Early Prediction Model for Critical Illness of Hospitalized COVID-19 Patients Based on Machine Learning Techniques.

Motivation: Patients with novel coronavirus disease 2019 (COVID-19) worsen into critical illness suddenly is a matter of great concern. Early identification and effective triaging of patients with a high risk of developing critical illness COVID-19 upon admission can aid in improving patient care, increasing the cure rate, and mitigating the burden on the medical care system. This study proposed and extended classical least absolute shrinkage and selection operator (LASSO) logistic regression to objectively identify clinical determination and risk factors for the early identification of patients at high risk of progression to critical illness at the time of hospital admission. Methods: In this retrospective multicenter study, data of 1,929 patients with COVID-19 were assessed. The association between laboratory characteristics measured at admission and critical illness was screened with logistic regression. LASSO logistic regression was utilized to construct predictive models for estimating the risk that a patient with COVID-19 will develop a critical illness. Results: The development cohort consisted of 1,363 patients with COVID-19 with 133 (9.7%) patients developing the critical illness. Univariate logistic regression analysis revealed 28 variables were prognosis factors for critical illness COVID-19 (p < 0.05). Elevated CK-MB, neutrophils, PCT, α-HBDH, D-dimer, LDH, glucose, PT, APTT, RDW (SD and CV), fibrinogen, and AST were predictors for the early identification of patients at high risk of progression to critical illness. Lymphopenia, a low rate of basophils, eosinophils, thrombopenia, red blood cell, hematocrit, hemoglobin concentration, blood platelet count, and decreased levels of K, Na, albumin, albumin to globulin ratio, and uric acid were clinical determinations associated with the development of critical illness at the time of hospital admission. The risk score accurately predicted critical illness in the development cohort [area under the curve (AUC) = 0.83, 95% CI: 0.78-0.86], also in the external validation cohort (n = 566, AUC = 0.84). Conclusion: A risk prediction model based on laboratory findings of patients with COVID-19 was developed for the early identification of patients at high risk of progression to critical illness. This cohort study identified 28 indicators associated with critical illness of patients with COVID-19. The risk model might contribute to the treatment of critical illness disease as early as possible and allow for optimized use of medical resources.

Clinical characteristics of COVID-19 patients with clinically diagnosed bacterial co-infection: A multi-center study.

OBJECTIVE: To understand the clinical characteristics of COVID-19 patients with clinically diagnosed bacterial co-infection (CDBC), and therefore contributing to their early identification and prognosis estimation. METHOD: 905 COVID-19 patients from 7 different centers were enrolled. The demography data, clinical manifestations, laboratory results, and treatments were collected accordingly for further analyses. RESULTS: Around 9.5% of the enrolled COVID-19 patients were diagnosed with CDBC. Older patients or patients with cardiovascular comorbidities have increased CDBC probability. Increased body temperature, longer fever duration, anhelation, gastrointestinal symptoms, illness severity, intensive care unit attending, ventilation treatment, glucocorticoid therapy, longer hospitalization time are correlated to CDBC. Among laboratory results, increased white blood cell counting (mainly neutrophil), lymphocytopenia, increased procalcitonin, erythrocyte sedimentation rate, C-reaction protein, D-dimer, blood urea nitrogen, lactate dehydrogenase, brain natriuretic peptide, myoglobin, blood sugar and decreased albumin are also observed, indicating multiple system functional damage. Radiology results suggested ground glass opacity mixed with high density effusion opacities and even pleural effusion. CONCLUSION: The aged COVID-19 patients with increased inflammatory indicators, worse lymphopenia and cardiovascular comorbidities are more likely to have clinically diagnosed bacterial co-infection. Moreover, they tend to have severer clinical manifestations and increased probability of multiple system functional damage.

Clinical characteristics of "re-positive" discharged COVID-19 pneumonia patients in Wuhan, China.

To analyze the clinical characteristics of re-positive discharged COVID-19 patients and find distinguishing markers. The demographic features, clinical symptoms, laboratory results, comorbidities, co-infections, treatments, illness severities and chest CT scan results of 267 patients were collected from 1st January to 15th February 2020. COVID-19 was diagnosed by RT-PCR. Clinical symptoms and nucleic acid test results were collected during the 14 days post-hospitalization quarantine. 30 out of 267 COVID-19 patients were detected re-positive during the post-hospitalization quarantine. Re-positive patients could not be distinguished by demographic features, clinical symptoms, laboratory results, comorbidities, co-infections, treatments, chest CT scan results or subsequent clinical symptoms. However, re-positive rate was found to be correlated to illness severity, according the Acute Physiology and Chronic Health Evaluation II (APACHE II) severity-of-disease classification system, and the confusion, urea, respiratory rate and blood pressure (CURB-65) score. Common clinical characteristics were not able to distinguish re-positive patients. However, severe and critical cases classified high according APACHE II and CURB-65 scores, were more likely to become re-positive after discharge.

