Interpretable machine-learning model for Predicting the Convalescent COVID-19 patients with pulmonary diffusing capacity impairment.

INTRODUCTION: The COVID-19 patients in the convalescent stage noticeably have pulmonary diffusing capacity impairment (PDCI). The pulmonary diffusing capacity is a frequently-used indicator of the COVID-19 survivors' prognosis of pulmonary function, but the current studies focusing on prediction of the pulmonary diffusing capacity of these people are limited. The aim of this study was to develop and validate a machine learning (ML) model for predicting PDCI in the COVID-19 patients using routinely available clinical data, thus assisting the clinical diagnosis. METHODS: Collected from a follow-up study from August to September 2021 of 221 hospitalized survivors of COVID-19 18 months after discharge from Wuhan, including the demographic characteristics and clinical examination, the data in this study were randomly separated into a training (80%) data set and a validation (20%) data set. Six popular machine learning models were developed to predict the pulmonary diffusing capacity of patients infected with COVID-19 in the recovery stage. The performance indicators of the model included area under the curve (AUC), Accuracy, Recall, Precision, Positive Predictive Value(PPV), Negative Predictive Value (NPV) and F1. The model with the optimum performance was defined as the optimal model, which was further employed in the interpretability analysis. The MAHAKIL method was utilized to balance the data and optimize the balance of sample distribution, while the RFECV method for feature selection was utilized to select combined features more favorable to machine learning. RESULTS: A total of 221 COVID-19 survivors were recruited in this study after discharge from hospitals in Wuhan. Of these participants, 117 (52.94%) were female, with a median age of 58.2 years (standard deviation (SD) = 12). After feature selection, 31 of the 37 clinical factors were finally selected for use in constructing the model. Among the six tested ML models, the best performance was accomplished in the XGBoost model, with an AUC of 0.755 and an accuracy of 78.01% after experimental verification. The SHAPELY Additive explanations (SHAP) summary analysis exhibited that hemoglobin (Hb), maximal voluntary ventilation (MVV), severity of illness, platelet (PLT), Uric Acid (UA) and blood urea nitrogen (BUN) were the top six most important factors affecting the XGBoost model decision-making. CONCLUSION: The XGBoost model reported here showed a good prognostic prediction ability for PDCI of COVID-19 survivors during the recovery period. Among the interpretation methods based on the importance of SHAP values, Hb and MVV contributed the most to the prediction of PDCI outcomes of COVID-19 survivors in the recovery period.

Seroprevalence of IgM and IgG Antibodies against SARS-CoV-2 in Asymptomatic People in Wuhan: Data from a General Hospital Near South China Seafood Wholesale Market during March to April in 2020.

The aim of this study was to estimate the seroprevalence of immunoglobulin M (IgM) and G (IgG) antibodies against SARS-CoV-2 in asymptomatic people in Wuhan. This was a cross-sectional study, which enrolled 18,712 asymptomatic participants from 154 work units in Wuhan. Pearson Chi-square test, t-test, and Mann-Whitney test were used to compare the standardized seroprevalence of IgG and IgM for age and gender between different groups. The results indicated the standardized seroprevalence of IgG and IgM showed a downward trend and was significantly higher among females than males. Besides, different geographic areas and workplaces had different seroprevalence of IgG among asymptomatic people, and the number of abnormalities in CT imaging were higher in IgG antibody-positive cases than IgG-negative cases. We hope these findings can provide references for herd immunity investigation and provide basis for vaccine development.

Early Use of Corticosteroid May Prolong SARS-CoV-2 Shedding in Non-Intensive Care Unit Patients with COVID-19 Pneumonia: A Multicenter, Single-Blind, Randomized Control Trial.

