BackgroundHospitalization expenditure of genitourinary system diseases among the aged is often overlooked. The aim of our research is to analyze the basic situation and influencing factors of hospitalization expenditure of the genitourinary system diseases and provide better data for the health system.MethodsA total of 1 377 681 patients aged 65 years and over were collected with multistage stratified cluster random sampling in 252 medical institutions in Liaoning China, and “System of Health Account 2011” (SHA2011) was conducted to analyze the expenditure of the diseases. The corresponding samples were extracted, the neural network model was utilized to fit the regression model of the diseases among the aged, and sensitivity analysis was used to rank the influencing factors.ResultsTotal hospitalization expenditure in Liaoning was 51.286 billion yuan, and curative care expenditure of diseases of the genitourinary system was 3.350 billion yuan, accounting for 6.53%. In the neural network model, the training set of R2 was 0.71. The test set of R2 was 0.74. In the sensitivity analysis, top-three influencing factors were the length of stay, type of institutions and type of insurances; the weight was 0.28, 0.19 and 0.14, respectively.ConclusionsThis research used SHA2011 to grab a large amount of data and analyzed them depending upon the corresponding dimensions. The neural network can analyze the influencing factors of hospitalization expenditure of genitourinary diseases in elderly patients accurately and directly, and can clearly describe the extent of its impact by combining sensitivity analysis.

The occlusion in traffic scenarios have posed great challenges in vehicle tracking. Establishing effective and robust vehicle tracking algorithms under occlusion conditions is a necessary issue for many traffic applications. This paper presents a novel approach of vehicle tracking by fusing the prior information of Kalman filter. The prior information of Kalman filter is used for background update, precise morphological operation and occlusion judgment. The fusion of observation and prior information is adopted to segment vehicles under occlusion. It effectively improves the robustness of the vehicle tracking algorithm in the case of occlusion. A novel vehicle description method is proposed to express vehicle shape more accurately and thus reduces the misjudgement of occlusion. Experiments show that the proposed algorithm can accurately track vehicles even under occlusion.

Background To develop the diagnostic criteria of childhood hypertension for different sex, age, and height in Haikou City and compare them with the national standard. Methods Stratified random cluster sampling method was used to sample 11,497 students from 227 classes of 29 primary and secondary schools at Haikou. Their height, weight, and blood pressure (BP) were measured during October 2013 to December 2014. The BP values were obtained with method of Korotkoff mercury sphygmomanometer by the trained examiners. Non-Haikou students and abnormal discrete samples were excluded. A total of 9,100 students of normal weight and height, aged 6–15 years, were enrolled. The sex-, age-, and height-specific BP percentile of 90%, 95%, and 99% (P90, P95, and P99) were calculated. Results The sex-, age-, and height-specific BP cutoff values of prehypertension (P90), grade 1 hypertension (P95), and grade 2 hypertension (P99) of children aged 6–15 years were developed. Compared with the 2017 national reference (“reference 2017”), the following characteristics were observed. The average height and height range of the same percentile in children at Haikou were lower. The P90 and P95 of systolic BP in Haikou were similar in most age groups of both sexes, but 4–5 mm Hg lower in 15-year-old males. Likewise, the P99 of systolic BP in Haikou was 1–8 mm Hg higher, except for 15-year-old males, which was 2 mm Hg lower. The difference of P90, P95, and P99 of diastolic BP between Haikou and “reference 2017” ranged from −1 to 5 mm Hg. Conclusions Hypertension of children aged 6–15 years in Haikou has its own characteristics and is different from the “reference 2017.”