ObjectiveTo investigate the distribution of bacteria detected from blood culture of pediatric patients and to observe the blood culture contamination rate. MethodsA total of 6 530 blood samples, collected from January 2011 to December 2012 were detected by BacT/Alert 3D automated blood culture system. We found out the contamination bacteria according to clinical data, laboratory data and microbiology knowledge. ResultsA total of 314 bacteria strains were isolated from 6 530 blood samples, and the positive rate was 4.8%, 228 of which were gram-positive bacteria. The isolates were mainly coagulase-negative staphylococci (43.9%), followed by Staphylococcus aureus (2.9%). In addition, 86 cases were gram-negative bacteria, the majority of which were Escherichia coli (9.6%), followed by Klebsiella pneumonia (8.3%). The overall blood culture contamination rate was 49.7% (156 bacteria were identified). The top two were coagulase-negative staphylococci (31.2%), followed by Bacillus sp. (6.4%). ConclusionThe contamination rate is high in children's blood culture, and coagulase-negative staphylococci are the main bacteria. It's necessary to use clinical data and laboratory data to determine its clinical significance, and avoid unnecessary use of antibiotics.
ObjectiveTo realize automatic risk bias assessment for the randomized controlled trial (RCT) literature using BERT (Bidirectional Encoder Representations from Transformers) as an approach for feature representation and text classification.MethodsWe first searched The Cochrane Library to obtain risk bias assessment data and detailed information on RCTs, and constructed data sets for text classification. We assigned 80% of the data set as the training set, 10% as the test set, and 10% as the validation set. Then, we used BERT to extract features, construct text classification model, and evaluate the seven types of risk bias values (high and low). The results were compared with those from traditional machine learning methods using a combination of n-gram and TF-IDF as well as the Linear SVM classifier. The accuracy rate (P value), recall rate (R value) and F1 value were used to evaluate the performance of the models.ResultsOur BERT-based model achieved F1 values of 78.5% to 95.2% for the seven types of risk bias assessment tasks, which was 14.7% higher than the traditional machine learning method. F1 values of 85.7% to 92.8% were obtained in the extraction task of the other six types of biased descriptors except "other sources of bias", which was 18.2% higher than the traditional machine learning method.ConclusionsThe BERT-based automatic risk bias assessment model can realize higher accuracy in risk of bias assessment for RCT literature, and improve the efficiency of assessment.