Performances of clinical characteristics and radiological findings in identifying COVID-19 from suspected cases.

BACKGROUND: To identify effective factors and establish a model to distinguish COVID-19 patients from suspected cases. METHODS: The clinical characteristics, laboratory results and initial chest CT findings of suspected COVID-19 patients in 3 institutions were retrospectively reviewed. Univariate and multivariate logistic regression were performed to identify significant features. A nomogram was constructed, with calibration validated internally and externally. RESULTS: 239 patients from 2 institutions were enrolled in the primary cohort including 157 COVID-19 and 82 non-COVID-19 patients. 11 features were selected by LASSO selection, and 8 features were found significant using multivariate logistic regression analysis. We found that the COVID-19 group are more likely to have fever (OR 4.22), contact history (OR 284.73), lower WBC count (OR 0.63), left lower lobe involvement (OR 9.42), multifocal lesions (OR 8.98), pleural thickening (OR 5.59), peripheral distribution (OR 0.09), and less mediastinal lymphadenopathy (OR 0.037). The nomogram developed accordingly for clinical practice showed satisfactory internal and external validation. CONCLUSIONS: In conclusion, fever, contact history, decreased WBC count, left lower lobe involvement, pleural thickening, multifocal lesions, peripheral distribution, and absence of mediastinal lymphadenopathy are able to distinguish COVID-19 patients from other suspected patients. The corresponding nomogram is a useful tool in clinical practice.

Assessment of dynamic hepatic and renal imaging changes in COVID-19 survivors using T1 mapping and IVIM-DWI.

PURPOSE: To explore the imaging changes of the liver and kidneys in COVID-19 survivors using variable flip angle (VFA) T1 mapping and intravoxel incoherent motion-diffusion weighted imaging (IVIM-DWI). METHODS: This prospective study included 37 discharged COVID-19 participants and 24 age-matched non-COVID-19 volunteers who underwent abdominal MRI with VFA T1 mapping and IVIM-DWI sequencing as a COVID-19 group and control group, respectively. Among those discharged COVID-19 participants, 23 patients underwent two follow-up MRI scans, and were enrolled as the 3-month follow-up group and 1-year follow-up group, respectively. The demographics, clinical characteristics, and laboratory tests were collected. Imaging parameters of the liver and kidneys were measured. All collected values were compared among different groups. RESULTS: The 3-month follow-up group had the lowest hepatic T1 value, which was significantly lower than the value in the control group (P < 0.001). Additionally, the 3-month follow-up group had the highest hepatic ADC and D values, cortical ADC and f values, which were significantly higher than those in the control group (for all, P < 0.05). The hepatic D value in the 1-year follow-up group decreased significantly in comparison with that in the 3-month follow-up group (P = 0.001). Compared to non-severe patients, severe cases had significantly higher hepatic D* and f*D* values (P = 0.031, P = 0.015, respectively). CONCLUSION: The dynamic alterations of hepatic and renal imaging parameters detected with T1 mapping and IVIM-DWI suggested that COVID-19 survivors might develop mild, non-symptomatic liver and kidney impairments, of which liver impairment could probably relieve over time and kidney impairment might be long-existing.

Longitudinal Radiological Findings in Patients With COVID-19 With Different Severities: From Onset to Long-Term Follow-Up After Discharge.

Objective: This study aimed to investigate the evolution of radiological findings in the patients with coronavirus disease 2019 (COVID-19) pneumonia with different severities from onset to 1-year follow-up and identify the predictive factors for different pulmonary lesion absorption status in the patients infected with COVID-19. Methods: A retrospective study was performed on the clinical and radiological features of 175 patients with COVID-19 pneumonia hospitalized at three institutions from January 21 to March 20, 2020. All the chest CT scans during hospitalization and follow-ups after discharge were collected. The clinical and radiological features from the chest CT scans both at the peak stage and before discharge from the hospital were used to predict whether the pulmonary lesions would be fully absorbed after discharge by Cox regression. Then, these patients were stratified into two groups with different risks of pulmonary lesion absorption, and an optimal timepoint for the first CT follow-up was selected accordingly. Results: A total of 132 (75.4%) patients were classified into the non-severe group, and 43 (24.6%) patients were classified into the severe group, according to the WHO guidelines. The opacification in both the groups changed from ground-glass opacity (GGO) to consolidation and then from consolidation to GGO. Among the 175 participants, 135 (112 non-severe and 23 severe patients with COVID-19) underwent follow-up CT scans after discharge. Pulmonary residuals could be observed in nearly half of the patients (67/135) with the presentation of opacities and parenchymal bands. The parenchymal bands in nine discharged patients got fully absorbed during the follow-up periods. The age of patient [hazard ratio (HR) = 0.95, 95% CI, 0.95-0.99], level of lactate dehydrogenase (LDH) (HR = 0.99; 95% CI, 0.99-1.00), level of procalcitonin (HR = 8.72; 95% CI, 1.04-73.03), existence of diffuse lesions (HR = 0.28; 95% CI, 0.09-0.92), subpleural distribution of lesions (HR = 2.15; 95% CI, 1.17-3.92), morphology of residuals (linear lesion: HR = 4.58, 95% CI, 1.22-17.11; nodular lesion: HR = 33.07, 95% CI, 3.58-305.74), and pleural traction (HR = 0.41; 95% CI, 0.22-0.78) from the last scan before discharge were independent factors to predict the absorption status of COVID-19-related pulmonary abnormalities after discharge. According to a Kaplan-Meier analysis, the probability of patients of the low-risk group to have pulmonary lesions fully absorbed within 90 days reached 91.7%. Conclusion: The development of COVID-19 lesions followed the trend from GGO to consolidation and then from consolidation to GGO. The CT manifestations and clinical and laboratory variables before discharge could help predict the absorption status of pulmonary lesions after discharge. The parenchymal bands could be fully absorbed in some COVID-19 cases. In this study, a Cox regression analysis indicated that a timepoint of 3 months since onset was optimal for the radiological follow-up of discharged patients.

