ObjectiveTo establish the model of nosocomial infection risk assessment, and evaluate its accuracy of prediction. MethodsThe model of nosocomial infection risk assessment was established by expert grading, and cross-section survey of nosocomial infection was used to evaluate the predictive effect from December 2013 to February 2014. ResultsThe infection risk score of the model had statistically significant influence on nosocomial infection [OR=1.35, 95%CI (1.26, 1.44), P<0.001]. The area under curve of the receiver operating characteristic curve was 0.754. The diagnostic test's sensitivity, specificity, positive predictive value, negative predictive value and accuracy were 56.30%, 84.50%, 17.80%, 97.00% and 82.95% respectively, and the cutoff was 4. ConclusionThe model of nosocomial infection risk assessment has certain significance in the prediction of nosocomial infection, and can be regarded as a reference for establishing precaution system of nosocomial infection.
Objective To introduce how to use Stata software to implement the randomization of clinical trials. Methods Some examples were taken to describe how to implement the randomization of each kind of clinical trials. Results Stata implemented its required functions, such as simple randomization, stratified randomization, block randomization and the randomization of group treatment. Conclusion Stata can easily implement the randomization of clinical trials.