Show: 20 | 50 | 100
Results 1 - 7 de 7
Filter

Database
Main subject
Type of study
Journal
Year
Document Type
Year range
1.
Med Phys ; 2022 Mar 08.
Article in English | MEDLINE | ID: covidwho-1729178

##### ABSTRACT

PURPOSE: To develop a deep learning model design that integrates radiomics analysis for enhanced performance of COVID-19 and non-COVID-19 pneumonia detection using chest x-ray images. METHODS: As a novel radiomics approach, a 2D sliding kernel was implemented to map the impulse response of radiomic features throughout the entire chest x-ray image; thus, each feature is rendered as a 2D map in the same dimension as the x-ray image. Based on each of the three investigated deep neural network architectures, including VGG-16, VGG-19, and DenseNet-121, a pilot model was trained using x-ray images only. Subsequently, two radiomic feature maps (RFMs) were selected based on cross-correlation analysis in reference to the pilot model saliency map results. The radiomics-boosted model was then trained based on the same deep neural network architecture using x-ray images plus the selected RFMs as input. The proposed radiomics-boosted design was developed using 812 chest x-ray images with 262/288/262 COVID-19/non-COVID-19 pneumonia/healthy cases, and 649/163 cases were assigned as training-validation/independent test sets. For each model, 50 runs were trained with random assignments of training/validation cases following the 7:1 ratio in the training-validation set. Sensitivity, specificity, accuracy, and ROC curves together with area-under-the-curve (AUC) from all three deep neural network architectures were evaluated. RESULTS: After radiomics-boosted implementation, all three investigated deep neural network architectures demonstrated improved sensitivity, specificity, accuracy, and ROC AUC results in COVID-19 and healthy individual classifications. VGG-16 showed the largest improvement in COVID-19 classification ROC (AUC from 0.963 to 0.993), and DenseNet-121 showed the largest improvement in healthy individual classification ROC (AUC from 0.962 to 0.989). The reduced variations suggested improved robustness of the model to data partition. For the challenging non-COVID-19 pneumonia classification task, radiomics-boosted implementation of VGG-16 (AUC from 0.918 to 0.969) and VGG-19 (AUC from 0.964 to 0.970) improved ROC results, while DenseNet-121 showed a slight yet insignificant ROC performance reduction (AUC from 0.963 to 0.949). The achieved highest accuracy of COVID-19/non-COVID-19 pneumonia/healthy individual classifications were 0.973 (VGG-19)/0.936 (VGG-19)/ 0.933 (VGG-16), respectively. CONCLUSIONS: The inclusion of radiomic analysis in deep learning model design improved the performance and robustness of COVID-19/non-COVID-19 pneumonia/healthy individual classification, which holds great potential for clinical applications in the COVID-19 pandemic.

2.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-312678

##### ABSTRACT

To develop a deep-learning model that integrates radiomics analysis for enhanced performance of COVID-19 and Non-COVID-19 pneumonia detection using chest X-ray image, two deep-learning models were trained based on a pre-trained VGG-16 architecture: in the 1st model, X-ray image was the sole input;in the 2nd model, X-ray image and 2 radiomic feature maps (RFM) selected by the saliency map analysis of the 1st model were stacked as the input. Both models were developed using 812 chest X-ray images with 262/288/262 COVID-19/Non-COVID-19 pneumonia/healthy cases, and 649/163 cases were assigned as training-validation/independent test sets. In 1st model using X-ray as the sole input, the 1) sensitivity, 2) specificity, 3) accuracy, and 4) ROC Area-Under-the-Curve of COVID-19 vs Non-COVID-19 pneumonia detection were 1) 0.90$\pm$0.07 vs 0.78$\pm$0.09, 2) 0.94$\pm$0.04 vs 0.94$\pm$0.04, 3) 0.93$\pm$0.03 vs 0.89$\pm$0.03, and 4) 0.96$\pm$0.02 vs 0.92$\pm$0.04. In the 2nd model, two RFMs, Entropy and Short-Run-Emphasize, were selected with their highest cross-correlations with the saliency maps of the 1st model. The corresponding results demonstrated significant improvements (p<0.05) of COVID-19 vs Non-COVID-19 pneumonia detection: 1) 0.95$\pm$0.04 vs 0.85$\pm$0.04, 2) 0.97$\pm$0.02 vs 0.96$\pm$0.02, 3) 0.97$\pm$0.02 vs 0.93$\pm$0.02, and 4) 0.99$\pm$0.01 vs 0.97$\pm$0.02. The reduced variations suggested a superior robustness of 2nd model design.