Medical students' mental health, professional pride, and intention to work in the front-line during coronavirus disease 2019 pandemic. / 2019å† çŠ¶ç— æ¯’ç— å¤§æµè¡ŒæœŸé—´åŒ»å­¦ç”Ÿå¿ƒç†å¥åº·ã€èŒä¸šè‡ªè±ªæ„Ÿä¸Žä¸€çº¿å·¥ä½œæ„æ„¿.

OBJECTIVES: To understand medical students' mental health, professional pride, and intention to work in the front-line during coronavirus disease 2019 (COVID-19) pandemic, and provide a reference for psychological intervention. METHODS: We used the depression-anxiety-stress scale and self-designed questionnaire on professional pride, intention to work in the front-line and the extent of family support. Medical students from 4 medical schools in Fujian and Hunan were investigated. Their mental health status, professional pride and first-line work willingness with different characteristics were compared, and the influential factors for professional pride and first-line work willingness were analyzed. RESULTS: A total of 266 valid questionnaires were collected. During the pandemic, there were significant differences in the proportion of depressed students among different college and universities, majors and stages (P<0.05), and the professional pride was significantly different (P<0.001). Medical students with different mental health status showed significant differences in professional pride (P<0.01). Marriage, pressure and extent of family support were the influential factors for their professional pride (P<0.05). The latter two were also influential factors for their intention to work in the front-line (P<0.05). CONCLUSIONS: During the pandemic, students from college and nursing have relatively better mental health and higher professional pride. The professional pride is low in medical students who married, with abnormal stress or low family support. The intention to work in front-line is decreased in students with abnormal stress or low family support.

Network pharmacological analysis and mechanism prediction of Xingnaojing Injection in treatment of neurological damage caused by SARS-CoV-2

Objective: To explore the active compounds, targets and signaling pathways of Xingnaojing Injection (XNJI) for the treatment of neurological damage caused by SARS-CoV-2, so as to explore its mechanism. Methods: Using TCMSP, BATMAN, Swiss Target Prediction, and other databases, the chemical compounds and targets of XNJI were retrieved. Cytoscape software was used to construct XNJI efficacy network of "drug-compounds-targets" for coronavirus and neuroprotection, and the action mechanism was predicted by Gene Ontology (GO) and the Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment. Then core compounds were verified by molecular docking with 3CL Mpro, ACE2, and 2019-nCoV RBD/ACE2-B0AT1 complex. Results: A total of 105 active compounds of XNJI, 928 drug targets, 741 targets of coronavirus, 611 targets of neuroprotection, 83 drug-disease common targets, 12 core compounds, and seven key targets were obtained. The function enrichment analysis of GO yielded 204 entries, KEGG pathway enrichment screened 120 signaling pathways, which included Hepatitis B, pathways in cancer, TNF, HIF-1, and VEGF signaling pathway, and so on. The results of molecular docking showed that core compounds of XNJI had a good bonding activity with 3CL Mpro, ACE2 and complex. The chlorogenin and kaempferol had the lowest binding energy with three proteins and might play an important role in treatment. Conclusion: The core compounds in XNJI including chlorogenin, kaempferol, 5-hydroxy- 6,7,3',4',5'-pentamethoxyflavone, 3-methylkempferol, morin, gardenin, quercetin, artemisetin, genistein, dryobalanone, curcumin, and elemicin, which might interfere with various signaling pathways by acting on key targets like PARP1, PTGS2, MMP9, CDK2, ADORA2A, ALOX5, GSK3B, and regulate the inflammatory response, apoptosis, oxidative stress, angiogenesis, and other processes to improve the neurological damage caused by SARS-CoV-2, and inhibit virus replication and prevent infection of the host cell by binding with 3CL Mpro, ACE2 and complex, which suggest that XNJI may have a positive therapeutic effect on the neurological damage caused by SARS-CoV-2.