Machine Learning-Based Scoring System for Early Prognosis Evaluation of Patients with Coronavirus Disease 2019

Background The global spread of coronavirus disease 2019 (COVID-19) continues to threaten human health security, exerting considerable pressure on healthcare systems worldwide. While prognostic models for COVID-19 hospitalized or intensive care patients are currently available, prognostic models developed for large cohorts of thousands of individuals are still lacking. Methods Between February 4 and April 16, 2020, we enrolled 3,974 patients admitted with COVID-19 disease in the Wuhan Huo-Shen-Shan Hospital and the Maternal and Child Hospital, Hubei Province, China. (1) Screening of key prognostic factors: A univariate Cox regression analysis was performed on 2,649 patients in the training set, and factors affecting prognosis were initially screened. Subsequently, a random survival forest model was established through machine analysis to further screen for factors that are important for prognosis. Finally, multivariate Cox regression analysis was used to determine the synergy among various factors related to prognosis. (2) Establishment of a scoring system: The nomogram algorithm established a COVID-19 patient death risk assessment scoring system for the nine selected key prognostic factors, calculated the C index, drew calibration curves and drew training set patient survival curves. (3) Verification of the scoring system: The scoring system assessed 1,325 patients in the test set, splitting them into high- and low-risk groups, calculated the C-index, and drew calibration and survival curves. Results The cross-sectional study found that age, clinical classification, sex, pulmonary insufficiency, hypoproteinemia, and four other factors (underlying diseases: blood diseases, malignant tumor;complications: digestive tract bleeding, heart dysfunction) have important significance for the prognosis of the enrolled patients with COVID-19. Herein, we report the discovery of the effects of hypoproteinemia and hematological diseases on the prognosis of COVID-19. Meanwhile, the scoring system established here can effectively evaluate objective scores for the early prognoses of patients with COVID-19 and can divide them into high- and low-risk groups (using a scoring threshold of 117.77, a score below which is considered low risk). The efficacy of the system was better than that of clinical classification using the current COVID-19 guidelines (C indexes, 0.95 vs. 0.89). Conclusions Age, clinical typing, sex, pulmonary insufficiency, hypoproteinemia, and four other factors were important for COVID-19 survival. Compared with general statistical methods, this method can quickly and accurately screen out the relevant factors affecting prognosis, provide an order of importance, and establish a scoring system based on the nomogram model, which is of great clinical significance.

[Exploration and example interpretation of real-world herbal prescription classification based on similarity matching algorithm].

In observational studies, herbal prescriptions are usually studied in the form of "similar prescriptions". At present, the classification of prescriptions is mainly based on clinical experience judgment, but there are some problems in manual judgment, such as lack of unified criteria, labor consumption, and difficulty in verification. In the construction of a database of integrated traditional Chinese and western medicine for the treatment of coronavirus disease 2019(COVID-19), our research group tried to classify real-world herbal prescriptions using a similarity matching algorithm. The main steps include 78 target prescriptions are determined in advance; four levels of importance labeling shall be carried out for the drugs of each target prescription; the combination, format conversion, and standardization of drug names of the prescriptions to be identified in the herbal medicine database; calculate the similarity between the prescriptions to be identified and each target prescription one by one; prescription discrimination is performed based on the preset criteria; remove the name of the prescriptions with "large prescriptions cover the small". Through the similarity matching algorithm, 87.49% of the real prescriptions in the herbal medicine database of this study can be identified, which preliminarily proves that this method can complete the classification of herbal prescriptions. However, this method does not consider the influence of herbal dosage on the results, and there is no recognized standard for the weight of drug importance and criteria, so there are some limitations, which need to be further explored and improved in future research.

Clinical Applicable AI System Based on Deep Learning Algorithm for Differentiation of Pulmonary Infectious Disease.