3.
EuropePMC; 2020.
Preprint in English | EuropePMC | ID: ppcovidwho-321361

##### ABSTRACT

Background: Since December 2019, coronavirus disease 2019 (COVID-19), as an infectious disease with cytokine storm, has become an emerging global challenge. To assess the duration of SARS-COV-2 viral shedding and associated risk factors in COVID-19 patients. Methods: : COVID-19 patients with interleukin (IL)-1b, soluble interleukin-2 receptor (sIL-2R), IL-6, IL-8, IL-10 and tumor necrosis factor (TNF)-α cytokines data consecutively admitted to Tongji Hospital from January 27, 2020 through February 5, 2020 were enrolled and been followed up until March 24, 2020. We utilized Kaplan-Meier method and Cox proportional hazards regression analysis to assess the duration of viral shedding and risk factors affecting virus clearance. Results: : 246 inpatients with laboratory confirmed COVID-19 were enrolled. The median duration of viral shedding was 24 days, ranging from 6 to 63 days. Age, severity of COVID-19, albumin, lactate dehydrogenase (LDH), D-dimer, ferritin and sIL-2R were associated with duration of viral shedding. Administration of lopinavir-ritonavir, arbidol, oseltamivir and intravenous immunoglobulin did not shorten viral shedding time. Multivariate cox regression analysis revealed that sIL-2R, LDH and severity of COVID-19 were independent factors associated with duration of viral shedding. At stratified analysis, the viral shedding time was positively correlated with age, sIL-2R and LDH in non-corticosteroid subgroup, while negatively correlated with lymphocyte count in corticosteroid group. Conclusions: : The present study demonstrated that elevated sIL-2R, increased LDH and severe status were related to prolongation of viral shedding in COVID-19 inpatients. Further research is urgent to investigate the mechanism of immune reaction involved in the virus clearance process and aim to the optimal antiviral therapy.

4.
EuropePMC; 2021.
Preprint in English | EuropePMC | ID: ppcovidwho-294967

##### ABSTRACT

To develop a deep-learning model that integrates radiomics analysis for enhanced performance of COVID-19 and Non-COVID-19 pneumonia detection using chest X-ray image, two deep-learning models were trained based on a pre-trained VGG-16 architecture: in the 1st model, X-ray image was the sole input;in the 2nd model, X-ray image and 2 radiomic feature maps (RFM) selected by the saliency map analysis of the 1st model were stacked as the input. Both models were developed using 812 chest X-ray images with 262/288/262 COVID-19/Non-COVID-19 pneumonia/healthy cases, and 649/163 cases were assigned as training-validation/independent test sets. In 1st model using X-ray as the sole input, the 1) sensitivity, 2) specificity, 3) accuracy, and 4) ROC Area-Under-the-Curve of COVID-19 vs Non-COVID-19 pneumonia detection were 1) 0.90$\pm$0.07 vs 0.78$\pm$0.09, 2) 0.94$\pm$0.04 vs 0.94$\pm$0.04, 3) 0.93$\pm$0.03 vs 0.89$\pm$0.03, and 4) 0.96$\pm$0.02 vs 0.92$\pm$0.04. In the 2nd model, two RFMs, Entropy and Short-Run-Emphasize, were selected with their highest cross-correlations with the saliency maps of the 1st model. The corresponding results demonstrated significant improvements (p<0.05) of COVID-19 vs Non-COVID-19 pneumonia detection: 1) 0.95$\pm$0.04 vs 0.85$\pm$0.04, 2) 0.97$\pm$0.02 vs 0.96$\pm$0.02, 3) 0.97$\pm$0.02 vs 0.93$\pm$0.02, and 4) 0.99$\pm$0.01 vs 0.97$\pm$0.02. The reduced variations suggested a superior robustness of 2nd model design.

5.
Ann Transl Med ; 9(18): 1446, 2021 Sep.
Article in English | MEDLINE | ID: covidwho-1436465

##### ABSTRACT

BACKGROUND: The rapid spread of coronavirus disease-19 (COVID-19) poses a global health emergency, and cases entering China from Russia are quite diverse. This study explored and compared the clinical characteristics and outcomes of severe and critically ill COVID-19 patients from Russia with and without influenza A infection, treated in a northern Chinese hospital (Russia imported patients). METHODS: A total of 32 severe and critically ill Russia-imported COVID-19 patients treated in the Heilongjiang Imported Severe and Critical COVID-19 Treatment Center from April 6 to May 11, 2020 were included, including 8 cases (group A) with and 24 cases (group B) without influenza A infection. The clinical characteristics of each group were compared, including prolonged hospital stay, duration of oxygen therapy, time from onset to a negative SARS-CoV-2 qRT-PCR RNA (Tneg) result, and duration of bacterial infection. RESULTS: The results showed that blood group, PaO2/FiO2, prothrombin time (PT), prothrombin activity (PTA), computed tomography (CT) score, hospital stay, duration of oxygenation therapy, Tneg, and duration of bacterial infection were statistically different between the two groups (P<0.05). Multivariant regression analysis showed that the Sequential Organ Failure Assessment (SOFA) score, C-reactive protein (CRP), and influenza A infection were factors influencing hospital stay; SOFA score, CRP, and CT score were factors influencing the duration of oxygenation therapy; PaO2/FiO2, platelet count (PLT), and CRP were factors influencing Tneg; and gender, SOFA score, and influenza A infection were factors influencing the duration of bacterial infection. CONCLUSIONS: Influenza A infection is common in Russia-imported COVID-19 patients, which can prolong the hospital stay and duration of bacterial infection. Routinely screening and treating influenza A should be conducted early in such patients.

