserver reliability was moderate to good (intraclass correlation coefficient = 0.745). A high RALE score predicted a poor outcome (intensive care unit hospitalization, intubation, or death) in COVID-19 patients; a score of ≥5 substantially increased the odds of having a poor outcome.ConclusionChest radiography was found not to be a valid diagnostic tool for COVID-19, as normal or near-normal CXRs are more likely early in the disease course. Pleural effusions at presentation suggest a diagnosis other than COVID-19. More extensive lung opacities at presentation are associated with poor outcome in COVID-19 patients. Thus, patients with more than minimal opacities should be monitored closely for clinical deterioration. This clinical application of CXR is its greatest strength in COVID-19 as it impacts patient care.

Project description:The COVID-19 pandemic is causing a major outbreak in more than 150 countries around the world, having a severe impact on the health and life of many people globally. One of the crucial step in fighting COVID-19 is the ability to detect the infected patients early enough, and put them under special care. Detecting this disease from radiography and radiology images is perhaps one of the fastest ways to diagnose the patients. Some of the early studies showed specific abnormalities in the chest radiograms of patients infected with COVID-19. Inspired by earlier works, we study the application of deep learning models to detect COVID-19 patients from their chest radiography images. We first prepare a dataset of 5000 Chest X-rays from the publicly available datasets. Images exhibiting COVID-19 disease presence were identified by board-certified radiologist. Transfer learning on a subset of 2000 radiograms was used to train four popular convolutional neural networks, including ResNet18, ResNet50, SqueezeNet, and DenseNet-121, to identify COVID-19 disease in the analyzed chest X-ray images. We evaluated these models on the remaining 3000 images, and most of these networks achieved a sensitivity rate of 98% ( ± 3%), while having a specificity rate of around 90%. Besides sensitivity and specificity rates, we also present the receiver operating characteristic (ROC) curve, precision-recall curve, average prediction, and confusion matrix of each model. We also used a technique to generate heatmaps of lung regions potentially infected by COVID-19 and show that the generated heatmaps contain most of the infected areas annotated by our board certified radiologist. While the achieved performance is very encouraging, further analysis is required on a larger set of COVID-19 images, to have a more reliable estimation of accuracy rates. The dataset, model implementations (in PyTorch), and evaluations, are all made publicly available for research community at https://github.com/shervinmin/DeepCovid.git.

Dataset Information

Predicting clinical outcomes in COVID-19 using radiomics on chest radiographs.

Objectives

Methods

Results

Conclusions

Advances in knowledge

Publications

Predicting clinical outcomes in COVID-19 using radiomics on chest radiographs.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets