Risk factors for persistent abnormality on chest radiographs at 12-weeks post hospitalisation with PCR confirmed COVID-19.
Ontology highlight
ABSTRACT: Background
The long-term consequences of COVID-19 remain unclear. There is concern a proportion of patients will progress to develop pulmonary fibrosis. We aimed to assess the temporal change in CXR infiltrates in a cohort of patients following hospitalisation for COVID-19.Methods
We conducted a single-centre prospective cohort study of patients admitted to University Hospital Southampton with confirmed SARS-CoV2 infection between 20th March and 3rd June 2020. Patients were approached for standard-of-care follow-up 12-weeks after hospitalisation. Inpatient and follow-up CXRs were scored by the assessing clinician for extent of pulmonary infiltrates; 0-4 per lung (Nil = 0, < 25% = 1, 25-50% = 2, 51-75% = 3, > 75% = 4).Results
101 patients with paired CXRs were included. Demographics: 53% male with a median (IQR) age 53.0 (45-63) years and length of stay 9 (5-17.5) days. The median CXR follow-up interval was 82 (77-86) days with median baseline and follow-up CXR scores of 4.0 (3-5) and 0.0 (0-1) respectively. 32% of patients had persistent CXR abnormality at 12-weeks. In multivariate analysis length of stay (LOS), smoking-status and obesity were identified as independent risk factors for persistent CXR abnormality. Serum LDH was significantly higher at baseline and at follow-up in patients with CXR abnormalities compared to those with resolution. A 5-point composite risk score (1-point each; LOS ≥ 15 days, Level 2/3 admission, LDH > 750 U/L, obesity and smoking-status) strongly predicted risk of persistent radiograph abnormality (0.81).Conclusion
Persistent CXR abnormality 12-weeks post COVID-19 was common in this cohort. LOS, obesity, increased serum LDH, and smoking-status were risk factors for radiograph abnormality. These findings require further prospective validation.
SUBMITTER: Wallis TJM
PROVIDER: S-EPMC8139368 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:As one of the most ubiquitous diagnostic imaging tests in medical practice, chest radiography requires timely reporting of potential findings and diagnosis of diseases in the images. Automated, fast, and reliable detection of diseases based on chest radiography is a critical step in radiology workflow. In this work, we developed and evaluated various deep convolutional neural networks (CNN) for differentiating between normal and abnormal frontal chest radiographs, in order to help alert radiologists and clinicians of potential abnormal findings as a means of work list triaging and reporting prioritization. A CNN-based model achieved an AUC of 0.9824 ± 0.0043 (with an accuracy of 94.64 ± 0.45%, a sensitivity of 96.50 ± 0.36% and a specificity of 92.86 ± 0.48%) for normal versus abnormal chest radiograph classification. The CNN model obtained an AUC of 0.9804 ± 0.0032 (with an accuracy of 94.71 ± 0.32%, a sensitivity of 92.20 ± 0.34% and a specificity of 96.34 ± 0.31%) for normal versus lung opacity classification. Classification performance on the external dataset showed that the CNN model is likely to be highly generalizable, with an AUC of 0.9444 ± 0.0029. The CNN model pre-trained on cohorts of adult patients and fine-tuned on pediatric patients achieved an AUC of 0.9851 ± 0.0046 for normal versus pneumonia classification. Pretraining with natural images demonstrates benefit for a moderate-sized training image set of about 8500 images. The remarkable performance in diagnostic accuracy observed in this study shows that deep CNNs can accurately and effectively differentiate normal and abnormal chest radiographs, thereby providing potential benefits to radiology workflow and patient care.
| S-EPMC7224391 | biostudies-literature
Project description:Convolutional neural networks (CNNs) trained on natural images are extremely successful in image classification and localization due to superior automated feature extraction capability. In extending their use to biomedical recognition tasks, it is important to note that visual features of medical images tend to be uniquely different than natural images. There are advantages offered through training these networks on large scale medical common modality image collections pertaining to the recognition task. Further, improved generalization in transferring knowledge across similar tasks is possible when the models are trained to learn modality-specific features and then suitably repurposed for the target task. In this study, we propose modality-specific ensemble learning toward improving abnormality detection in chest X-rays (CXRs). CNN models are trained on a large-scale CXR collection to learn modality-specific features and then repurposed for detecting and localizing abnormalities. Model predictions are combined using different ensemble strategies toward reducing prediction variance and sensitivity to the training data while improving overall performance and generalization. Class-selective relevance mapping (CRM) is used to visualize the learned behavior of the individual models and their ensembles. It localizes discriminative regions of interest (ROIs) showing abnormal regions and offers an improved explanation of model predictions. It was observed that the model ensembles demonstrate superior localization performance in terms of Intersection of Union (IoU) and mean Average Precision (mAP) metrics than any individual constituent model.
| S-EPMC7083159 | biostudies-literature
Project description:Reports of persistent symptoms after hospitalization with COVID-19 have raised concern of a "long COVID" syndrome. This study aimed at determining the prevalence of and risk factors for acute and persistent symptoms in non-hospitalized patients with polymerase chain reaction (PCR) confirmed COVID-19. We conducted a cohort study of non-hospitalized participants identified via the Danish Civil Registration System with a SARS-CoV-2-positive PCR-test and available biobank samples. Participants received a digital questionnaire on demographics and COVID-19-related symptoms. Persistent symptoms: symptoms > 4 weeks (in sensitivity analyses > 12 weeks). We included 445 participants, of whom 34% were asymptomatic. Most common acute symptoms were fatigue, headache, and sneezing, while fatigue and reduced smell and taste were most severe. Persistent symptoms, most commonly fatigue and memory and concentration difficulties, were reported by 36% of 198 symptomatic participants with follow-up > 4 weeks. Risk factors for persistent symptoms included female sex (women 44% vs. men 24%, odds ratio 2.7, 95% CI 1.4-5.1, p = 0.003) and BMI (odds ratio 1.1, 95% CI 1.0-1.2, p = 0.001). In conclusion, among non-hospitalized PCR-confirmed COVID-19 patients one third were asymptomatic while one third of symptomatic participants had persistent symptoms illustrating the heterogeneity of disease presentation. These findings should be considered in health care planning and policy making related to COVID-19.
| S-EPMC8222239 | biostudies-literature
Project description:Background Disease severity on chest radiographs (CXR) has been associated with higher risk of disease progression and adverse outcomes from COVID-19. Few studies have evaluated COVID-19-related racial/ethnic disparities in radiology. Purpose To evaluate whether Non-White minority patients hospitalized with confirmed COVID-19 infection presented with increased severity on admission CXR compared with White/Non-Hispanic patients. Methods Single-institution, retrospective cohort study approved by the IRB. Patients hospitalized with confirmed COVID-19 infection (3/27/20-4/10/20) were identified using the electronic medical record (EMR) (n=326, mean age: 59 years (SD: 17 years), M:F (188:138). Primary outcome was severity of lung disease on admission CXR, measured by modified Radiographic Assessment of Lung Edema (mRALE) score. Secondary outcome was a composite adverse clinical outcome of intubation, ICU admission, or death. Primary exposure was racial/ethnic category: White/Non-Hispanic versus Non-White [i.e., Hispanic, Black, Asian, Other]. Multivariable linear regression analyses were performed to evaluate the association between mRALE scores and race/ethnicity. Results Non-White patients had significantly higher mRALE scores (median 6.1, 95% CI 5.4-6.7) compared with White/Non-Hispanic patients (median 4.2, 95% CI 3.6-4.9) (unadjusted average difference 1.8, 95% CI 0.9-2.8, p<0.01). For both White (Adjusted HR, 1.3, 95%CI 1.2-1.4, p<0.001) and Non-White patients (Adjusted HR 1.2, 95%CI 1.1-1.3, p<0.001), increasing mRALE scores were associated with a higher likelihood of experiencing composite adverse outcome with no evidence of interaction (p = 0.16). Multivariable linear regression analyses demonstrated that Non-White patients presented with higher mRALE scores on admission CXR versus White/Non-Hispanic patients (adjusted average difference 1.6, 95% CI 0.5-2.7, p<0.01). Adjustment for hypothesized mediators revealed that the association between race/ethnicity and mRALE scores was mediated by limited English proficiency (p<0.01). Conclusion Non-White patients hospitalized with COVID-19 infection were more likely to present with higher severity of disease on admission CXR than White/Non-Hispanic patients, and increased severity was associated with worse outcomes for all patients.
| S-EPMC7370353 | biostudies-literature
Project description:The purposes of this study are to propose an unsupervised anomaly detection method based on a deep neural network (DNN) model, which requires only normal images for training, and to evaluate its performance with a large chest radiograph dataset. We used the auto-encoding generative adversarial network (α-GAN) framework, which is a combination of a GAN and a variational autoencoder, as a DNN model. A total of 29,684 frontal chest radiographs from the Radiological Society of North America Pneumonia Detection Challenge dataset were used for this study (16,880 male and 12,804 female patients; average age, 47.0 years). All these images were labeled as "Normal," "No Opacity/Not Normal," or "Opacity" by board-certified radiologists. About 70% (6,853/9,790) of the Normal images were randomly sampled as the training dataset, and the rest were randomly split into the validation and test datasets in a ratio of 1:2 (7,610 and 15,221). Our anomaly detection system could correctly visualize various lesions including a lung mass, cardiomegaly, pleural effusion, bilateral hilar lymphadenopathy, and even dextrocardia. Our system detected the abnormal images with an area under the receiver operating characteristic curve (AUROC) of 0.752. The AUROCs for the abnormal labels Opacity and No Opacity/Not Normal were 0.838 and 0.704, respectively. Our DNN-based unsupervised anomaly detection method could successfully detect various diseases or anomalies in chest radiographs by training with only the normal images.
| S-EPMC8289984 | biostudies-literature
Project description:Tph1WT (n = 3) and Tph1KO (n = 3) mice were exposed to 6 azoxymethane (AOM) injections and euthanatized after 12 weeks from the first carcinogenic exposure.
2019-02-12 | GSE126393 | GEO
Project description:Introduction What is known about checklists for interpreting chest radiographs? The question will guide the development of the inclusion criteria for the scoping review. Breaking down the scoping review question will allow the evaluation of inclusion and exclusion criteria for the protocol. The eligibility of the proposed research question will be assessed using the Population or Participants, Concept and Context (PCC) framework. Background X-ray reporting can be standardised using checklists. Checklists may reduce the time needed to produce a comprehensive X-ray report and improve the quality and consistency of detecting abnormalities on chest radiographs. This scoping review aims to map the available literature on what is known about checklists for interpreting chest radiographs. Methods We will follow the methodological framework for scoping reviews originally described by Arksey and O’Malley. The scoping review will include articles that describe checklists for reducing diagnostic errors, checklists for analysing chest radiographs, checklists for identifying abnormalities on chest radiographs and checklists for reporting chest radiographs in all settings. Search terms are chest radiographs, checklists, and chest X-rays. We will search for peer-reviewed articles and grey literature including dissertations and theses. We will search online databases including Ovid Medline and Ebscohost, to identify articles published in English from 1994 to 2022. The searched articles will undergo two levels of screening, first the title and abstract screening, then a full-text screening by two reviewers. Data from the selected articles will be extracted, using a tested extraction form and charted using the Joanna Briggs Institute guidelines. Results The results will be collated, summarised and discussed including any limitations of the included articles. The articles will be summarised in a table, as well as narratively. The distribution of studies will be summarised quantitatively and the numerical analysis will provide an overview and identify knowledge gaps. Content analysis will map different checklists available for chest interpretation. Discussion The results of the scoping review will be used to develop a checklist that will be used by medical doctors in collaboration with radiographers working in settings where there are no radiologists on-site, for interpreting chest radiographs. Systematic review registration Scoping review protocol registered with Open Science Framework on 27 July 2022. Registration https://doi.org/10.17605/OSF.IO/JS5PQ Supplementary Information The online version contains supplementary material available at 10.1186/s13643-023-02327-w.
