[Epidemic situation of malaria in Lishui City from 2013 to 2018]

OBJECTIVE

To analyze the epidemic situation and epidemiological characteristics of malaria in Lishui City from 2013 to 2018, so as to provide the evidence for formulating the malaria control strategy.

METHODS

The data pertaining malaria cases in Lishui City from 2013 to 2018 were captured from National Notifiable Communicable Disease Reporting System and the Information System for Parasitic Diseases Control and Prevention, and the epidemiological features of malaria cases were analyzed.

RESULTS

A total of 119 malaria cases were reported in Lishui City from 2013 to 2018, including 101 cases with falciparum malaria (84.87%), 6 cases with vivax malaria (5.04%), 8 cases with ovale malaria (6.72%), and 4 cases with mixed infection (3.36%). Among the 119 cases, there were one local case with blood transfusion-induced malaria and 118 cases with over- seas imported malaria. There were 98.32% of the imported malaria cases acquiring infection in African countries, and most cases were reported in Qingtian County (60.50%) and Liandu District (22.69%). In addition, 86.55% of the malaria cases were detected in individuals at ages of 20 to 50 years, and most cases were found in oversea workers (52.94%) and businessmen (38.65%).

CONCLUSIONS

Most of the malaria cases in Lishui City are imported from Africa, and the monitoring and health education pertaining to malaria control knowledge requires to be intensified among high-risk populations.

Optimizing the Predictive Ability of Machine Learning Methods for Landslide Susceptibility Mapping Using SMOTE for Lishui City in Zhejiang Province, China

The main goal of this study was to use the synthetic minority oversampling technique (SMOTE) to expand the quantity of landslide samples for machine learning methods (i.e., support vector machine (SVM), logistic regression (LR), artificial neural network (ANN), and random forest (RF)) to produce high-quality landslide susceptibility maps for Lishui City in Zhejiang Province, China. Landslide-related factors were extracted from topographic maps, geological maps, and satellite images. Twelve factors were selected as independent variables using correlation coefficient analysis and the neighborhood rough set (NRS) method. In total, 288 soil landslides were mapped using field surveys, historical records, and satellite images. The landslides were randomly divided into two datasets: 70% of all landslides were selected as the original training dataset and 30% were used for validation. Then, SMOTE was employed to generate datasets with sizes ranging from two to thirty times that of the training dataset to establish and compare the four machine learning methods for landslide susceptibility mapping. In addition, we used slope units to subdivide the terrain to determine the landslide susceptibility. Finally, the landslide susceptibility maps were validated using statistical indexes and the area under the curve (AUC). The results indicated that the performances of the four machine learning methods showed different levels of improvement as the sample sizes increased. The RF model exhibited a more substantial improvement (AUC improved by 24.12%) than did the ANN (18.94%), SVM (17.77%), and LR (3.00%) models. Furthermore, the ANN model achieved the highest predictive ability (AUC = 0.98), followed by the RF (AUC = 0.96), SVM (AUC = 0.94), and LR (AUC = 0.79) models. This approach significantly improves the performance of machine learning techniques for landslide susceptibility mapping, thereby providing a better tool for reducing the impacts of landslide disasters.