Triage Modeling for Differential Diagnosis Between COVID-19 and Human Influenza A Pneumonia: Classification and Regression Tree Analysis.

Background: The coronavirus disease 2019 (COVID-19) pandemic has lasted much longer than an influenza season, but the main signs, symptoms, and some imaging findings are similar in COVID-19 and influenza patients. The aim of the current study was to construct an accurate and robust model for initial screening and differential diagnosis of COVID-19 and influenza A. Methods: All patients in the study were diagnosed at Fuyang No. 2 People's Hospital, and they included 151 with COVID-19 and 155 with influenza A. The patients were randomly assigned to training set or a testing set at a 4:1 ratio. Predictor variables were selected based on importance, assessed by random forest algorithms, and analyzed to develop classification and regression tree models. Results: In the optimal model A, the best single predictor of COVID-19 patients was a normal or high level of low-density lipoprotein cholesterol, followed by low level of creatine kinase, then the presence of <3 respiratory symptoms, then a highest temperature on the first day of admission <38°C. In the suboptimal model B, the best single predictor of COVID-19 was a low eosinophil count, then a normal monocyte ratio, then a normal hematocrit value, then a highest temperature on the first day of admission of <37°C, then a complete lack of respiratory symptoms. Conclusions: The two models provide clinicians with a rapid triage tool. The optimal model can be used to developed countries/regions and major hospitals, and the suboptimal model can be used in underdeveloped regions and small hospitals.

Cerebral Micro-Structural Changes in COVID-19 Patients - An MRI-based 3-month Follow-up Study.

BACKGROUND: Increasing evidence supported the possible neuro-invasion potential of SARS-CoV-2. However, no studies were conducted to explore the existence of the micro-structural changes in the central nervous system after infection. We aimed to identify the existence of potential brain micro-structural changes related to SARS-CoV-2. METHODS: In this prospective study, diffusion tensor imaging (DTI) and 3D high-resolution T1WI sequences were acquired in 60 recovered COVID-19 patients (56.67% male; age: 44.10 ± 16.00) and 39 age- and sex-matched non-COVID-19 controls (56.41% male; age: 45.88 ± 13.90). Registered fractional anisotropy (FA), mean diffusivity (MD), axial diffusivity (AD), and radial diffusivity (RD) were quantified for DTI, and an index score system was introduced. Regional volumes derived from Voxel-based Morphometry (VBM) and DTI metrics were compared using analysis of covariance (ANCOVA). Two sample t-test and Spearman correlation were conducted to assess the relationships among imaging indices, index scores and clinical information. FINDINGS: In this follow-up stage, neurological symptoms were presented in 55% COVID-19 patients. COVID-19 patients had statistically significantly higher bilateral gray matter volumes (GMV) in olfactory cortices, hippocampi, insulas, left Rolandic operculum, left Heschl's gyrus and right cingulate gyrus and a general decline of MD, AD, RD accompanied with an increase of FA in white matter, especially AD in the right CR, EC and SFF, and MD in SFF compared with non-COVID-19 volunteers (corrected p value <0.05). Global GMV, GMVs in left Rolandic operculum, right cingulate, bilateral hippocampi, left Heschl's gyrus, and Global MD of WM were found to correlate with memory loss (p value <0.05). GMVs in the right cingulate gyrus and left hippocampus were related to smell loss (p value <0.05). MD-GM score, global GMV, and GMV in right cingulate gyrus were correlated with LDH level (p value <0.05). INTERPRETATION: Study findings revealed possible disruption to micro-structural and functional brain integrity in the recovery stages of COVID-19, suggesting the long-term consequences of SARS-CoV-2. FUNDING: Shanghai Natural Science Foundation, Youth Program of National Natural Science Foundation of China, Shanghai Sailing Program, Shanghai Science and Technology Development, Shanghai Municipal Science and Technology Major Project and ZJ Lab.