| S-EPMC10466731 | biostudies-literature
Project description:PurposeTo develop a machine learning model to classify the severity grades of pulmonary edema on chest radiographs.Materials and methodsIn this retrospective study, 369 071 chest radiographs and associated radiology reports from 64 581 patients (mean age, 51.71 years; 54.51% women) from the MIMIC-CXR chest radiograph dataset were included. This dataset was split into patients with and without congestive heart failure (CHF). Pulmonary edema severity labels from the associated radiology reports were extracted from patients with CHF as four different ordinal levels: 0, no edema; 1, vascular congestion; 2, interstitial edema; and 3, alveolar edema. Deep learning models were developed using two approaches: a semisupervised model using a variational autoencoder and a pretrained supervised learning model using a dense neural network. Receiver operating characteristic curve analysis was performed on both models.ResultsThe area under the receiver operating characteristic curve (AUC) for differentiating alveolar edema from no edema was 0.99 for the semisupervised model and 0.87 for the pretrained models. Performance of the algorithm was inversely related to the difficulty in categorizing milder states of pulmonary edema (shown as AUCs for semisupervised model and pretrained model, respectively): 2 versus 0, 0.88 and 0.81; 1 versus 0, 0.79 and 0.66; 3 versus 1, 0.93 and 0.82; 2 versus 1, 0.69 and 0.73; and 3 versus 2, 0.88 and 0.63.ConclusionDeep learning models were trained on a large chest radiograph dataset and could grade the severity of pulmonary edema on chest radiographs with high performance.Supplemental material is available for this article.See also the commentary by Auffermann in this issue.© RSNA, 2021.
| S-EPMC8043362 | biostudies-literature
Project description:We propose a deep learning system to automatically detect four explainable emphysema signs on frontal and lateral chest radiographs. Frontal and lateral chest radiographs from 3000 studies were retrospectively collected. Two radiologists annotated these with 4 radiological signs of pulmonary emphysema identified from the literature. A patient with ≥2 of these signs present is considered emphysema positive. Using separate deep learning systems for frontal and lateral images we predict the presence of each of the four visual signs and use these to determine emphysema positivity. The ROC and AUC results on a set of 422 held-out cases, labeled by both radiologists, are reported. Comparison with a black-box model which predicts emphysema without the use of explainable visual features is made on the annotations from both radiologists, as well as the subset that they agreed on. DeLong's test is used to compare with the black-box model ROC and McNemar's test to compare with radiologist performance. In 422 test cases, emphysema positivity was predicted with AUCs of 0.924 and 0.946 using the reference standard from each radiologist separately. Setting model sensitivity equivalent to that of the second radiologist, our model has a comparable specificity (p = 0.880 and p = 0.143 for each radiologist respectively). Our method is comparable with the black-box model with AUCs of 0.915 (p = 0.407) and 0.935 (p = 0.291), respectively. On the 370 cases where both radiologists agreed (53 positives), our model achieves an AUC of 0.981, again comparable to the black-box model AUC of 0.972 (p = 0.289). Our proposed method can predict emphysema positivity on chest radiographs as well as a radiologist or a comparable black-box method. It additionally produces labels for four visual signs to ensure the explainability of the result. The dataset is publicly available at https://doi.org/10.5281/zenodo.6373392.
| S-EPMC9333227 | biostudies-literature
Project description:BackgroundLung cancer is the second most common and the most fatal form of cancer. Although annual low-dose computed tomography is used as the primary method of cancer screening, it presents challenges regarding resources as well as potential health risks from radiation exposure. Chest radiography (CXR), though less effective, is used frequently and commonly. Moreover, often in clinical settings, CXR is the first imaging modality used; computed tomography is subsequently performed if abnormalities are detected on CXRs. This study examined whether controlling for distractors and time constraints, as well as side-by-side comparison of multiple CXRs in clinical settings can aid earlier detection of radiological abnormalities indicative of lung cancer lesions.MethodsThirty-two attending physicians in the Republic of Korea examined 1,750 radiographs of 50 lung cancer cases. Using "hot spot" technology, participants indicated the possible locations of cancer lesions on each radiograph. Subsequently, the same radiographs, cropped to focus the anatomical regions where lung cancers were diagnosed, were shown side-by-side to the participants. The participants were asked to identify the radiograph which first enabled the diagnosis of lung cancer and which first showed a possible lesion.ResultsRemoval of systemic constraints alone significantly improved lesion identification by 221.72±9.69 days. Presenting radiographs side-by-side, cropped to relevant areas, had an additional significant and positive impact on cancer detection in both hidden and open areas on CXRs. Also, lesions were detected at smaller sizes and earlier than when actually diagnosed.ConclusionsCXR with improved methods and settings provides an easily accessible and low-risk imaging method for earlier detection of lung cancer compared to current clinical imaging settings. Further, this study demonstrates the potential effectiveness of programs that allow side-by-side comparisons of cropped areas of multiple radiographs to detect radiological abnormalities.
| S-EPMC7354112 | biostudies-literature