Active regression model for clinical grading of COVID-19.

Background: In the therapeutic process of COVID-19, the majority of indicators that physicians have for assisting treatment have come from clinical tests represented by proteins, metabolites, and immune levels in patients' blood. Therefore, this study constructs an individualized treatment model based on deep learning methods, aiming to realize timely intervention based on clinical test indicator data of COVID-19 patients and provide an important theoretical basis for optimizing medical resource allocation. Methods: This study collected clinical data from a total of 1,799 individuals, including 560 controls for non-respiratory infectious diseases (Negative), 681 controls for other respiratory virus infections (Other), and 558 coronavirus infections (Positive) for COVID-19. We first used the Student T-test to screen for statistically significant differences (Pvalue<0.05); we then used the Adaptive-Lasso method stepwise regression to screen the characteristic variables and filter the features with low importance; we then used analysis of covariance to calculate the correlation between variables and filter the highly correlated features; and finally, we analyzed the feature contribution and screened the best combination of features. Results: Feature engineering reduced the feature set to 13 feature combinations. The correlation coefficient between the projected results of the artificial intelligence-based individualized diagnostic model and the fitted curve of the actual values in the test group was 0.9449 which could be applied to the clinical prognosis of COVID-19. In addition, the depletion of platelets in patients with COVID-19 is an important factor affecting their severe deterioration. With the progression of COVID-19, there is a slight decrease in the total number of platelets in the patient's body, particularly as the volume of larger platelets sharply decreases. The importance of plateletCV (count*mean platelet volume) in evaluating the severity of COVID-19 patients is higher than the count of platelets and mean platelet volume. Conclusion: In general, we found that for patients with COVID-19, the increase in mean platelet volume was a predictor for SARS-Cov-2. The rapid decrease of platelet volume and the decrease of total platelet volume are dangerous signals for the aggravation of SARS-Cov-2 infection. The analysis and modeling results of this study provide a new perspective for individualized accurate diagnosis and treatment of clinical COVID-19 patients.

Hypertension in Patients Hospitalized with COVID-19 in Wuhan, China.

It is unclear whether patients with hypertension are more likely to be infected with severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) than the general population and whether there is a difference in the severity of coronavirus disease (COVID-19) pneumonia in patients who have taken ACEI/ARB drugs compared with those who have not.This observational study included data from all patients with clinically confirmed COVID-19 admitted to Hankou Hospital, Wuhan, China, between January 5 and March 8, 2020. Data were extracted from clinical and laboratory records. Follow-up was cut off on March 8, 2020.A total of 274 patients, 75 with hypertension and 199 without hypertension, were included in the analysis. Compared with patients without hypertension, patients with hypertension were older and were more likely to have preexisting comorbidities, including chronic renal insufficiency, cardiovascular disease, diabetes mellitus, and cerebrovascular disease. Moreover, patients with hypertension tended to have higher positive rate for SARS-CoV-2 PCR detection. Multivariate logistic regression analysis showed that age (P = 0.005) and gender (P = 0.019) were independent risk factors associated with the severity of pneumonia in patients on admission, whereas ACEI/ARB treatment (P = 0.184) was not.Patients with COVID-19 with hypertension were significantly older and were more likely to have underlying comorbidities, including chronic renal insufficiency, cardiovascular disease, diabetes mellitus, and cerebrovascular disease. ACEI/ARB drugs did not influence the severity of pneumonia in patients with SARS-CoV-2. In future studies, a larger sample size and multi-center clinical data would be needed to support these conclusions.

[Acute kidney injury in patients hospitalized with COVID-19 in Wuhan, China: a single-center retrospective observational study].

OBJECTIVE: To assess the predictors and outcomes of acute kidney injury (AKI) among patients with coronavirus disease 2019 (COVID-19). OBJECTIVE: This retrospective observational study was conducted among patients with a confirmed diagnosis of COVID-19 admitted to Hankou Hospital between January, 5 and March 8, 2020. We evaluated the association of AKI with the demographic and biochemical parameters and clinical outcomes of the patients using univariate regression analysis. OBJECTIVE: Atotal of 287 COVID-19 patients, including 55 with AKI and 232 without AKI, were included in the analysis. Compared with the patients without AKI, the patients with AKI were older, predominantly male, and were more likely to have hypoxia and pre-existing hypertension and cerebrovascular diseases. The patients with AKI also had higher levels of white blood cells, D-dimer, aspartate aminotransferase, total bilirubin, creatine kinase, lactate dehydrogenase, procalcitonin, C-reactive protein, a higher prevalence of hyperkalemia, lower lymphocyte counts, and higher chest computed tomographic scores. The incidence of stage 1 AKI was 14.3% and that of stage 2 or 3 AKI was 4.9%. The patients with AKI had much higher mortality rate than those without AKI. OBJECTIVE: AKI is an important complication of COVID-19. An older age, a male gender, multiple pre- existing comorbidities, lymphopenia, increased infection indicators, elevated D-dimer, and impaired heart and liver functions are all potential risk factors ofAKI. COVID- 19 patients with AKI that progresses into stages 2 or 3 AKI have a high mortality rate. Prevention of AKI and monitoring kidney function is critical in the care of COVID-19 patients.