6.
J Med Virol ; 92(11): 2684-2692, 2020 11.
Article in English | MEDLINE | ID: covidwho-526739

##### ABSTRACT

BACKGROUND: The rapid outbreak of coronavirus disease 2019 (COVID-19) has turned into a public health emergency of international concern. Epidemiological research has shown that sex is associated with the severity of COVID-19, but the underlying mechanism of sex predisposition remains poorly understood. We aim to study the gendered differences in inflammation reaction, and the association with severity and mortality of COVID-19. METHODS: In this retrospective study, we enrolled 548 COVID-19 inpatients from Tongji Hospital from 26 January to 5 February 2020, and followed up to 3 March 2020. Epidemiological, demographic and clinical features, and inflammatory indexes were collected and compared between males and females. The Cox proportional hazard regression model was applied to identify the gendered effect on mortality of COVID-19 after adjusting for age, comorbidity, and smoking history. The multiple linear regression method was used to explore the influence of sex on inflammation reaction. RESULTS: Males had higher mortality than females did (22.2% vs 10.4%), with an hazard ratio of 1.923 (95% confidence interval, 1.181-3.130); elder age and comorbidity were significantly associated with decease of COVID-19 patients. Excess inflammation reaction was related to severity of COVID-19. Male patients had greater inflammation reaction, with higher levels of interleukin 10, tumor necrosis factor-α, lactose dehydrogenase, ferritin, and hyper-sensitive C-reactive protein, but a lower lymphocyte count than females adjusted by age and comorbidity. CONCLUSIONS: Sex, age, and comorbidity are critical risk factors for mortality of COVID-19. Excess innate immunity and proinflammation activity, and deficiency in adaptive immunity response promote males, especially elder males, to develop a cytokine storm, causing potential acute respiratory distressed syndrome, multiple organ failure and decease.

##### Subject(s)
COVID-19/immunology , COVID-19/mortality , Cytokine Release Syndrome/immunology , Inflammation/virology , Adolescent , Adult , Age Factors , Aged , Child , Child, Preschool , China/epidemiology , Comorbidity , Cytokine Release Syndrome/virology , Female , Hospitalization/statistics & numerical data , Humans , Infant , Infant, Newborn , Inflammation/epidemiology , Male , Middle Aged , Proportional Hazards Models , Retrospective Studies , Risk Factors , Severity of Illness Index , Sex Factors , Young Adult
7.
J Allergy Clin Immunol ; 146(1): 110-118, 2020 Jul.
Article in English | MEDLINE | ID: covidwho-46911

##### ABSTRACT

BACKGROUND: In December 2019, the coronavirus disease 2019 (COVID-19) outbreak occurred in Wuhan. Data on the clinical characteristics and outcomes of patients with severe COVID-19 are limited. OBJECTIVE: We sought to evaluate the severity on admission, complications, treatment, and outcomes of patients with COVID-19. METHODS: Patients with COVID-19 admitted to Tongji Hospital from January 26, 2020, to February 5, 2020, were retrospectively enrolled and followed-up until March 3, 2020. Potential risk factors for severe COVID-19 were analyzed by a multivariable binary logistic model. Cox proportional hazard regression model was used for survival analysis in severe patients. RESULTS: We identified 269 (49.1%) of 548 patients as severe cases on admission. Older age, underlying hypertension, high cytokine levels (IL-2R, IL-6, IL-10, and TNF-α), and high lactate dehydrogenase level were significantly associated with severe COVID-19 on admission. The prevalence of asthma in patients with COVID-19 was 0.9%, markedly lower than that in the adult population of Wuhan. The estimated mortality was 1.1% in nonsevere patients and 32.5% in severe cases during the average 32 days of follow-up period. Survival analysis revealed that male sex, older age, leukocytosis, high lactate dehydrogenase level, cardiac injury, hyperglycemia, and high-dose corticosteroid use were associated with death in patients with severe COVID-19. CONCLUSIONS: Patients with older age, hypertension, and high lactate dehydrogenase level need careful observation and early intervention to prevent the potential development of severe COVID-19. Severe male patients with heart injury, hyperglycemia, and high-dose corticosteroid use may have a high risk of death.

##### Subject(s)
Coronavirus Infections/complications , Coronavirus Infections/mortality , Pneumonia, Viral/complications , Pneumonia, Viral/mortality , Adolescent , Adult , Aged , Aged, 80 and over , Betacoronavirus , COVID-19 , China/epidemiology , Cohort Studies , Comorbidity , Female , Humans , Inpatients/statistics & numerical data , Male , Middle Aged , Pandemics , Risk Factors , SARS-CoV-2 , Treatment Outcome , Young Adult