Statistical Analysis and Machine Learning Prediction of Disease Outcomes for COVID-19 and Pneumonia Patients.

The Coronavirus Disease 2019 (COVID-19) has spread all over the world and impacted many people's lives. The characteristics of COVID-19 and other types of pneumonia have both similarities and differences, which confused doctors initially to separate and understand them. Here we presented a retrospective analysis for both COVID-19 and other types of pneumonia by combining the COVID-19 clinical data, eICU and MIMIC-III databases. Machine learning models, including logistic regression, random forest, XGBoost and deep learning neural networks, were developed to predict the severity of COVID-19 infections as well as the mortality of pneumonia patients in intensive care units (ICU). Statistical analysis and feature interpretation, including the analysis of two-level attention mechanisms on both temporal and non-temporal features, were utilized to understand the associations between different clinical variables and disease outcomes. For the COVID-19 data, the XGBoost model obtained the best performance on the test set (AUROC = 1.000 and AUPRC = 0.833). On the MIMIC-III and eICU pneumonia datasets, our deep learning model (Bi-LSTM_Attn) was able to identify clinical variables associated with death of pneumonia patients (AUROC = 0.924 and AUPRC = 0.802 for 24-hour observation window and 12-hour prediction window). The results highlighted clinical indicators, such as the lymphocyte counts, that may help the doctors to predict the disease progression and outcomes for both COVID-19 and other types of pneumonia.

Performance of CURB-65, PSI, and APACHE-II for predicting COVID-19 pneumonia severity and mortality

No prognostic tools for the prediction of COVID-19 pneumonia severity and mortality are available. We explored whether CURB-65, PSI, and APACHE-II could predict COVID-19 pneumonia severity and mortality. We included 167 patients with confirmed COVID-19 pneumonia in this retrospective study. The severity and 30-day mortality of COVID-19 pneumonia were predicted using PSI, CURB-65, and APACHE-II scales. Kappa test was performed to compare the consistency of the three scales. There was a significant difference in the distribution of the scores of the three scales (P < 0.001). Patients with PSI class ⩽III, CURB-65 ⩽1, and APACHE-II-I all survived. The ROC analysis showed the areas under the curve of the PSI, CURB-65, and APACHE-II scales were 0.83 (95% CI, 0.74–0.93), 0.80 (95% CI, 0.69–0.90), and 0.83 (95% CI, 0.75–0.92), respectively. Our findings suggest that PSI and CURB-65 might be useful to predict the severity and mortality of COVID-19 pneumonia. [ABSTRACT FROM AUTHOR] Copyright of European Journal of Inflammation (Sage Publications, Ltd.) is the property of Sage Publications, Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

SARS-CoV-2 infection induces sustained humoral immune responses in convalescent patients following symptomatic COVID-19.

Long-term antibody responses and neutralizing activities in response to SARS-CoV-2 infection are not yet clear. Here we quantify immunoglobulin M (IgM) and G (IgG) antibodies recognizing the SARS-CoV-2 receptor-binding domain (RBD) of the spike (S) or the nucleocapsid (N) protein, and neutralizing antibodies during a period of 6 months from COVID-19 disease onset in 349 symptomatic COVID-19 patients who were among the first be infected world-wide. The positivity rate and magnitude of IgM-S and IgG-N responses increase rapidly. High levels of IgM-S/N and IgG-S/N at 2-3 weeks after disease onset are associated with virus control and IgG-S titers correlate closely with the capacity to neutralize SARS-CoV-2. Although specific IgM-S/N become undetectable 12 weeks after disease onset in most patients, IgG-S/N titers have an intermediate contraction phase, but stabilize at relatively high levels over the 6 month observation period. At late time points, the positivity rates for binding and neutralizing SARS-CoV-2-specific antibodies are still >70%. These data indicate sustained humoral immunity in recovered patients who had symptomatic COVID-19, suggesting prolonged immunity.

Changes of hematological and immunological parameters in COVID-19 patients.

The aim of this study was to identify the changes of hematologic and immunological parameters in COVID-19 patients. We collected and analyzed the data of 117 patients who were laboratory confirmed as SARS-CoV-2 infection. The cases were divided into regular group, severe group and critically ill group according to the sixth edition scheme for COVID-19 diagnosis and treatment of China. The laboratory tests included blood routine, cellular and humoral immunity indices, biochemical detections and inflammatory biomarker. Compared with regular patients, severe and critically ill patients had significantly lower lymphocyte count (p < 0.01), decreased red blood cell and hemoglobin (p < 0.01), low levels of immunoglobulin G (p < 0.05) and significantly higher in D-dimer (p < 0.0001), fibrinogen (p < 0.01), white blood cell count (p < 0.01), neutrophil count (p < 0.0001), interleukin-6 (p < 0.05), C-reactive protein (p < 0.01), procalcitonin (p < 0.01), erythrocyte sedimentation rate (p < 0.05), ferritin (p < 0.01) and lactate dehydrogenase (p < 0.0001). The specific immunoglobulin G antibodies to the SARS-CoV-2 in severe and critically ill patients were significantly lower than that in regular patients (p < 0.05). Our findings suggest that the lymphocyte counts, red blood cell counts and the immunoglobulin G antibodies of COVID-19 patients were impaired to varying degrees and the blood was in a state of hypercoagulation, which were more obvious in critically ill patients.