BACKGROUND: There is still no clinical evidence available to support or to oppose corticosteroid treatment for coronavirus disease 2019 (COVID-19) pneumonia. OBJECTIVE: To investigate the efficacy and safety of corticosteroid given to the hospitalized patients with COVID-19 pneumonia. METHODS: This was a prospective, multicenter, single-blind, randomized control trial. Adult patients with COVID-19 pneumonia who were admitted to the general ward were randomly assigned to either receive methylprednisolone or not for 7 days. The primary end point was the incidence of clinical deterioration 14 days after randomization. RESULTS: We terminated this trial early because the number of patients with COVID-19 pneumonia in all the centers decreased in late March. Finally, a total of 86 COVID-19 patients underwent randomization. There was no difference of the incidence of clinical deterioration between the methylprednisolone group and control group (4.8 vs. 4.8%, p = 1.000). The duration of throat viral RNA detectability in the methylprednisolone group was 11 days (interquartile range, 6-16 days), which was significantly longer than that in the control group (8 days [2-12 days], p = 0.030). There were no significant differences between the 2 groups in other secondary outcomes. Mass cytometry discovered CD3+ T cells, CD8+ T cells, and NK cells in the methylprednisolone group which were significantly lower than those in the control group after randomization (p < 0.05). CONCLUSIONS: From this prematurely closed trial, we found that the short-term early use of corticosteroid could suppress the immune cells, which may prolong severe acute respiratory syndrome coronavirus 2 shedding in patients with COVID-19 pneumonia. TRIAL REGISTRATION: ClinicalTrials.gov, NCT04273321.

Suppressed T cell-mediated immunity in patients with COVID-19: A clinical retrospective study in Wuhan, China.

IMPORTANCE: An ongoing outbreak of COVID-19 has exhibited significant threats around the world. We found a significant decrease of T lymphocyte subsets and an increase of inflammatory cytokines of hospitalized patients with COVID-19 in clinical practice. METHODS: We conducted a retrospective, single-center observational study of in-hospital adult patients with confirmed COVID-19 in Hubei Provincial Hospital of traditional Chinese and Western medicine (Wuhan, China) by Mar 1, 2020. Demographic, clinical, laboratory information, especially T lymphocyte subsets and inflammatory cytokines were reported. For patients who died or discharge from hospital, the associations of T lymphocyte subsets on admission were evaluated by univariate logistic regression with odds ratios (ORs) and 95% confidence intervals (CIs), warning values to predict in-hospital death were assessed by Receiver Operator Characteristic (ROC) curves. RESULTS: A total of 187 patients were enrolled in our study from Dec 26, 2019 to Mar 1, 2020, of whom 145 were survivors (discharge = 117) or non-survivors (in-hospital death ==28). All patients exhibited a significant drop of T lymphocyte subsets counts with remarkably increasing concentrations of SAA, CRP, IL-6, and IL-10 compared to normal values. The median concentrations of SAA and CRP in critically-ill patients were nearly 4- and 10-fold than those of mild-ill patients, respectively. As the severity of COVID-19 getting worse, the counts of T lymphocyte drop lower.28 patients died in hospital, the median lymphocyte, CD3+ T-cell, CD4+ T-cell, CD8+ T-cell and B-cell were significantly lower than other patients. Lower counts (/uL) of T lymphocyte subsets lymphocyte (<500), CD3+T-cell (<200), CD4+ T-cell (<100), CD8+ T-cell (<100) and B-cell (<50) were associated with higher risks of in-hospital death of CIVID-19. The warning values to predict in-hospital death of lymphocyte, CD3+ T-cell, CD4+ T-cell, CD8+ T-cell, and B-cell were 559, 235, 104, 85 and 82, respectively. CONCLUSION: We find a significant decrease of T lymphocyte subset is positively correlated with in-hospital death and severity of illness. The decreased levels of T lymphocyte subsets reported in our study were similar with SARS but not common among other virus infection, which may be possible biomarkers for early diagnosis of COVID-19. Our findings may shed light on early warning of high risks of mortality and help early intervention and treatment of COVID-19.

[The absorption spectrum of green-sensitive cyanine dyes J-aggregate adsorbed on silver chloride microcrystals].

The silver chloride microcrystals emulsion which are sensitized by the adsorbed green-sensitive cyanine dye of different concentration, was studied by using the absorption spectrum. The experiments show that when the sensitizing concentration is less than 0.02 mL (5.0 mg x mL(-1))/40 g emulsion, the dye J-aggregate is not formed on the surface of silver chloride microcrystals; when the dye concentration is more than 0.2 mL (5.0 mg x mL(-1)/40 g emulsion, the dye J-aggregate is formed on the surface of silver chloride microcrystals; compare to the M-state of dye, the maximal absorption peak of J-aggregate shifted to a longer wavelength by about 50 nm. It was found, when the J-aggregate is formed, the absorption in the wavelength range of more than 450 nm is increased.