RESUMO
Objective To explore the machine learning model and risk factor analysis for hospital infection caused by carbapenem-resistant enterobacteriaceae(CRE).Methods The clinical data of totally 451 patients infected with extended-spectrum β-lactamases(ESBL)producing Enterobacteriaceae treated in the hospital from 2018 to 2022 were retrospectively collected.The patients were divided into CRE group(115 cases)and sensitive group(336 cases)according to the susceptibility of carbapenem.Four machine learning methods in-cluding Logistic regression analysis,random forest,support vector machine,and neural network were used to build prediction models and receiver operating characteristic curve was used to evaluate.Based on the predic-tion model with the best performance,risk factors for CRE infection were analyzed.Results Random forest model had the best performance,with the area under the curve of 0.952 3.The risk factors for predicting CRE infection by the random forest model included 15 clinical data items,namely fever for more than 3 days,cere-bral injury,drainage fluid sample,trunk surgery,first-level or special-level nursing,ICU treatment,procalcito-nin,anti-anaerobic bacteria,the use of third-generation cephalosporins,age,pre-albumin,creatinine,white blood cell count,and albumin.Conclusion The CRE prediction model developed in this study has good predic-tive value and the risk factors have guiding significance for the early prevention and treatment of CRE infec-tion in clinical practice.
RESUMO
Obsjective To analyze the inflammation characteristics and changes of small airway function in patients with eosinophil and neutrophil asthma, and provide evidence for individualized treatment of asthma. Methods:Using a cross-sectional study, 46 patients with eosinophilic asthma and 42 patients with neutrophilic asthma confirmed by cytology of induced sputum were recruited from July 1, 2017 to June 30, 2019 at the respiratory Department of Respiratory Medicine,Jinshan Branch of the Sixth People's Hospital of Shanghai. Patients were divided by asthma category into eosinophilic asthma group and neutrophilic asthma group.The severity of acute attack, the score of asthma control test (ACT) and the concentration of serum C-reactive protein (CRP) were compared between the two groups The fraction of exhaled nitric oxide (FeNO), related cytokines(interleukin-4(IL-4), interleukin-5(IL-5), interleukin-13(IL-13), interleukin-17(IL-17) and interferon γ(IFN-γ)) in peripheral blood and induced sputum supernatant and lung function indicators (forced exhalation volume in one second (FEV1)% percent predicted (%pred), maximal mid-expiratory flow (MMEF)% pred, forced expiratory flow (FEF) 75% pred, forced expiratory flow at 50% of FVC exhaled (FEF50%) pred were detected. Independent sample t-test was used for the comparison between measurement data groups comforming to normal distritution, rank sum test was used for the comparison between measurement data groups not conforming to normal distribution, and χ 2 test was used for the comparison of counting data. Results:There were no significant differences in the general data and ACT scores between the two groups (all P>0.05). The ratio of severe and critical degree (52.38%(22/42)), uncontrolled and partially controlled patients (59.52%(25/42)), CRP level (24.6(7.1, 35.0) mg/L) in neutrophil asthma group were higher than those in eosinophilic asthma group(30.43% (14/46), 36.96% (17/46), and 8.5 (2.0, 12.0) mg/L, respectively) (χ 2=4.37, χ 2=4.48, Z=4.76; P=0.036, P=0.034, P<0.001). The concentration of FeNO was higher in eosinophilic asthma group (76(54,93) ppb) than that in neutrophil asthma group(27(15,41) ppb),and the differences was statistically significant ( Z=6.52, P<0.001). The values of FEV1% pred ((56.13±21.51)%), MMEF% pred ((62.03±23.97)%), FEF75% pred ((54.42±20.49)%), FEF50% pred ((66.89±26.47)%) in neutrophil asthma group were lower than those in eosinophilic asthma group ((68.53±29.81)%, (72.16±23.05)%, (65.38±25.46)% and (79.86±27.61)%), and the difference between the two groups was statistically significant( t values were 2.25, 2.02, 2.21, 2.24; P values were 0.027, 0.046, 0.030, 0.027). The concentrations of serum IL-4((49.42±24.46) ng/L), IL-5((104.89±43.91) ng/L) and IL-4((44.49±19.12) ng/L), IL-5((95.45±28.58) ng/L) in induced sputum supernatant were higher than neutrophilic asthma group((32.29±14.19), (50.35±22.30), (33.33±15.08), (55.61±26.41) ng/L). The difference between the two groups was statistically significant ( t values were 4.06, 7.44, 3.02, 6.77, P values were <0.001, <0.001, 0.003, <0.001). In eosinophilic asthma group, the concentrations of serum IL-13 ((76.18±20.62) ng/L), IL-17 ((31.32±9.32) ng/L), IFN-γ ((18.27±5.56) ng/L) and IL-13((71.08±20.08) ng/L), IL-17((26.29±6.70) ng/L), and IFN-γ((17.61±5.94) ng/L) in induced sputum supernatant were lower than those in neutrophilic asthma group((153.83±44.53 ) ng/L, (55.27±18.89) ng/L, (26.46±10.08) ng/L, (120.32±28.41) ng/L, (44.99±12.66) ng/L, (23.91±7.66) ng/L). The difference between the two groups was statistically significant ( t values were 10.33, 7.43, 4.66,9.31,8.54,4.33, respectively; all P<0.001). Conclusion:Eosinophilic asthma and neutrophil asthma have different inflammation, small airway function characteristics and different response to treatment. The small airway function changes in early stage of neutrophil asthma are more obvious.