ABSTRACT
Objective To explore the application of support vector regression (SVR) model combined with meteorological and air pollutants index in the prediction of the cases of bacillary dysentery in Lanzhou City, so as to provide scientific reference for the prevention and control of bacillary dysentery.Methods Time series data of the reported cases of bacillary dysentery from December 2013 to August 2016, combined with the meteorological and air pollutants data, were used as training set to fit support vector regression model. The data from September 2016 to December 2017 was used as validation set to verify the model and compare the effect in fit and prediction with different models. Results A total of 7 192 bacillary dysentery cases were reported in Lanzhou City from 2013 to 2017. The correlation coefficient of meteorological and pollution factors with the cases of bacillary dysentery was more than 0.4, except air pressure. The parameters of the fit model were selected based on the integrated data, acquiring the three parameters with the smallest test error were C=5, γ=0.02 and ε=0.000 1, respectively. The validation set was used to test the different models, which showed that the integrated data model had the best predictive accuracy and robustness . The root mean squared error (RMSE) was 0.164 7 and the mean absolute percentage error (MAPE) was 16.405%. Conclusion SVR model combined with meteorological and air pollutants index is effective in the prediction of bacterial dysentery.
ABSTRACT
BACKGROUND: Although more and more accurate and personalized detection and assistive tools are used in the field of orthopedics with the development of technology, the preoperative CT is still the first-line examination choice of many orthopedic surgeons. Therefore, to master the lumbar spine CT imaging performance is not only the basis of spine surgeons, but also the cornerstone of spinal nail surgery. OBJECTIVE: Through CT imaging technique, we measured the parameters of lumbar pedicle imaging, and understood its internal structure as the basis for the choice of screws, in order to improve the safety and accuracy of nail surgery. METHODS: Totally 36 cases without lumbar vertebrae-related disease undergoing lumbar vertebra and abdominal cavity CT scan were randomly selected, including 20 males and 16 females at the age of (43.3±12.3) years. PACS was used to reconstruct lumbar vertebrae, and the related imaging parameters were measured. RESULTS AND CONCLUSION: (1) There was no significant difference between the left and right sides of the pedicle for paired t-test (P >0.05). (2) Pedicle sagittal angle had downward trend, the level of change was small; L4increased relative to L3; L5level was minimum at the average of -1.3°. Pedicle transverse angle had gradually increased trend, and maximum at L5; the average was 25.4°. (3) The length of the pedicle channel increased first and then decreased in the lumbar segment; the longest average was 52.2 mm in the L2segment, the shortest at L5, with an average of 47.4 mm. (4) The pedicle height was slightly narrowed at L1-L3levels; the smallest was 15.4 mm (L3mean), and reached the maximum in the L5at 22.7 mm (L5mean). Cancellous bone height also showed the same trend, the minimum in the L3at 10.2 mm, the maximum in the L5at 17.9 mm. (5) Lumbar pedicle width showed an upward trend, L1minimum of 7.7 mm, L5maximum of 12.5 mm. Cancellous bone width also became a similar upward trend; the narrowest L1, averagely 4.9 mm; the maximum L5, averagely 8.5 mm. (6) Overall, the upper lumbar pedicle channel was slender, while the lower lumbar spine was slightly short. (7) The parameters of the pedicle can be used as the basis for selecting the appropriate screw. At the same time, lumbar pedicle morphology has a certain difference, and there is a certain law. Accurately grasping its structure and image characteristics of pedicle screw fixation is the basis of surgery. The preoperative imaging data collection and assessment, combined with the general situation of patients, and the development of personalized programming, will help in improving the safety and accuracy of screw placement.