Objective To assess the quantitative relationship between the distribution of Himalayan marmot and its ecological environment,the terrain,the temperature and the precipitation,using remote sensing and geographic information system in Qinghai province.Methods The distribution of Himalayan marmot was located by Google Earth and ArcGIS software and by using field survey data provided by Chinese Center for Disease Control and Prevention.The corresponding ecological environment of marmot including terrain,temperature and precipitation were derived from the spatial information datasets.All results were processed according to the overlay and statistics analysis using ArcGIS software.Results Seventy-seven point twenty-seven percent(153/198) of Himalayan marmot were distributed in the area of elevation between 3000 and 4000 meters.The number of marmot reached the highest when the slope was between 0 and 17 degrees,and aspect range was between 91 and 270 degrees,180 degree was as south direction.During the period with the maximum temperature of the warmest month of 14.3-17.5 ℃,17.6-20.8 ℃ and 20.9-24.0 ℃,the distribution of marmot reached 95％(186/198) of the total area.Meanwhile,most of the marmot were presented in the area with average precipitation of 46-108 mm.Conclusions A quantitative analysis of appropriate ecological environment of Himalayan marmot in a large scope is carried uul successfully using remote sensing and geographic information system.The study indicates that spatial information technology has important applications in plague prevention and control.

Objective To analyze the surveillance data on hemorrhagic fever with renal syndrome (HFRS) including the epidemiological characteristics and trend of the disease,in 2010.Methods Descriptive methods were conducted to analyze the surveillance data in 2010 which were collected from the internet-based National Notifiable Disease Reporting System and 40 HFRS sentinels in China.Results There were 9526 cases of HFRS reported in 2010 in the country with an annual morbidity of 0.71/105,which was higher than that reported in 2009.And the case fatality rate in 2010 was 1.24％.During the year 2010,most cases were reported in spring and autumn-winter season,with November as the peak month.The proportion of cases reported in autumn-winter season was higher than that in spring.The number of cases reported in males was higher than that in females among all the age groups,and similar pattern of mortality could be seen in most of the age groups.The percentage of cases over 60 years old had increased in recent years.Farmers were still under the highest risk.Density and the virus-carrying rate of animal hosts,as well as the infection rate were relatively stable and similar to the previous findings.As to the prevailing species,Apodemus agrarius and Rattus norvegicus were still the most common and leading animal hosts.However,the dominant species in sentinel of Yunnan were Rattus flavipectus and Eothenomys miletus respectively,and a new hantavirus called LUXV was found,namely Eothenomys miletus.Conclusion HFRS cases were widely distributed in most provinces of China,but cases mainly focus on certain areas and present the nature of aggregation.The risk of outbreak could not be ruled out for variety of factors.Population characteristics and seasonal fluctuation had been changing.

The efficacy of traditional Chinese medicine (TCM) treatments for Western medicine (WM) diseases relies heavily on the proper classification of patients into TCM syndrome types. The authors developed a data-driven method for solving the classification problem, where syndrome types were identified and quantified based on statistical patterns detected in unlabeled symptom survey data. The new method is a generalization of latent class analysis (LCA), which has been widely applied in WM research to solve a similar problem, i.e., to identify subtypes of a patient population in the absence of a gold standard. A well-known weakness of LCA is that it makes an unrealistically strong independence assumption. The authors relaxed the assumption by first detecting symptom co-occurrence patterns from survey data and used those statistical patterns instead of the symptoms as features for LCA. This new method consists of six steps: data collection, symptom co-occurrence pattern discovery, statistical pattern interpretation, syndrome identification, syndrome type identification and syndrome type classification. A software package called Lantern has been developed to support the application of the method. The method was illustrated using a data set on vascular mild cognitive impairment.
Data Collection ; Data Interpretation, Statistical ; Diagnosis, Differential ; Humans ; Medicine, Chinese Traditional

BACKGROUND: The current deep learning diagnosis of breast masses is mainly reflected by the diagnosis of benign and malignant lesions. In China, breast masses are divided into four categories according to the treatment method: inflammatory masses, adenosis, benign tumors, and malignant tumors. These categorizations are important for guiding clinical treatment. In this study, we aimed to develop a convolutional neural network (CNN) for classification of these four breast mass types using ultrasound (US) images. METHODS: Taking breast biopsy or pathological examinations as the reference standard, CNNs were used to establish models for the four-way classification of 3623 breast cancer patients from 13 centers. The patients were randomly divided into training and test groups (n = 1810 vs. n = 1813). Separate models were created for two-dimensional (2D) images only, 2D and color Doppler flow imaging (2D-CDFI), and 2D-CDFI and pulsed wave Doppler (2D-CDFI-PW) images. The performance of these three models was compared using sensitivity, specificity, area under receiver operating characteristic curve (AUC), positive (PPV) and negative predictive values (NPV), positive (LR+) and negative likelihood ratios (LR-), and the performance of the 2D model was further compared between masses of different sizes with above statistical indicators, between images from different hospitals with AUC, and with the performance of 37 radiologists. RESULTS: The accuracies of the 2D, 2D-CDFI, and 2D-CDFI-PW models on the test set were 87.9%, 89.2%, and 88.7%, respectively. The AUCs for classification of benign tumors, malignant tumors, inflammatory masses, and adenosis were 0.90, 0.91, 0.90, and 0.89, respectively (95% confidence intervals [CIs], 0.87-0.91, 0.89-0.92, 0.87-0.91, and 0.86-0.90). The 2D-CDFI model showed better accuracy (89.2%) on the test set than the 2D (87.9%) and 2D-CDFI-PW (88.7%) models. The 2D model showed accuracy of 81.7% on breast masses ≤1 cm and 82.3% on breast masses >1 cm; there was a significant difference between the two groups (P < 0.001). The accuracy of the CNN classifications for the test set (89.2%) was significantly higher than that of all the radiologists (30%). CONCLUSIONS: The CNN may have high accuracy for classification of US images of breast masses and perform significantly better than human radiologists. TRIAL REGISTRATION Chictr.org, ChiCTR1900021375; http://www.chictr.org.cn/showproj.aspx?proj=33139.
Area Under Curve ; Breast/diagnostic imaging* ; Breast Neoplasms/diagnostic imaging* ; China ; Deep Learning ; Humans ; ROC Curve ; Sensitivity and Specificity