Objective: To assess the performance of a novel deep learning (DL)-based artificial intelligence (AI) system in classifying computed tomography (CT) scans of pneumonia patients into different groups, as well as to present an effective clinically relevant machine learning (ML) system based on medical image identification and clinical feature interpretation to assist radiologists in triage and diagnosis. Methods: The 3,463 CT images of pneumonia used in this multi-center retrospective study were divided into four categories: bacterial pneumonia (n = 507), fungal pneumonia (n = 126), common viral pneumonia (n = 777), and COVID-19 (n = 2,053). We used DL methods based on images to distinguish pulmonary infections. A machine learning (ML) model for risk interpretation was developed using key imaging (learned from the DL methods) and clinical features. The algorithms were evaluated using the areas under the receiver operating characteristic curves (AUCs). Results: The median AUC of DL models for differentiating pulmonary infection was 99.5% (COVID-19), 98.6% (viral pneumonia), 98.4% (bacterial pneumonia), 99.1% (fungal pneumonia), respectively. By combining chest CT results and clinical symptoms, the ML model performed well, with an AUC of 99.7% for SARS-CoV-2, 99.4% for common virus, 98.9% for bacteria, and 99.6% for fungus. Regarding clinical features interpreting, the model revealed distinctive CT characteristics associated with specific pneumonia: in COVID-19, ground-glass opacity (GGO) [92.5%; odds ratio (OR), 1.76; 95% confidence interval (CI): 1.71-1.86]; larger lesions in the right upper lung (75.0%; OR, 1.12; 95% CI: 1.03-1.25) with viral pneumonia; older age (57.0 years ± 14.2, OR, 1.84; 95% CI: 1.73-1.99) with bacterial pneumonia; and consolidation (95.8%, OR, 1.29; 95% CI: 1.05-1.40) with fungal pneumonia. Conclusion: For classifying common types of pneumonia and assessing the influential factors for triage, our AI system has shown promising results. Our ultimate goal is to assist clinicians in making quick and accurate diagnoses, resulting in the potential for early therapeutic intervention.

Effective inhibition of coronavirus replication by Polygonum cuspidatum.

Background: The coronavirus disease 2019 pandemic, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has infected more than 210 million individuals globally and resulted in over 4 million deaths since the first report in December 2019. The early use of traditional Chinese medicine (TCM) for light and ordinary patients, can rapidly improve symptoms, shorten hospitalization days and reduce severe cases transformed from light and normal. Many TCM formulas and products have a wide application in treating infectious and non-infectious diseases. Polygonum cuspidatum Sieb. et Zucc. (P. cuspidatum), is an important Traditional Chinese Medicine with actions of clearing away heat and eliminating dampness, draining the gallbladder to relieve jaundice, removing blood stasis to alleviate pain, resolving phlegm and arrest cough. In the search for anti-SARS-CoV-2, P. cuspidatum was recommended as as a therapeutic drug of COVID-19 pneumonia.In this study, we aimed to identifies P. cuspidatum is the potential broad-spectrum inhibitor for the treatment of coronaviruses infections. Methods: In the present study , we infected human malignant embryonal rhabdomyoma (RD) cells with the OC43 strain of the coronavirus, which represent an alternative model for SARS-CoV-2 and then employed the cell viability assay kit for the antiviral activity. We combined computer aided virtual screening to predicte the binding site and employed Surface plasmon resonance analysis (SPR) to comfirm the interaction between drugs and coronavirus. We employed fluorescence resonance energy transfer technology to identify drug's inhibition in the proteolytic activity of 3CLpro and Plpro. Results: Based on our results, polydatin and resveratrol derived from P. cuspidatum significantly suppressed HCoV-OC43 replication. 50% inhibitory concentration (IC50) values of polydatin inhibited SARS-CoV-2 Mpro and Plpro, MERS Mpro and Plpro were 18.66, 125, 14.6 and 25.42 µm, respectively. IC50 values of resveratrol inhibited SARS-CoV-2 Mpro and Plpro, MERS Mpro and Plpro were 29.81 ,60.86, 16.35 and19.04 µM, respectively. Finally, SPR assay confirmed that polydatin and resveratrol had high affinity to SARS-CoV-2, SARS-CoV 3Clpro, MERS-CoV 3Clpro and PLpro protein. Conclusions: we identified the antiviral activity of flavonoids polydatin and resveratrol on RD cells. Polydatin and resveratrol were found to be specific and selective inhibitors for SARS-CoV-2, 3CLpro and PLpro, viral cysteine proteases. In summary, this study identifies P. cuspidatum as the potential broad-spectrum inhibitor for the treatment of coronaviruses infections.

[Bioinformatics Analysis of the Influence of Coronavirus Infection on Hematopoietic System and Potential Intervention Drugs and Their Significance for COVID-19].

