ABSTRACT
BACKGROUND@#This study aimed to analyse the epidemiological characteristics of bacillary dysentery (BD) caused by Shigella in Chongqing, China, and to establish incidence prediction models based on the correlation between meteorological factors and BD, thus providing a scientific basis for the prevention and control of BD.@*METHODS@#In this study, descriptive methods were employed to investigate the epidemiological distribution of BD. The Boruta algorithm was used to estimate the correlation between meteorological factors and BD incidence. The genetic algorithm (GA) combined with support vector regression (SVR) was used to establish the prediction models for BD incidence.@*RESULTS@#In total, 68,855 cases of BD were included. The incidence declined from 36.312/100,000 to 23.613/100,000, with an obvious seasonal peak from May to October. Males were more predisposed to the infection than females (the ratio was 1.118:1). Children < 5 years old comprised the highest incidence (295.892/100,000) among all age categories, and pre-education children comprised the highest proportion (34,658 cases, 50.335%) among all occupational categories. Eight important meteorological factors, including the highest temperature, average temperature, average air pressure, precipitation and sunshine, were correlated with the monthly incidence of BD. The obtained mean absolute percent error (MAPE), mean squared error (MSE) and squared correlation coefficient (R) of GA_SVR_MONTH values were 0.087, 0.101 and 0.922, respectively.@*CONCLUSION@#From 2009 to 2016, BD incidence in Chongqing was still high, especially in the main urban areas and among the male and pre-education children populations. Eight meteorological factors, including temperature, air pressure, precipitation and sunshine, were the most important correlative feature sets of BD incidence. Moreover, BD incidence prediction models based on meteorological factors had better prediction accuracies. The findings in this study could provide a panorama of BD in Chongqing and offer a useful approach for predicting the incidence of infectious disease. Furthermore, this information could be used to improve current interventions and public health planning.
ABSTRACT
Objective To evaluate the dosimetric differences of one RapidPlan Model on different Radiotherapy devices.Methods A RapidPlan Model was built based on 30 reoptimization IMRT plans of cervical cancer patients on typeA LA.Dosimetric differences of automatic optimized IMRT plans using this model on 4 different type LAs,named respectivelyA,B,C andD,were compared with 12 test cervical cancer cases.These four LAs were well commissioned in the treatment planning system (TPS).Student t test was applied for statistical analysis on dosimetric differences.Results Dosimetric differences between A vs.B,C and D were observed on Dmean,HI,CI of PTV50 and PTV45,as well as on V50,V40,V30 of rectum and bladder.Significant dosimetric differences were observed between A and D (P<0.05).Conclusions Automatic planning with RapidPlan model may result in dosimetric differences on different Radiotherapy devices.These differences should be aware of with caution in its clinical application.
ABSTRACT
To facilitate noninvasive diagnosis of anemia, high-performance and portable near infrared (NIR) spectrometer for human blood constituents was designed and fabricated based on linear variable filter (LVF).Meanwhile, the performance of support vector regression (SVR) model for quantitative analysis of human hemoglobin (Hb) was investigated.Spectral data were collected noninvasively from 100 volunteers by self-designed LVF-NIR spectrometer, then divided into calibration set, validation set 1 and 2.To establish a robust SVR model, grid search method was applied to optimize the penalty parameter and kernel function parameter c=5.28, g=0.33.Then, Hb levels in the validation 1 and 2 sets were quantitatively analyzed.The results showed that the root mean square error of prediction (RMSEP) were 10.20 g/L and 10.85 g/L, respectively, and the relative RMSEP (R-RMSEP) were 6.85% and 7.48%, respectively.The results indicated that the SVR model had high prediction accuracy to Hb level and adaptability to different samples, and could satisfy the requirements of clinical measurement.Based on the SVR algorithm, the self-designed LVF-NIR spectrometer has a wide application prospect in the field of non-invasive anemia diagnosis.
ABSTRACT
Objective To investigate the predictive value of dose?volume histograms ( DVHs ) of organs at risk ( OARs ) including the bladder, rectum, and small intestine in volumetric modulated arc therapy ( VMAT) plans for cervical cancer. Methods A total of 100 VMAT plans for cervical cancer were assigned into the learning group. The correlation of the anatomical information with the V30 , V40 , and V50 values of the bladder, rectum, and small intestine was evaluated in the group. The support vector regression ( SVR) algorithm was used to establish the correspondence between the anatomical information and the DVHs of OARs. The DVHs of OARs in the verification group containing 20 VMAT plans were predicted based on the anatomical information. Results The DVHs of the bladder, rectum, and small intestine were likely to be influenced mainly by the spatial relationship between these OARs and target volume. In the verification group, the prediction errors of V30,V40 and V50 by SVR algorithm were-2.4%±3. 5%,-2.5%±3. 8%, and-1.5%±4. 9% for the bladder, 0.5%±2. 6%,-1.5%±5. 1%, and-2.0%±7. 4% for the rectum, and-2.9%± 5. 3%, 2.7%±7. 7%, and 5.3%±11. 1% for the small intestine, respectively. Conclusions After learning the correlation between the anatomical information and the DVHs of OARs from prior VMAT plans for cervical cancer, SVR algorithm can precisely predict the DVHs of the bladder, rectum, and small intestine based on the anatomical information.