[Clinical features of severe or critical ill patients with COVID-19].

OBJECTIVE: To analyze the clinical features of severe or critical ill adult patients with coronavirus disease (COVID-19). METHODS: The clinical data of 75 patients with severe or critical COVID-19 in Honghu People's Hospital from January to March in 2020 were collected. RESULTS: Of the 75 patients with COVID-19 pneumonia, 41 were male (54.67%) and 34 were female (45.33%) with a mean age of 67.53 ±12.37 years; 43 patients had severe and 32 had critical COVID-19, and 49.3% of the patients had underlying diseases. The main clinical manifestations included fever (78.67%) and coughing (70.67%). Compared with the severe patients, the critically ill patients had higher proportions of patients over 60 years old with elevated white blood cell count, increased prothrombin time, and higher levels of hsCRP, PCT, D-dimer, ALT, LDH, cTnI and NT-proBNP. Univariate logistic regression analysis showed that an age over 60 years, leukocytosis, hs-CRP elevation, prolonged prothrombin time, and increased levels of D-dimer, NT-proBNP and cTnI were associated with severe COVID-19. Multivariate logistic regression showed that an age over 60 years (OR=8.165, 95% CI: 1.483-45.576, P=0.017), prolonged prothrombin time (OR=7.516, 95% CI: 2.568-21.998, P=0.006) and elevated NT-proBNP (OR=6.194, 95% CI: 1.305-29.404, P=0.022) were independent risk factors for critical type of COVID-19. CONCLUSIONS: An age over 60 years, a prolonged prothrombin time and elevated NT-proBNP level are important clinical features of critically ill patients with COVID-19, and can be deemed as early warning signals for critical conditions of the disease.

[Clinical characteristics and outcomes of adult critically ill patients with COVID-19 in Honghu, Hubei Province].

OBJECTIVE: To explore the clinical characteristics and outcomes of adult critically ill patients with COVID-19 and identify the risk factors correlated with in-hospital deaths. METHODS: This study was conducted among 20 confirmed adult cases of COVID-19 in the Intensive Care Unit (ICU) of Honghu People's Hospital in Jingzhou City, Hubei Province. According to the final outcome, the patients were divided into survivor group and death group with 10 patients each. The demographic data, clinical manifestations and signs, laboratory findings, treatment measures and clinical outcomes were obtained from electronic medical records to compare the clinical characteristics and outcomes between the two groups. Univariate logistic analysis was used to analyze the risk factors associated with in-hospital death. RESULTS: The mean age of patients with confirmed COVID-19 was 70 ± 12 years, and 40% of them were male. The patients were admitted to ICU 11 ± 9 days after symptom onset. The most common symptoms on admission were cough (19 cases), fatigue or myalgia (18 cases), fever (17 cases) and dyspnea (16 cases). Eleven (55%) of the patients had underlying diseases, among which hypertension was the most common (11 cases), followed by cardiovascular disease (4 cases) and diabetes (3 cases). Six (30%) of the patients received invasive mechanical ventilation and continued renal replacement therapy but eventually died. Acute cardiac injury was the most common complication (19 cases). Half of the patients died between the 2nd and 19th day after ICU admission. Compared with dead patients, the surviving patients had a lower average body weight (61.70±2.36 vs 68.60±7.15 kg, P=0.01) and a higher Glasgow Coma Index (14.69 ± 0.70 vs 12.70 ± 2.45, P=0.03), and were less likely to develop shock (2 vs 10, P=0.001) or acute respiratory distress syndrome (2 vs 10, P=0.001). CONCLUSIONS: Critically ill patients with COVID-19 are generally older. A higher body weight and a lower lymphocyte count are potentially associated with a greater likeliness of fatality in ICU patients with COVID-19.