OBJECTIVE: To analyze and predict the effect of coronavirus infection on hematopoietic system and potential intervention drugs, and explore their significance for coronavirus disease 2019 (COVID-19). METHODS: The gene expression omnibus (GEO) database was used to screen the whole genome expression data related with coronavirus infection. The R language package was used for differential expression analysis and KEGG/GO enrichment analysis. The core genes were screened by PPI network analysis using STRING online analysis website. Then the self-developed apparent precision therapy prediction platform (EpiMed) was used to analyze diseases, drugs and related target genes. RESULTS: A database in accordance with the criteria was found, which was derived from SARS coronavirus. A total of 3606 differential genes were screened, including 2148 expression up-regulated genes and 1458 expression down-regulated genes. GO enrichment mainly related with viral infection, hematopoietic regulation, cell chemotaxis, platelet granule content secretion, immune activation, acute inflammation, etc. KEGG enrichment mainly related with hematopoietic function, coagulation cascade reaction, acute inflammation, immune reaction, etc. Ten core genes such as PTPRC, ICAM1, TIMP1, CXCR5, IL-1B, MYC, CR2, FSTL1, SOX1 and COL3A1 were screened by protein interaction network analysis. Ten drugs with potential intervention effects, including glucocorticoid, TNF-α inhibitor, salvia miltiorrhiza, sirolimus, licorice, red peony, famciclovir, cyclosporine A, houttuynia cordata, fluvastatin, etc. were screened by EpiMed plotform. CONCLUSION: SARS coronavirus infection can affect the hematopoietic system by changing the expression of a series of genes. The potential intervention drugs screened on these grounds are of useful reference significance for the basic and clinical research of COVID-19.

What we know about SARS-CoV-2: recent research progress

SARS-CoV-2 is a novel member of the coronavirus family. The virus has caused disease in more than 18 million people worldwide, including respiratory, circulatory, reproductive, digestive and urinary symptoms. However, the first infected case was identified as unexplained pneumonia. SARS-CoV-2 has stronger infection and transmission ability than SARS-CoV, which caused a pneumonia epidemic in 2003. Many researchers have carried out extensive studies on SARS-CoV-2. They have focused on further elucidating the microbiological characteristics of this virus and have made gradual progress in developing vaccines, therapeutic antibodies and antiviral drugs. Our country has made remarkable achievements in vaccine research. In this review, we focus on recent research progress on the biological characteristics, origin, infection and host immune response, transmission and treatment of SARS-CoV-2.

Targeting Proteases for Treating COVID-19.

The unprecedented pandemic of coronavirus disease 2019 (COVID-19) demands effective treatment for severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection. The infection of SARS-CoV-2 critically depends on diverse viral or host proteases, which mediate viral entry, viral protein maturation, as well as the pathogenesis of the viral infection. Endogenous and exogenous agents targeting for proteases have been proved to be effective toward a variety of viral infections ranging from HIV to influenza virus, suggesting protease inhibitors as a promising antiviral treatment for COVID-19. In this Review, we discuss how host and viral proteases participated in the pathogenesis of COVID-19 as well as the prospects and ongoing clinical trials of protease inhibitors as treatments.

Bioinformatics analysis of hematopoietic injury and potential therapeutic drugs associated with SARS-CoV-2 infection

Objective To analyze and predict hematopoietic injury caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) infection and potential therapeutic drugs, and to provide theoretical basis for clinical treatment of the hematopoietic injury. Methods The gene expression omnibus (GEO) database was used to screen the whole genome expression data related to SARS-CoV-2 infection. The R language package was used for differential expression analysis and the Kyoto Encyclopedia of Genes and Genomes (KEGG) and Gene Ontology (GO) enrichment analysis. The core genes were screened by protein-protein interaction (PPI) network analysis using STRING online analysis website. Then the self-developed apparent precision therapy prediction platform (EpiMed) was used to analyze diseases, drugs and related target genes. Results A total of 222 differential genes were screened, including 172 up-regulated and 50 down-regulated. GO enrichment analysis suggested that gene is mainly related to type I interferon response, cell cycle regulation, inflammatory cell migration, innate immune response, secretion of blood particles and vesicles, chemokines and their receptors. KEGG enrichment analysis suggested that gene is mainly related to viral infection, myocardial injury, complement and coagulation cascade, cell chemotaxis, platelet activation, acute inflammation, immune response, cellular signal transduction and so on. Ten core genes such as STAT1, IL-6, IRF7, TNF, MX1, ISG15, IFIH1, IRF9, DDX58 and GBP1were screened by PPI network analysis. EpiMed screened 10 drugs with potential intervention effects, including Rabdosia rubescens, sirolimus, glucocorticoid, Houttuynia cordata, Polygonum multiflorum, Red peony, tretinoin, Glycyrrhiza, cyclosporine A, fluvastatin and so on. Conclusions SARS-CoV-2 infection can damage the hematopoietic system by changing the expression of a series of genes. The potential intervention drugs screened from this have certain reference significance for the basic and clinical research of coronavirus disease 2019 (COVID-19). © 2020 People's Military Medical Press. All rights reserved.

