Severity Assessment of COVID-19 based on Clinical and Imaging Data

ObjectivesThis study aims to develop a machine learning approach for automated severity assessment of COVID-19 patients based on clinical and imaging data. Materials and MethodsClinical data--demographics, signs, symptoms, comorbidities and blood test results--and chest CT scans of 346 patients from two hospitals in the Hubei province, China, were used to develop machine learning models for automated severity assessment of diagnosed COVID-19 cases. We compared the predictive power of clinical and imaging data by testing multiple machine learning models, and further explored the use of four oversampling methods to address the imbalance distribution issue. Features with the highest predictive power were identified using the SHAP framework. ResultsTargeting differentiation between mild and severe cases, logistic regression models achieved the best performance on clinical features (AUC:0.848, sensitivity:0.455, specificity:0.906), imaging features (AUC:0.926, sensitivity:0.818, specificity:0.901) and the combined features (AUC:0.950, sensitivity:0.764, specificity:0.919). The SMOTE oversampling method further improved the performance of the combined features to AUC of 0.960 (sensitivity:0.845, specificity:0.929). DiscussionImaging features had the strongest impact on the model output, while a combination of clinical and imaging features yielded the best performance overall. The identified predictive features were consistent with findings from previous studies. Oversampling yielded mixed results, although it achieved the best performance in our study. ConclusionsThis study indicates that clinical and imaging features can be used for automated severity assessment of COVID-19 patients and have the potential to assist with triaging COVID-19 patients and prioritizing care for patients at higher risk of severe cases.

Severity Assessment and Progression Prediction of COVID-19 Patients based on the LesionEncoder Framework and Chest CT

Automatic severity assessment and progression prediction can facilitate admission, triage, and referral of COVID-19 patients. This study aims to explore the potential use of lung lesion features in the management of COVID-19, based on the assumption that lesion features may carry important diagnostic and prognostic information for quantifying infection severity and forecasting disease progression. A novel LesionEncoder framework is proposed to detect lesions in chest CT scans and to encode lesion features for automatic severity assessment and progression prediction. The LesionEncoder framework consists of a U-Net module for detecting lesions and extracting features from individual CT slices, and a recurrent neural network (RNN) module for learning the relationship between feature vectors and collectively classifying the sequence of feature vectors. Chest CT scans of two cohorts of COVID-19 patients from two hospitals in China were used for training and testing the proposed framework. When applied to assessing severity, this framework outperformed baseline methods achieving a sensitivity of 0.818, specificity of 0.952, accuracy of 0.940, and AUC of 0.903. It also outperformed the other tested methods in disease progression prediction with a sensitivity of 0.667, specificity of 0.838, accuracy of 0.829, and AUC of 0.736. The LesionEncoder framework demonstrates a strong potential for clinical application in current COVID-19 management, particularly in automatic severity assessment of COVID-19 patients. This framework also has a potential for other lesion-focused medical image analyses.

Assessing kidney injury of hyperuricemia patients with MR diffusion tensor imaging / 中国医学影像技术

Objective: To investigate the feasibility of MR diffusion tensor imaging (DTI) in evaluating early renal function injury of hyperuricemia. Methods: Totally 23 male patients with asymptomatic hyperuricemia (AH group), 30 patients with gouty arthritis (GA group) and 23 healthy volunteers (HC group) were collected. Serum uric acid (SUA) and estimated glomerular filtration rate (eGFR) were recorded, and then routine MRI and DTI were performed. The differences of apparent diffusion coefficient (ADC) and fractional anisotropy (FA) values of renal cortex or medulla, SUA and eGFR of 3 groups were compared. The correlations of ADC and FA values of renal cortex or medulla with SUA and eGFR were analyzed, and the correlation of SUA and eGFR was analyzed. Results: SUA of HC group was lower than that of AH and GA group (both P<0.05), while eGFR of GA group was lower than that of HC group (P<0.05). FA values of renal cortex and medulla in AH group and GA group were lower than that of HC group (all P<0.05). The cortical ADC values in AH group and GA group and medullary ADC value in GA group were lower than that in HC group (all P<0.05). FA values of renal cortex and medulla (r=-0.41, -0.40), ADC values of renal cortex and medulla (r=-0.34, -0.28,) showed negative correlations with SUA (all P<0.05) but not with eGFR. Also, negative correlation of eGFR and SUA was found (r=-0.43, P<0.05). Conclusion: DTI can be used to evaluate early renal function injury caused by hyperuricemia. ADC and FA value of renal cortex and medulla of hyperuricemia patients are lower than that of normal people. ADC value and FA value of renal cortex or medulla are negatively correlated with SUA, while SUA is positively correlated with the degree of renal impairment.