1.Pathogen profile of bloodstream infections in low birth weight preterm infants:a report of 95 cases
Xiaohua TANG ; Xicai TANG ; Weiqin YANG ; Jiezhen HUANG ; Zihao OU
Chinese Journal of Infection and Chemotherapy 2015;(5):439-442
Objective To study the etiology and antibiotic resistance of bloodstream infections in low birth weight preterm infants .Methods A total of 95 cases of bloodstream infections in low birth weight preterm infants were treated in our hospital from January 2011 to April 2014 .The clinical data of these patients were analyzed retrospectively .Results A total of 96 pathogens were isolated ,including 57 strains of gram‐negative bacilli ,38 strains of gram‐positive cocci ,and 1 strains of Trichosporon asahii .The most frequently isolated pathogens were Klebsiella pneumoniae (40 strains)and coagulase‐negative Staphylococcus(31 strains).All gram‐negative bacilli were sensitive to carbapenems such as imipenem and panipenem . Streptococcus isolates were sensitive to most antibiotics .Most Staphylococcus isolates were methicillin‐resistant ,which were highly resistant to common antibiotics but all sensitive to linezolid , vancomycin and teicoplanin . Conclusions The most important pathogens responsible for bloodstream infections in low birth weight preterm infants in our hospital are K lebsiella pneumoniae and coagulase‐negative Staphylococcus . Early identification of responsible pathogen and rational antimicrobial therapy are critical for good prognosis of bloodstream infections in low birth weight preterm infants .
2.Working Temperature Predication of Artificial Heart Based on Neural Network.
Qilei LI ; Ming YANG ; Wenchu OU ; Fan MENG ; Zihao XU ; Liang XU
Chinese Journal of Medical Instrumentation 2015;39(2):87-112
The purpose of this paper is to achieve a measurement of temperature prediction for artificial heart without sensor, for which the research briefly describes the application of back propagation neural network as well as the optimized, by genetic algorithm, BP network. Owing to the limit of environment after the artificial heart implanted, detectable parameters out of body are taken advantage of to predict the working temperature of the pump. Lastly, contrast is made to demonstrate the prediction result between BP neural network and genetically optimized BP network, by which indicates that the probability is 1.84% with the margin of error more than 1%.
Heart, Artificial
;
Neural Networks (Computer)
;
Temperature