Prokaryotic expression, purification and antiserum preparation of severe acute respiratory syndrome coronavirus 2 nucleocapsid protein

Objective To express and purify the recombinant nucleocapsid (N) protein of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), and prepare antiserum from immunized mice. Methods The prokaryotic plasmid pET28a-N containing SARS-CoV-2 N gene was transformed into Escherichia coli BL21 (DE3). The expression of recombinant SARS-CoV-2 N protein was induced by isopropyl-β-D-thiogalactopyranoside. The Ni-NTA affinity chromatography column was used to purify the recombinant SARS-CoV-2 N protein, and antiserum was obtained from the BALB/c mice immunized with recombinant SARS-CoV-2 N protein combined with manganese adjuvant through intramuscular and subcutaneous injections. The reactions of recombinant SARS-CoV-2 N protein with SARS-CoV-2 N monoclonal antibodies and severe acute respiratory syndrome coronavirus (SARS-CoV) N polyclonal antibodies were detected by Western blotting. The reaction of mouse antiserum with the recombinant SARS-CoV-2 N protein expressed in the cells transfected with eukaryotic expression plasmid was examined by indirect immunofluorescence assay. Results The recombinant SARS-CoV-2 N protein was successfully induced and expressed as a soluble protein with a molecular weight of about 55 000. High concentration of purified protein was obtained. The results of Western blotting showed that the recombinant SARS-CoV-2 N protein could be specifically recognized by the SARS-CoV-2 N monoclonal antibodies and the SARS-CoV N polyclonal antibodies. The prepared mouse antiserum could also correctly recognize the recombinant SARS-CoV-2 N protein expressed in mammalian cells by indirect immunofluorescence assay. Conclusion Recombinant SARS-CoV-2 N protein has been successfully expressed and purified from the prokaryotic expression system, and mouse antiserum has been prepared, which lays a foundation for establishing a rapid SARS-CoV-2 diagnostic tool and further studying the function of SARS-CoV-2 N protein..

Efficacy analysis of severe acute respiratory syndrome coronavirus 2 DNA vaccine and recombinant subunit vaccine inducing neutralizing antibodies in mice

Objective To investigate the efficacy of neutralizing antibodies induced by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) receptor-binding domain (RBD) and spike (S) protein S1 subunit. Methods The SARS-CoV-2 RBD and mouse immunoglobulin G1 (IgG1) Fc fragment (mFc) fusion protein expression plasmid pVRCRBD- mFc was constructed and transfected into human embryonic kidney 293T cells. The RBD-mFc fusion protein in the cell supernatants was detected by Western blotting. The effect of RBD-mFc in cell supernatants and CHO recombinant S1-human IgG1 Fc (S1-hFc) fusion protein on SARS-CoV-2 infection was detected by microneutralization test. BALB/c mice were immunized with plasmid pVRC-RBD-mFc and S1-hFc fusion protein via intramuscular injection. Anti-S1 IgG antibodies in mouse sera were detected by enzyme-linked immunosorbent assay (ELISA), and the virus neutralization activity of mouse sera was detected by microneutralization test. Results The RBD-mFc fusion protein could be detected in the culture supernatants of 293T cells transfected with the plasmid pVRC-RBD-mFc, the concentrated supernatants and the S1- hFc fusion protein could inhibit SARS-CoV-2 infection on Vero E6 cells in a concentration-dependent manner. Anti-S1 IgG antibodies could be detected in the sera of mice immunized with plasmid pVRC-RBD-mFc and S1-hFc fusion protein, and the sera of both groups could neutralize SARS-CoV-2 infection. The serum antibody titers and virus neutralization activity of S1- hFc fusion protein immunized mice were significantly higher than those of plasmid pVRC-RBD-mFc immunized mice (both P<0.01). Conclusion Both SARS-CoV-2 RBD and S1 subunit may be used as effective vaccine antigens. Compared with DNA vaccine, recombinant subunit vaccine can induce neutralizing antibody more effectively..

Stability and infectivity of coronaviruses in inanimate environments.

