Value of S100A8 in evaluating the prognosis of children with acute lymphoblastic leukemia / 中国当代儿科杂志

OBJECTIVE@#To study the association between S100A8 expression and prognosis in children with acute lymphoblastic leukemia (ALL).@*METHODS@#The clinical data of 377 children with ALL who were treated with the CCLG-2008-ALL regimen were retrospectively reviewed. ELISA and PCR were used to measure serum protein levels and mRNA expression of S100A8. The Kaplan-Meier method was used for survival analysis and a Cox regression analysis was also performed.@*RESULTS@#The children were followed up for 56 months, and the overall survival rate of the 377 children was 89.1%. The prednisone good response group had significantly lower S100A8 protein and mRNA levels than the prednisone poor response group (P<0.01). In the children with standard or median risk, both S100A8 protein and mRNA levels were associated with event-free survival rate (P<0.05). There were significant differences in S100A8 protein and mRNA levels between the children with different risk stratifications (P<0.01). The children who experienced events had significantly higher S100A8 protein and mRNA levels than those who did not (P<0.01). The Kaplan-Meier survival analysis and the Cox regression model suggested that S100A8 overexpression was an independent risk factor for the prognosis of children with ALL.@*CONCLUSIONS@#High S100A8 expression may be associated with the poor prognosis of children with ALL and is promising as a new marker for individualized precise treatment of children with ALL.

Artificial neural network in the prediction of nosocomial infection risk / 中南大学学报(医学版)

OBJECTIVE@#To establish a model based on artificial neural network in the prediction of nosocomial infection risk.@*METHODS@#Clinical data of 27,352 inpatients extracted from hospital information system were cleaned and coded, and the model of prediction in nosocomial infection risk was developed based on artificial neural network.@*RESULTS@#The structure of artificial neural network is {16-6-1}-BP, and the fit rate of prediction was 0.9891. The area under ROC curve was 0.986.@*CONCLUSION@#Artificial neural network model can be used as a tool for nosocomial infection forecasting, which can provide supplementary information for the diagnosis and control of nosocomial infection.