Application of least square support vector machine algorithm in clinical pulse diagram parameter-blood pressure prediction model of traditional Chinese medicine / 第二军医大学学报

Objective To propose a learning model based on least square support vector machine (LSSVM) algorithm to improve the accuracy and efficiency for predicting clinical blood pressure data of traditional Chinese medicine (TCM). Methods The LSSVM learning model was used to predict the clinical blood pressure of TCM. By replacing the inequality constraints of support vector machine with LSSVM equality constraints, the quadratic programming problem was transformed into a linear equation solution problem to reduce computational complexity and speed up algorithm convergence. The clinical pulse diagram parameters and blood pressure data of 320 patients were collected. Three hundred of them were used as training samples, the remaining 20 samples were used as test data. The LSSVM learning model was used to predict blood pressure data according to the pulse diagram parameters of the patients. Results Experimental results showed that the LSSVM learning model had high prediction accuracy for blood pressure data. The LSSVM learning model based on polynomial kernel function had better learning and prediction abilities than the LSSVM learning model based on radial basis kernel function. The mean prediction errors of systolic blood pressure, diastolic blood pressure and mean arterial pressure obtained by the LSSVM learning model based on polynomial kernel function were 7.88%, 8.40% and 6.67%, respectively, which were lower than those obtained by the LSSVM learning model based on radial basis kernel function (7.95%, 9.70% and 7.48%, respectively). Conclusion The LSSVM learning model proposed in this experiment can be used to predict the blood pressure data of patients only by the clinical pulse diagram parameters, and is a good reference for clinical diagnosis of TCM.

Clustering of Rotavirus Based on KNN-kernel Function / 浙江中医药大学学报

Objective] To discuss application of KNN-kernel clustering methods for diarrhea patients serum immune indexes detection data classification and diagnosis of applicability and clinical significance. [Methods] To reveal the applicability and clinical signnificance of KNN-kernel function clustering method in the diagnosis of serun immune index. In this research, the KNNCLUST algorithm is used to program the serum immune index data of 74 patients with diarrhea by Matlab software. [Results] 74 patients were divided into 5 categories by cluster analysis. The patients with diarrhea were divided into rotavirus negative and positive class, and the patients were further subdivided, especially the three early rotavirus tests were negative but later confirmed positive and were clustered into one group. [Conclusions] This can be seen that the KNN-kernel clustering method is helpful for early screening of rotavirus infection, practical clinical significance on the early treatment of disease.

Application of gene-based logistic kernel-machine regression model on studies related to the genome-wide association / 中华流行病学杂志

[Introduction] To explore the gene-based logistic kemel-machine regression model and its application in genome-wide association study (GWAS).Using the simulated genome-wide singlenucleotide polymorphism (SNPs) genotypes data,we proposed a practical statistical analysis strategynamed ‘ the logistic kernel-machine regression model',based on the gene levels to assess the association between genetic variations and complex diseases.The results from simulation showed that the P value of genes in related diseases was the smallest among all the genes.The results of simulation indicated that not only it could borrow information from different SNPs that were grouped in genes and reducing the degree of freedom through hypothesis testing,but could also incorporate the covariate effects and the complex SNPs interactions.The gene-based logistic kernel-machine regression model seemed to have certain statistical power for testing the association between genetic genes and diseases in GWAS.

Three-dimensional dose rate table for 103pd radioactive stent / 中华放射肿瘤学杂志

Objective To investigate three-dimensional dose distribution for 103Pd radioactive stent.Methods The surface dose,the axial dose and radial dose in surface for 103pd stent (3 mm × 13 mm) were estimated by experimental simulating method, analytic function and MCNP4b code. Three-dimensional dose distribution was calculated by MCNP4b code. Results The surface dose of 103pd stent was 0. 109 and 0. 106 Gy estimated by experimental simulating method and MCNP4b code,between which the difference was less than 3%. The axial dose calculated by analytic function and MCNP4b code was well consistent,and so was the radial dose estimated by the three methods. Dose rate table were estimated by MCNP4b code. Conclnsions Dose distribution for 103 Pd stent estimated by the three methods is relatively accurate. Three-dimensional dose table estimated by MCNP4b may be used to calculate dose for 103Pd stent in animal experiment and clinical application.

Estimation of Occurrence Peaks of Adverse Events Using Hazard Functions / 薬剤疫学

Objective : The incidence rate is used frequently in drug safety assessment. The incidence rate of adverse events is defined as the number of patients experiencing a certain adverse event divided by the number of patients administered a drug in spite of duration of administration (observation). In post-marketing surveillance, the duration of administration (observation) typically differs by patient and most of the analyses fail to take into account the differences in duration of administration (observation). Therefore, we investigated the usefulness of hazard functions in a drug safety assessment using the interim results from Clinical Experience Investigation of the oral anticancer drug, TS-1.<BR>Methods : About three thousand patients with gastric cancer were enrolled in this Clinical Experience Investigation. TS-1 was administrated orally twice daily. One course consisted of consecutive administration for 28 days and 14 days rest. Administration was repeated in two courses. Hematological measurements, stomatitis, anorexia, nausea/vomiting, diarrhea, malaise were analyzed. Adverse events were evaluated in accordance with the criteria of the Japan Society for Cancer Therapy, which were established based on criteria established by the WHO. Time to occurrence of an adverse event was calculated from the first day of administration until the adverse event was first observed. Hazard functions were estimated by smoothing methods using kernel functions.<BR>Results : The occurrence of adverse events using smoothed hazard functions had one peak around 10 days in the first course and decreased by administration rest. With the resumption of administration, the occurrence increased again. The occurrence in the second course were less than that of the first course.<BR>Conclusion : The occurrence peaks of adverse events were estimated graphically by smoothed hazard functions. We conclude that hazard functions are useful as an analytical tool in drug safety assessment.