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is a highly contagious virus that can transmit through respiratory droplets, aerosols, or contacts. Frequent touching of contaminated surfaces in public areas is therefore a potential route of SARS-CoV-2 transmission. The inanimate surfaces have often been described as a source of nosocomial infections. However, summaries on the transmissibility of coronaviruses from contaminated surfaces to induce the coronavirus disease 2019 are rare at present. This review aims to summarize data on the persistence of different coronaviruses on inanimate surfaces. The literature was systematically searched on Medline without language restrictions. All reports with experimental evidence on the duration persistence of coronaviruses on any type of surface were included. Most viruses from the respiratory tract, such as coronaviruses, influenza, SARS-CoV, or rhinovirus, can persist on surfaces for a few days. Persistence time on inanimate surfaces varied from minutes to up to one month, depending on the environmental conditions. SARS-CoV-2 can be sustained in air in closed unventilated buses for at least 30 min without losing infectivity. The most common coronaviruses may well survive or persist on surfaces for up to one month. Viruses in respiratory or fecal specimens can maintain infectivity for quite a long time at room temperature. Absorbent materials like cotton are safer than unabsorbent materials for protection from virus infection. The risk of transmission via touching contaminated paper is low. Preventive strategies such as washing hands and wearing masks are critical to the control of coronavirus disease 2019.

Potential influence of COVID-19/ACE2 on the female reproductive system.

The 2019 novel coronavirus (2019-nCoV) appeared in December 2019 and then spread throughout the world rapidly. The virus invades the target cell by binding to angiotensin-converting enzyme (ACE) 2 and modulates the expression of ACE2 in host cells. ACE2, a pivotal component of the renin-angiotensin system, exerts its physiological functions by modulating the levels of angiotensin II (Ang II) and Ang-(1-7). We reviewed the literature that reported the distribution and function of ACE2 in the female reproductive system, hoping to clarify the potential harm of 2019-nCoV to female fertility. The available evidence suggests that ACE2 is widely expressed in the ovary, uterus, vagina and placenta. Therefore, we believe that apart from droplets and contact transmission, the possibility of mother-to-child and sexual transmission also exists. Ang II, ACE2 and Ang-(1-7) regulate follicle development and ovulation, modulate luteal angiogenesis and degeneration, and also influence the regular changes in endometrial tissue and embryo development. Taking these functions into account, 2019-nCoV may disturb the female reproductive functions through regulating ACE2.

[Clinical features of coronavirus disease 2019 in children: a systemic review of severe acute respiratory syndrome, Middle East respiratory syndrome, and coronavirus disease 2019]

OBJECTIVE: To systematically summarize the clinical features of coronavirus disease 2019 (COVID-19) in children. METHODS: PubMed, Embase, Web of Science, The Cochrane Library, CNKI, Weipu Database, and Wanfang Database were searched for clinical studies on COVID-19 in children published up to May 21, 2020. Two reviewers independently screened the articles, extracted data, and assessed the risk of bias of the studies included. A descriptive analysis was then performed for the studies. Related indices between children with COVID-19 and severe acute respiratory syndromes (SARS) or Middle East respiratory syndrome (MERS) were compared. RESULTS: A total of 75 studies were included, with a total of 806 children with COVID-19. The research results showed that the age of the children ranged from 36 hours after birth to 18 years, with a male-female ratio of 1.21 : 1. Similar to SARS and MERS, COVID-19 often occurred with familial aggregation, and such cases accounted for 74.6% (601/806). The children with COVID-19, SARS, and MERS had similar clinical symptoms, mainly fever and cough. Some children had gastrointestinal symptoms. The children with asymptomatic infection accounted for 17.9% (144/806) of COVID-19 cases, 2.5% (2/81) of SARS cases, and 57.1% (12/21) of MERS cases. The children with COVID-19 and MERS mainly had bilateral lesions on chest imaging examination, with a positive rate of lesions of 63.4% (421/664) and 26.3% (5/19) respectively, which were lower than the corresponding positive rates of viral nucleic acid detection, which were 99.8% and 100% respectively. The chest radiological examination of the children with SARS mainly showed unilateral lesion, with a positive rate of imaging of 88.9% (72/81), which was higher than the corresponding positive rate of viral nucleic acid detection (29.2%). Viral nucleic acid was detected in the feces of children with COVID-19 or SARS, with positive rates of 60.2% (56/93) and 71.4% (5/7) respectively. The children with COVID-19 had a rate of severe disease of 4.6% (31/686) and a mortality rate of 0.1% (1/806), the children with SARS had a rate of severe disease of 1.5% (1/68) and a mortality rate of 0%, and those with MERS had a rate of severe disease of 14.3% (3/21) and a mortality rate of 9.5% (2/21). CONCLUSIONS: Children with COVID-19 have similar symptoms to those with SARS or MERS, mainly fever and cough. Asymptomatic infection is observed in all three diseases. Children with COVID-19 or SARS have milder disease conditions than those with MERS. COVID-19 in children often occurs with familial aggregation. Epidemiological contact history, imaging examination findings, and viral nucleic acid testing results are important bases for the diagnosis of COVID-19.