Objective To explore the value of MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms in the diagnosis of mild cognitive impairment(MCI).Methods Patients who underwent cranial MR examination were retrospectively selected.According to the inclusion and exclusion criteria,a total of 173 subjects were finally included and randomly divided into training set and test set in a ratio of 7∶3.After delineating the regions of interest(ROI)of the frontal and temporal lobes on T2-fluid attenuated inversion recovery(FLAIR)images,radiomics features were extracted based on the Pyradiomics data package.Features were screened through inter-and intraclass correlation coefficient(ICC),independent samples t-test,and the LightGBM algorithm.Diagnostic models were constructed using support vector machine(SVM),random forest(RF),decision tree(DT),K-nearest neighbor(KNN),gradient boosting decision tree(GBDT),and extreme gradient boosting(XGBoost)combined with 10-fold cross-validation respectively.The training set was further divided into 9 training data sets and 1 validation data set through 10-fold cross-validation,and the hyperparameters were optimized through iterative cycles.The diagnostic efficacy of the model was evaluated by receiver operating characteristic(ROC)curve and area under the curve(AUC),and the DeLong test was applied to compare the differences between different models.Results The AUC of the radiomics models constructed by SVM,DT,RF,KNN,GBDT,XGBoost in the training set were 0.951,0.992,0.998,0.957,1.000,and 1.000 respectively,in the validation set were 0.890,0.843,0.934,0.878,0.930,and 0.945 respectively,and in the test set were 0.902,0.711,0.899,0.849,0.889,and 0.882 respectively.Conclusion MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms can diagnose MCI,and the model constructed based on SVM shows the highest diagnostic value.

Objective To explore the value of MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms in the diagnosis of mild cognitive impairment(MCI).Methods Patients who underwent cranial MR examination were retrospectively selected.According to the inclusion and exclusion criteria,a total of 173 subjects were finally included and randomly divided into training set and test set in a ratio of 7∶3.After delineating the regions of interest(ROI)of the frontal and temporal lobes on T2-fluid attenuated inversion recovery(FLAIR)images,radiomics features were extracted based on the Pyradiomics data package.Features were screened through inter-and intraclass correlation coefficient(ICC),independent samples t-test,and the LightGBM algorithm.Diagnostic models were constructed using support vector machine(SVM),random forest(RF),decision tree(DT),K-nearest neighbor(KNN),gradient boosting decision tree(GBDT),and extreme gradient boosting(XGBoost)combined with 10-fold cross-validation respectively.The training set was further divided into 9 training data sets and 1 validation data set through 10-fold cross-validation,and the hyperparameters were optimized through iterative cycles.The diagnostic efficacy of the model was evaluated by receiver operating characteristic(ROC)curve and area under the curve(AUC),and the DeLong test was applied to compare the differences between different models.Results The AUC of the radiomics models constructed by SVM,DT,RF,KNN,GBDT,XGBoost in the training set were 0.951,0.992,0.998,0.957,1.000,and 1.000 respectively,in the validation set were 0.890,0.843,0.934,0.878,0.930,and 0.945 respectively,and in the test set were 0.902,0.711,0.899,0.849,0.889,and 0.882 respectively.Conclusion MRI radiomics based on the frontal and temporal lobes combined with multiple machine learning algorithms can diagnose MCI,and the model constructed based on SVM shows the highest diagnostic value.

OBJECTIVE To investigate the 16S rRNA methylase gene and aminoglycoside-modifying enzyme genes in Pseudomonas aeruginosa isolated from burned patients. METHODS GNS-448 and K-B tests were performed to detect the susceptibility to 19 kinds of antimicrobial agents against these strains. 16S rRNA methylase gene and aminoglycoside-modifying enzyme genes were amplified by polymerase chain reaction (PCR) and verified by DNA sequencing. RESULTS The 32 isolated strains were all resistant to ampicillin,cefuroxime,cefoxitin,SMZ-TMP,The sensitive rates to amikacin and gentamicin were 68% and 46.9%,respectively. The resistant rates to imipenem and meropenem were 68.8% and 59.4%,respectively. The 16S rRNA methylase gene and aminoglycoside-modifying enzyme genes including aac(6')-Ⅰb,aac(6')-Ⅱ,ant(3″)-Ⅰ,ant(2″)-Ⅰ and rmtB were found and positive rates were 9.4%,3.1%,28.1%,25.0% and 3.1%,respectively. A novel subtype of aac(6')-Ⅰb was reported firstly. CONCLUSIONS There are high positive percentage of 16S rRNA methylase gene and aminoglycoside-modifying enzyme genes in P. aeruginosa isolated from burned patients. P. aeruginosa resistance to aminoglycoside relates to the existence of 16S rRNA methylase gene and aminoglycoside-modifying enzyme genes.

OBJECTIVE To analyze antibiotic resistance pattern and use pulsed-field gel electrophoresis(PFGE) to study the molecular epidemiology of Pseudomonas aeruginosa isolated from burn unit. METHODS P.aeruginosa had been isolated and tested by K-B method from clinical samples and antibiotic resistance was analyzed and studied retrospectively. RESULTS The drug resistance of P.aeruginosa to nine antibiotics was high,the multiple drug resistance rate was 30%. CONCLUSIONS The resistance rates to commonly used antibacterials in P.aeruginosa are high and the resistance pattern is wide.PEGE is a better genotyping method to study molecular epidemiology and analytic homology.

OBJECTIVE To investigate the disinfectant-resistant gene qacE△1-sul1 in Pseudomonas aeruginosa isolated from burned patients. METHODS GNS-448 and K-B tests were performed to detect the susceptibility of 19 kinds of antimicrobial agents against these strains. Genotype was analyzed by polymerase chain reaction(PCR) and verified by DNA sequencing. RESULTS The 32 strains isolated were all resistant to ampicillin,cefuroxime,cefoxitin,SMZ/TPM. The sensitive rates to amikacin and gentamicin were 68.0%,and 46.9%,respectively,the resistant rates to imipenem and meropenem were 68.8% and 59.4%,respectively. The positive rate of gene qacE△1-sul1 was 50.0%. CONCLUSIONS The resistance of P. aeruginosa isolated from burned patients is a serious issue.There is high positive percentage of qacE△1-sul1 gene in P. aeruginosa isolated from burned patients.

OBJECTIVE To analyze the cause of Acinetobacter baumannii resistance to ?-lactam and the aminoglycoside-modifying antibacterials. METHODS Three-dimensional test was used to analyze and classify the ?-lactamases. Proper primers was used to do PCR and determined by sequencing. RESULTS A. baumannii clinical isolate harbored blaOXA2-23,blaTEM and blaADC genes and aac(3)-Ⅰ,aac(6')-Ⅰb and ant(3″)-Ⅰ aminoglycoside-modifying enzyme genes. CONCLUSIONS An A. baumannii strain which carries TEM,OXA-23,ADC ?-lactams and aac(3)-Ⅰ,aac(6')-Ⅰb,ant(3″)-Ⅰ aminoglycoside-modifying enzyme genes is detected.