The usage of deep neural network improves distinguishing COVID-19 from other suspected viral pneumonia by clinicians on chest CT: a real-world study.

OBJECTIVES: Based on the current clinical routine, we aimed to develop a novel deep learning model to distinguish coronavirus disease 2019 (COVID-19) pneumonia from other types of pneumonia and validate it with a real-world dataset (RWD). METHODS: A total of 563 chest CT scans of 380 patients (227/380 were diagnosed with COVID-19 pneumonia) from 5 hospitals were collected to train our deep learning (DL) model. Lung regions were extracted by U-net, then transformed and fed to pre-trained ResNet-50-based IDANNet (Identification and Analysis of New covid-19 Net) to produce a diagnostic probability. Fivefold cross-validation was employed to validate the application of our model. Another 318 scans of 316 patients (243/316 were diagnosed with COVID-19 pneumonia) from 2 other hospitals were enrolled prospectively as the RWDs to testify our DL model's performance and compared it with that from 3 experienced radiologists. RESULTS: A three-dimensional DL model was successfully established. The diagnostic threshold to differentiate COVID-19 and non-COVID-19 pneumonia was 0.685 with an AUC of 0.906 (95% CI: 0.886-0.913) in the internal validation group. In the RWD cohort, our model achieved an AUC of 0.868 (95% CI: 0.851-0.876) with the sensitivity of 0.811 and the specificity of 0.822, non-inferior to the performance of 3 experienced radiologists, suggesting promising clinical practical usage. CONCLUSIONS: The established DL model was able to achieve accurate identification of COVID-19 pneumonia from other suspected ones in the real-world situation, which could become a reliable tool in clinical routine. KEY POINTS: • In an internal validation set, our DL model achieved the best performance to differentiate COVID-19 from non-COVID-19 pneumonia with a sensitivity of 0.836, a specificity of 0.800, and an AUC of 0.906 (95% CI: 0.886-0.913) when the threshold was set at 0.685. • In the prospective RWD cohort, our DL diagnostic model achieved a sensitivity of 0.811, a specificity of 0.822, and AUC of 0.868 (95% CI: 0.851-0.876), non-inferior to the performance of 3 experienced radiologists. • The attention heatmaps were fully generated by the model without additional manual annotation and the attention regions were highly aligned with the ROIs acquired by human radiologists for diagnosis.

Development and Validation of a Prognostic Nomogram Based on Clinical and CT Features for Adverse Outcome Prediction in Patients with COVID-19.

OBJECTIVE: The purpose of our study was to investigate the predictive abilities of clinical and computed tomography (CT) features for outcome prediction in patients with coronavirus disease (COVID-19). MATERIALS AND METHODS: The clinical and CT data of 238 patients with laboratory-confirmed COVID-19 in our two hospitals were retrospectively analyzed. One hundred sixty-six patients (103 males; age 43.8 ± 12.3 years) were allocated in the training cohort and 72 patients (38 males; age 45.1 ± 15.8 years) from another independent hospital were assigned in the validation cohort. The primary composite endpoint was admission to an intensive care unit, use of mechanical ventilation, or death. Univariate and multivariate Cox proportional hazard analyses were performed to identify independent predictors. A nomogram was constructed based on the combination of clinical and CT features, and its prognostic performance was externally tested in the validation group. The predictive value of the combined model was compared with models built on the clinical and radiological attributes alone. RESULTS: Overall, 35 infected patients (21.1%) in the training cohort and 10 patients (13.9%) in the validation cohort experienced adverse outcomes. Underlying comorbidity (hazard ratio [HR], 3.35; 95% confidence interval [CI], 1.67-6.71; p < 0.001), lymphocyte count (HR, 0.12; 95% CI, 0.04-0.38; p < 0.001) and crazy-paving sign (HR, 2.15; 95% CI, 1.03-4.48; p = 0.042) were the independent factors. The nomogram displayed a concordance index (C-index) of 0.82 (95% CI, 0.76-0.88), and its prognostic value was confirmed in the validation cohort with a C-index of 0.89 (95% CI, 0.82-0.96). The combined model provided the best performance over the clinical or radiological model (p < 0.050). CONCLUSION: Underlying comorbidity, lymphocyte count and crazy-paving sign were independent predictors of adverse outcomes. The prognostic nomogram based on the combination of clinical and CT features could be a useful tool for predicting adverse outcomes of patients with COVID-19.