Provincial clustering and related factors analysis of clinic antimicrobial resistance in China.

OBJECTIVE: Antimicrobial resistance (AMR) is among the biggest and most pressing risks facing healthcare in China and globally. We aimed to describe the current status regarding the distribution of clinic AMR in China through provincial clustering and analyse the related factors. METHODS: Based on the detection rates of 13 major drug-resistant bacteria in 31 provinces across the country, as reported by the National Bacterial Resistance Surveillance Network in 2019, we carried out a provincial clustering by dividing the conditions of provincial clinical AMR into different groups, and we then examined the potentially related factors, such as the use of antibiotics, economic development status, health service utilization, and health resource allocation. RESULTS: According to the different levels of bacterial resistance, the provinces were clustered into three categories: low, medium, and high detection rates of AMR. The three categories had notable geographic clustering and associations. Economic development status, health service utilization, such as the number of the types of antibacterial drugs (P = 0.025), health resource allocations, such as low licensed pharmacist per 1000 patient visits (P = 0.004) were related to AMR in China. CONCLUSIONS: The levels of AMR in public hospitals within the coastal areas of North China and East China were higher than those in other areas. The regions with higher levels of clinical bacterial resistance also had higher levels of health costs, health services volume and utilization, insufficient health resources per time, and higher probability of overuse of antimicrobials. Targeted measures should be taken in these areas to curb the resistance trends.

Stacking Ensemble Method for Gestational Diabetes Mellitus Prediction in Chinese Pregnant Women: A Prospective Cohort Study.

Gestational diabetes mellitus (GDM) is closely related to adverse pregnancy outcomes and other diseases. Early intervention in pregnant women who are at high risk of developing GDM could help prevent adverse health consequences. The study aims to develop a simple model using the stacking ensemble method to predict GDM for women in the first trimester based on easily available factors. We used the data from the Chinese Pregnant Women Cohort Study from July 2017 to November 2018. A total of 6,848 pregnant women in the first trimester were included in the analysis. Logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) were considered as base learners. Optimal feature subsets for each learner were chosen by using recursive feature elimination cross-validation. Then, we built a pipeline to process imbalance data, tune hyperparameters, and evaluate model performance. The learners with the best hyperparameters were employed in the first layer of the proposed stacking method. Their predictions were obtained using optimal feature subsets and served as meta-learner's inputs. Another LR was used as a meta-learner to obtain the final prediction results. Accuracy, specificity, error rate, and other metrics were calculated to evaluate the performance of the models. A paired samples t-test was performed to compare the model performance. In total, 967 (14.12%) women developed GDM. For base learners, the RF model had the highest accuracy (0.638 (95% confidence interval (CI) 0.628-0.648)) and specificity (0.683 (0.669-0.698)) and lowest error rate (0.362 (0.352-0.372)). The stacking method effectively improved the accuracy (0.666 (95% CI 0.663-0.670)) and specificity (0.725 (0.721-0.729)) and decreased the error rate (0.333 (0.330-0.337)). The differences in the performance between the stacking method and RF were statistically significant. Our proposed stacking method based on easily available factors has better performance than other learners such as RF.