Construction and validation of a deterioration model for elderly COVID-19 Sub-variant BA.2 patients

Rationale COVID-19 pandemic has imposed tremendous stress and burden on the economy and society worldwide. There is an urgent demand to find a new model to estimate the deterioration of patients inflicted by Omicron variants. Objective This study aims to develop a model to predict the deterioration of elderly patients inflicted by Omicron Sub-variant BA.2. Methods COVID-19 patients were randomly divided into the training and the validation cohorts. Both Lasso and Logistic regression analyses were performed to identify prediction factors, which were then selected to build a deterioration model in the training cohort. This model was validated in the validation cohort. Measurements and main results The deterioration model of COVID-19 was constructed with five indices, including C-reactive protein, neutrophil count/lymphocyte count (NLR), albumin/globulin ratio (A/G), international normalized ratio (INR), and blood urea nitrogen (BUN). The area under the ROC curve (AUC) showed that this model displayed a high accuracy in predicting deterioration, which was 0.85 in the training cohort and 0.85 in the validation cohort. The nomogram provided an easy way to calculate the possibility of deterioration, and the decision curve analysis (DCA) and clinical impact curve analysis (CICA)showed good clinical net profit using this model. Conclusion The model we constructed can identify and predict the risk of deterioration (requirement for ventilatory support or death) in elderly patients and it is clinically practical, which will facilitate medical decision making and allocating medical resources to those with critical conditions.

C-reactive protein to lymphocyte ratio is a significant predictive factor for poor short-term clinical outcomes of SARS-CoV-2 BA.2.2 patients.

Objective: The aim of the present study is to assess the utility of C-reactive protein to Lymphocyte Ratio (CLR) in predicting short-term clinical outcomes of patients infected by SARS-CoV-2 BA.2.2. Methods: This retrospective study was performed on 1,219 patients with laboratory-confirmed SARS-CoV-2 BA.2.2 to determine the association of CLR with short-term clinical outcomes. Independent Chi square test, Rank sum test, and binary logistic regression analysis were performed to calculate mean differences and adjusted odds ratios (aORs) with their 95% CI, respectively. Results: Over 8% of patients admitted due to SARS-CoV-2 BA.2.2. were critically ill. The best cut-off value of CLR was 21.25 in the ROC with a sensitivity of 72.3% and a specificity of 86%. After adjusting age, gender, and comorbidities, binary logistic regression analysis showed that elevated CLR was an independent risk factor for poor short-term clinical outcomes of COVID-19 patients. Conclusion: C-reactive protein to Lymphocyte Ratio is a significant predictive factor for poor short-term clinical outcomes of SARS-CoV-2 BA.2.2 inflicted patients.

PAM-DenseNet: A Deep Convolutional Neural Network for Computer-Aided COVID-19 Diagnosis.

Currently, several convolutional neural network (CNN)-based methods have been proposed for computer-aided COVID-19 diagnosis based on lung computed tomography (CT) scans. However, the lesions of pneumonia in CT scans have wide variations in appearances, sizes, and locations in the lung regions, and the manifestations of COVID-19 in CT scans are also similar to other types of viral pneumonia, which hinders the further improvement of CNN-based methods. Delineating infection regions manually is a solution to this issue, while excessive workload of physicians during the epidemic makes it difficult for manual delineation. In this article, we propose a CNN called dense connectivity network with parallel attention module (PAM-DenseNet), which can perform well on coarse labels without manually delineated infection regions. The parallel attention module automatically learns to strengthen informative features from both channelwise and spatialwise simultaneously, which can make the network pay more attention to the infection regions without any manual delineation. The dense connectivity structure performs feature maps reuse by introducing direct connections from previous layers to all subsequent layers, which can extract representative features from fewer CT slices. The proposed network is first trained on 3530 lung CT slices selected from 382 COVID-19 lung CT scans, 372 lung CT scans infected by other pneumonia, and 200 normal lung CT scans to obtain a pretrained model for slicewise prediction. We then apply this pretrained model to a CT scans dataset containing 94 COVID-19 CT scans, 93 other pneumonia CT scans, and 93 normal lung scans, and achieve patientwise prediction through a voting mechanism. The experimental results show that the proposed network achieves promising results with an accuracy of 94.29%, a precision of 93.75%, a sensitivity of 95.74%, and a specificity of 96.77%, which is comparable to the methods that are based on manually delineated infection regions.

Prediction of Disease Progression of COVID-19 Based upon Machine Learning.

BACKGROUND: Since December 2019, COVID-19 has spread throughout the world. Clinical outcomes of COVID-19 patients vary among infected individuals. Therefore, it is vital to identify patients at high risk of disease progression. METHODS: In this retrospective, multicenter cohort study, COVID-19 patients from Huoshenshan Hospital and Taikang Tongji Hospital (Wuhan, China) were included. Clinical features showing significant differences between the severe and nonsevere groups were screened out by univariate analysis. Then, these features were used to generate classifier models to predict whether a COVID-19 case would be severe or nonsevere based on machine learning. Two test sets of data from the two hospitals were gathered to evaluate the predictive performance of the models. RESULTS: A total of 455 patients were included, and 21 features showing significant differences between the severe and nonsevere groups were selected for the training and validation set. The optimal subset, with eleven features in the k-nearest neighbor model, obtained the highest area under the curve (AUC) value among the four models in the validation set. D-dimer, CRP, and age were the three most important features in the optimal-feature subsets. The highest AUC value was obtained using a support vector-machine model for a test set from Huoshenshan Hospital. Software for predicting disease progression based on machine learning was developed. CONCLUSION: The predictive models were successfully established based on machine learning, and achieved satisfactory predictive performance of disease progression with optimal-feature subsets.