AI assistance improved radiologists' performance in distinguishing COVID-19 from pneumonia of other etiology on chest CT. Key Results: An AI model had higher test accuracy (96% vs 85%, p<0.001), sensitivity (95% vs 79%, p<0.001), and specificity (96% vs 88%, p=0.002) than radiologists. In an independent test set, our AI model achieved an accuracy of 87%, sensitivity of 89% and specificity of 86%. With AI assistance, the radiologists achieved a higher average accuracy (90% vs 85%, p<0.001), sensitivity (88% vs 79%, p<0.001) and specificity (91% vs 88%, p=0.001). AbstractBackground: COVID-19 and pneumonia of other etiology share similar CT characteristics, contributing to the challenges in differentiating them with high accuracy.Purpose: To establish and evaluate an artificial intelligence (AI) system in differentiating COVID-19 and other pneumonia on chest CT and assess radiologist performance without and with AI assistance.Methods: 521 patients with positive RT-PCR for COVID-19 and abnormal chest CT findings were retrospectively identified from ten hospitals from January 2020 to April 2020. 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia on chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by two-layer fully-connected neural network to pool slices together.Our final cohort of 1,186 patients (132,583 CT slices) was divided into training, validation and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance on separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance.Results: Our final model achieved a test accuracy of 96% (95% CI: 90-98%), sensitivity 95% (95% CI: 83-100%) and specificity of 96% (95% CI: 88-99%) with Receiver Operating Characteristic (ROC) AUC of 0.95 and Precision-Recall (PR) AUC of 0.90. On independent testing, our model achieved an accuracy of 87% (95% CI: 82-90%), sensitivity of 89% (95% CI: 81-94%) and specificity of 86% (95% CI: 80-90%) with ROC AUC of 0.90 and PR AUC of 0.87. Assisted by the models' probabilities, the radiologists achieved a higher average test accuracy (90% vs. 85%, ∆=5, p<0.001), sensitivity (88% vs. 79%, ∆=9, p<0.001) and specificity (91% vs. 88%, ∆=3, p=0.001).
Highlights Blood group was the risk factors for COVID-19. Blood group was related to the clinical characteristics of patients. Patients with blood group A had an increased risk for infection with SARS-CoV-2, whereas blood group O was associated with a decreased risk.
The outbreak of coronavirus disease 2019 (COVID-19) has rapidly spread to become a worldwide emergency. Early identification of patients at risk of progression may facilitate more individually aligned treatment plans and optimized utilization of medical resource. Here we conducted a multicenter retrospective study involving patients with moderate COVID-19 pneumonia to investigate the utility of chest computed tomography (CT) and clinical characteristics to risk-stratify the patients. Our results show that CT severity score is associated with inflammatory levels and that older age, higher neutrophil-to-lymphocyte ratio (NLR), and CT severity score on admission are independent risk factors for short-term progression. The nomogram based on these risk factors shows good calibration and discrimination in the derivation and validation cohorts. These findings have implications for predicting the progression risk of COVID-19 pneumonia patients at the time of admission. CT examination may help risk-stratification and guide the timing of admission.
Rationale:The increasing speed of confirmed 2019 novel coronavirus (COVID-19) cases is striking in China. The purpose of this study is to summarize the outcomes of patients with novel COVID-19 pneumonia (NCP) at our institution. Methods: In this single-center study, we retrospectively included 118 cases of NCP, from January 16, 2020 to February 4, 2020. The clinical outcomes were monitored up to February 11, 2020. The outcomes of NCP patients were phase summarized at our institution. Three kinds of responses to clinical treatment were defined and evaluated: 1) good, symptoms continually improved; 2) fair, symptoms not improved or relapsed; 3) poor, symptoms aggravated. The risk factors, including basal clinical characteristics, CT imaging features, and follow-up CT changes (no change, progress, and improvement) related to poor/fair outcomes, were also investigated. Results: Six patients were improved to no-emergency type, 2 remained the same, and 2 progressed to fatal type. Besides, 13 patients progressed from the common type group to the emergency group (3 in fatal type and 10 in severe type). Forty-two (35.6%) patients were discharged with a median hospital stay of 9.5 days (range, 4.0-15.0 days). Thus, the numbers in different responses were, 73 patients in good response group (4 emergency cases, 69 no-emergency cases), 28 in fair response group (3 emergency cases, 25 no-emergency cases), and 17 in poor response group (3 emergency cases, 14 no-emergency cases). No patient has died in our hospital to date. The median duration of progress observed from CT scans was 6 days (range, 2-14 days). The progression in abnormal imaging findings indicate a poor/fair response, whereas the alleviated symptoms seen from CT suggest a good response. Conclusion: Most cases are no-emergency type and have a favorable response to clinical treatment. Follow-up CT changes during the treatment can help evaluate the treatment response of patients with NCP.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.