Research On The Characteristics Of COVID-19 Clinical Big Data And The Establishment Of Diagnosis And Treatment Models

Objectives:Coronavirus Disease 2019(COVID-19)and influenza share many similarities such as transmission and clinical symptoms.Failure to distinguish the two diseases may increase the risk of transmission.A fast and convenient differential diagnosis between COVID-19 and influenza has significant clinical value,especially for the undeveloped countries with the shortage of nucleic acid detection kit.This study aimed to develop a diagnostic model to differentiate the two diseases based on the big clinical data.Patients and methods:A total of 493 patients were enrolled including 282 with COVID-19 and 211 with influenza.All data were collected and reviewed retrospectively.The clinical and laboratory characteristics of all the patients were analyzed and compared.Then we divided all patients into training set and validation set randomly,and developed a diagnostic model using multivariate logistic regression analysis.Finally,we also validated the diagnosis model using the validation set.Results:We established the diagnostic model between COVID-19 and influenza,which was consisted of five variables: age,dry cough,fever,white cell count and D-dimer,it showed good performance of differential diagnosis.Using the predictive model,the sensitivity,specificity,positive predictive value,and negative predictive value with a cutoff level of 0.36were73.3,87.5,87.5,and 73.3 respectively in the validation data set.Conclusions:We established the diagnostic model between COVID-19 and influenza,which was consisted of five variables: age,dry cough,fever,white cell count and D-dimer,it showed good performance of differential diagnosis.Background:Severe patients account for most coronavirus disease(COVID-19)deaths.Diabetes is one of the most common comorbidities.We aimed to investigate the clinical characteristics of severe COVID-19 patients with diabetes and explore the impact of glucose-lowering medications on the outcomes of these patients.Method:A total of 858 consecutive patients with severe COVID-19 were enrolled in this retrospective study,and 164 patients had diabetes.Clinical characteristics,laboratory findings,clinical management,and outcomes were analyzed and severe COVID-19 patients with and without diabetes were compared.Outcomes of patients taking different glucose-lowering drugs were also compared.Results:Among the 858 hospitalized patients,19.1%(164/858)had diabetes.COVID-19 diabetic patients had a higher mortality rate than non-diabetic patients,after adjusting for confounders.Severe COVID-19 diabetic patients without antidiabetic therapy demonstrated a higher mortality risk than those on antidiabetic therapy.The relative mortality rate in users with?-glucosidase inhibitors was much lower than those without ?-glucosidase inhibitors.Secretagogues,biguanides,and insulin showed no effect on reduction of mortality risk in severe COVID-19 patients with diabetes.Conclusions:Mortality risk was high in severe COVID-19 diabetic patients.?-glucosidase inhibitors may be associated with a decreased mortality rate in these patients,whereas secretagogues,biguanides and insulin may have no effect.Background:Coronavirus disease 2019(COVID-19)has caused over two million deaths globally.WHO confirmed that the incidence rate of COVID-19 reached a peak again earlier in 2021.The analysis of risk factors and clinical course of fatal cases would help to reduce the mortality.Methods:Medical records of 109 deaths were collected between February 4,2020,and April 7,2020.Clinical characteristics,laboratory indices,treatments,and deep-learning system-assessed lung lesion volumes were analyzed.The impact of different medicines on survival time was also investigated.Results:The median age of the patients was 73.0 years,and 65.1% were male.The most common symptoms were fever(75 [68.8%]),cough(71 [65.1%]),anorexia(61 [60.0%]),fatigue(64 [58.7%]),and dyspnea(59 [54.1%]).Most patients had chronic diseases such as hypertension(50[45.9%]),diabetes(31[28.4%]),and cardiovascular disease(31[28.4%]).The volumes of ground-glass,consolidation,total lesions and total lung were quantified.Median time from symptom onset to death was 23.5(IQR16.8-34.2)days.Respiratory failure(63 [57.8%]),shock(40 [36.7%]),and acute respiratory distress syndrome(29 [26.6%])were common complications.Most patients received antibiotic(96 [88.1%]),antiviral(75[68.8%]),traditional Chinese medicine(82 [75.2%]),and glucocorticoid(77 [71.3%])treatments.Forty(36.6%)and 17(15.6%)patients received immunoglobulin and targeted immunomodulatory therapy,respectively.Meanwhile,Pearson correlation analysis showed that the volume of consolidation in lungs was positively correlated with the absolute neutrophils,D-dimer and procalcitonin(P < 0.05).Conclusions:Most patients with fatal outcomes had comorbidities.The leading causes of death were respiratory failure and multiple organ dysfunction syndrome.Antivirals,antibodies,and traditional Chinese medicine might prolong the survival time of COVID-19 patients on admission.