ABSTRACT
Inhibition of cytochrome P450 (CYP450) enzymes is the most common reasons for drug interactions, so the study on early prediction of CYPs inhibitors can help to decrease the incidence of adverse reactions caused by drug interactions.CYP450 2E1(CYP2E1), as a key role in drug metabolism process, has broad spectrum of drug metabolism substrate. In this study, 32 CYP2E1 inhibitors were collected for the construction of support vector regression (SVR) model. The test set data were used to verify CYP2E1 quantitative models and obtain the optimal prediction model of CYP2E1 inhibitor. Meanwhile, one molecular docking program, CDOCKER, was utilized to analyze the interaction pattern between positive compounds and active pocket to establish the optimal screening model of CYP2E1 inhibitors.SVR model and molecular docking prediction model were combined to screen traditional Chinese medicine database (TCMD), which could improve the calculation efficiency and prediction accuracy. 6 376 traditional Chinese medicine (TCM) compounds predicted by SVR model were obtained, and in further verification by using molecular docking model, 247 TCM compounds with potential inhibitory activities against CYP2E1 were finally retained. Some of them have been verified by experiments. The results demonstrated that this study could provide guidance for the virtual screening of CYP450 inhibitors and the prediction of CYPs-mediated DDIs, and also provide references for clinical rational drug use.
ABSTRACT
It has been reported that hyperspectral data could be employed to qualitatively elucidate the spatial composition of tablets of Chinese medicinal plants. To gain more insights into this technology, a quantitative profile provided by near infrared (NIR) spectromicroscopy was further studied by determining the glycyrrhizic acid content in licorice, Glycyrrhiza uralensis. Thirty-nine samples from twenty-four different origins were analyzed using NIR spectromicroscopy. Partial least squares, interval partial least square (iPLS), and least squares support vector regression (LS-SVR) methods were used to develop linear and non-linear calibration models, with optimal calibration parameters (number of interval numbers, kernel parameter, etc.) being explored. The root mean square error of prediction (RMSEP) and the coefficient of determination (R(2)) of the iPLS model were 0.717 7% and 0.936 1 in the prediction set, respectively. The RMSEP and R(2) of LS-SVR model were 0.515 5% and 0.951 4 in the prediction set, respectively. These results demonstrated that the glycyrrhizic acid content in licorice could barely be analyzed by NIR spectromicroscopy, suggesting that good quality quantitative data are difficult to obtain from microscopic NIR spectra for complicated Chinese medicinal plant materials.
Subject(s)
Calibration , Drugs, Chinese Herbal , Chemistry , Glycyrrhiza , Chemistry , Glycyrrhizic Acid , Least-Squares Analysis , Microscopy , Methods , Spectroscopy, Near-Infrared , MethodsABSTRACT
Near infrared spectroscopy ( NIRS) is capable of determining water contents in oils. However, too much moisture contents in the oils will scatter rather than absorb the NIRS. This may cause greater measurement error. For this reason, a nonionic surfactant (Span-80) was screened to make the water in the oils evenly dispersed into small droplets. The NIRS analysis was subsequently employed to build support vector regression ( SVR ) model of the water content. In this experiments, the upper limit of the water content determination was improved from the conventional 0. 1% to 1. 0% ( V/V) by the oil-water stabilization. Applying successive projection algorithm, 15 valid variables (2. 9% of the original ones) from 511 NIRS variables were selected. With the proposed SVR model, the measurement precision criteria for the validation dataset were root mean squares error percentage 2 . 93%, correlation coefficient 0 . 9944 , and relative percent derivation 9 . 4732%.
ABSTRACT
OBJECTIVES: Congenital muscular torticollis, a common disorder that refers to the shortening of the sternocleidomastoid in infants, is sensitive to correction through physical therapy when treated early. If physical therapy is unsuccessful, surgery is required. In this study, we developed a support vector regression model for congenital muscular torticollis to investigate the prognosis of the physical therapy treatent in infants. METHODS: Fifty-nine infants with congenital muscular torticollis received physical therapy until the degree of neck tilt was less than 5degrees. After treatment, the mass diameter was reevaluated. Based on the data, a support vector regression model was applied to predict the prognoses. RESULTS: 10-, 20-, and 50-fold cross-tabulation analyses for the proposed model were conducted based on support vector regression and conventional multi-regression method based on least squares. The proposed methodbased on support vector regression was robust and enabled the effective analysis of even a small amount of data containing outliers. CONCLUSIONS: The developed support vector regression model is an effective prognostic tool for infants with congenital muscular torticollis who receive physical therapy.