medRxiv preprint 6 datasets. The predictive performance was further evaluated in test dataset on lung lobe-and patients-level. Main outcomesShort-term hospital stay (≤10 days) and long-term hospital stay (>10 days). ResultsThe CT radiomics models based on 6 second-order features were effective in discriminating short-and long-term hospital stay in patients with pneumonia associated with SARS-CoV-2 infection, with areas under the curves of 0.97 (95%CI 0.83-1.0) and 0.92 (95%CI 0.67-1.0) by LR and RF, respectively, in the test dataset. The LR model showed a sensitivity and specificity of 1.0 and 0.89, and the RF model showed similar performance with sensitivity and specificity of 0.75 and 1.0 in test dataset. ConclusionsThe machine learning-based CT radiomics models showed feasibility and accuracy for predicting hospital stay in patients with pneumonia associated with SARS-CoV-2 infection.All rights reserved. No reuse allowed without permission.author/funder, who has granted medRxiv a license to display the preprint in perpetuity. Results Patient characteristicsA total of 52 patients with laboratory-confirmed SARS-CoV-2 infection and initial CT images were enrolled from 5 designated hospitals in Ankang, Lishui, Zhenjiang, Lanzhou, and Linxia, China. As of February 20, 14 patients were still hospitalized, and 7 patients had non-findings in CT images. Therefore, 31 patients with 72 lesion segments were included in the final analysis. The training and inter-validation cohort comprised 26 patients (12 from Ankang, 8 from Lishui, 4 from Lanzhou, and 2 from Linxia) with 59 lesion segments, and test cohort comprised 5 patients from Zhenjiang with 13 lesion segments. The median age was 38.00 (interquartile range, 26.00-47.00) years and 17 (57%) were male. Comorbidities, symptoms and laboratory findings at admission were summarized in Table 1. Performance of CT radiomics modelThe CT radiomics model, based on 6 features (supplementary Table1), showed the highest AUC on the training and inter-validation dataset. The performance of modeling using LR and RF methods was shown in Figure 2. On lung lobe-level, models using LR method significantly distinguished short-and long-term hospital stay (In training and inter-validation datasets, cut-off value 0.31, AUC 0.94 (95%CI 0.92-0.97), sensitivity 1.0, specificity 0.87, NPV 1.0, and PPV 0.88; In test dataset, AUC 0.97 (95%CI 0.83-1.0), sensitivity 1.0, specificity 0.89, NPV 1.0, and PPV 0.8). Besides, models using RF method obtained satisfied results (In training and inter-validation datasets, cut-off value 0.68, AUC 1.0 (95%CI 1.0-1.0), All rights reserved. No reuse allowed without permission.author/funder, who has granted medRxiv a license to display the preprint in perpetuity.

consultation; and (iii) establish a short-term web-based followup to define drug efficacy and adapt treatment accordingly. Thus, in this particular situation the diagnosis of AIH may be given without histology, if typical biochemical and serological results are followed by a convincing treatment response. Prove of the diagnosis can be undertaken later, either by a relapse upon therapy reduction, or a follow-up liver biopsy when conditions are safer. As already reported in China, 8 advanced liver cirrhosis and decompensated patients can be monitored with a webbased system and all non-urgent medical visits should be postponed until the emergency is over. Urgent procedures (i.e. paracentesis) should be organised using a COVID-19-free path in the hospital, another COVID-19-free facility or home care. Finally, we recommend strict adherence to standard social distancing protocols and social isolation and emphasise, in cirrhotic patients, the importance of vaccination for Streptococcus pneumoniae and seasonal flu and of reinforcing social distancing measures. Further data are needed in order to demonstrate the real impact of COVID-19 infection in immunocompromised patients. Until then, and while vaccination is not available, we suggest continuing a cautious approach during low-level seasonal persistence of COVID-19 in the years to come.Although we cannot currently evaluate the efficacy of our management protocol, we believe this framework might be a useful tool for management of AILD for the time being.

Background: The coronavirus disease 2019 (COVID-19) has become a global challenge since the December 2019. The hospital stay is one of the prognostic indicators, and its predicting model based on CT radiomics features is important for assessing the patients' clinical outcome. The study aimed to develop and test machine learning-based CT radiomics models for predicting hospital stay in patients with COVID-19 pneumonia.Methods: This retrospective, multicenter study enrolled patients with laboratory-confirmed SARS-CoV-2 infection and their initial CT images from 5 designated hospitals in Ankang,

No abstract

Background and Aims: Patients with critical coronavirus disease 2019 (COVID-19) have a mortality rate higher than 50%. The purpose of this study was to establish a model for the prediction of the risk of severe disease and/or death in patients with COVID-19 on admission.Materials and Methods: Patients diagnosed with COVID-19 in four hospitals in China from January 22, 2020 to April 15, 2020 were retrospectively enrolled. The demographic, laboratory, and clinical data of the patients with COVID-19 were collected. The independent risk factors related to the severity of and death due to COVID-19 were identified with a multivariate logistic regression; a nomogram and prediction model were established. The area under the receiver operating characteristic curve (AUROC) and predictive accuracy were used to evaluate the model's effectiveness.Results: In total, 582 patients with COVID-19, including 116 patients with severe disease, were enrolled. Their comorbidities, body temperature, neutrophil-to-lymphocyte ratio (NLR), platelet (PLT) count, and levels of total bilirubin (Tbil), creatinine (Cr), creatine kinase (CK), and albumin (Alb) were independent risk factors for severe disease. A nomogram was generated based on these eight variables with a predictive accuracy of 85.9% and an AUROC of 0.858 (95% CI, 0.823–0.893). Based on the nomogram, the CANPT score was established with cut-off values of 12 and 16. The percentages of patients with severe disease in the groups with CANPT scores <12, ≥12, and <16, and ≥16 were 4.15, 27.43, and 69.64%, respectively. Seventeen patients died. NLR, Cr, CK, and Alb were independent risk factors for mortality, and the CAN score was established to predict mortality. With a cut-off value of 15, the predictive accuracy was 97.4%, and the AUROC was 0.903 (95% CI 0.832, 0.974).Conclusions: The CANPT and CAN scores can predict the risk of severe disease and mortality in COVID-19 patients on admission.