Optimization of ethanol extraction process for Yihuang powder by orthogonal experiment combined with AHP and GA-BP neural network / 中国药房

OBJECTIVE To optimize ethanol extraction process of Yihuang powder. METHODS An orthogonal experiment was designed by reflux extraction with ethanol volume fraction， liquid-to-material ratio， and extraction time as investigation factors. The parameters used were the contents of hesperidin， nobiletin， tangeretin， gallic acid， chebulagic acid， chebulinic acid， liquiritin， glycyrrhizin， eugenol， and the paste-forming rate. The analytic hierarchy process （AHP） was used to calculate the comprehensive score. The optimal ethanol extraction process parameters of Yihuang powder were determined by verifying the results predicted by orthogonal experiment and genetic algorithm （GA）-back propagation neural network （BP neural network）. RESULTS The optimal ethanol extraction process parameters， as optimized by orthogonal experiment， were as follows: ethanol volume fraction of 60%， liquid-solid ratio of 14∶1 （mL/g)， extraction time of 90 min， and extraction for 2 times. The comprehensive score obtained by verification was 79.19. Meanwhile， the optimal ethanol extraction process parameters， optimized by GA-BP neural network， were ethanol volume fraction of 65%， liquid-solid ratio of 14∶1 （mL/g )， extraction time of 60 min， and extraction for 2 times. The comprehensive score obtained by verification was 85.30， higher than the results obtained from orthogonal experiment. CONCLUSIONS The optimization method of orthogonal experiment combined with GA-BP neural network is superior to the traditional orthogonal experiment optimization method. The optimized ethanol extraction process of Yihuang powder is stable and reliable.

Optimization of water extraction technology of Xiangqin jiere granules by orthogonal design based on G1-entropy weight compared with BP neural network / 中国药房

OBJECTIVE Optimizing the water extraction technology of Xiangqin jiere granules. METHODS The orthogonal test of 3 factors and 3 levels was designed， and comprehensive scoring was conducted for the above indexes by using G1-entropy weight to obtain the optimized water extraction technology of Xiangqin jiere granules with water addition ratio， extraction time and extraction times as factors， using the contents of forsythoside A， baicalin， phillyrin， oroxylin A-7-O-β-D-glycoside， wogonoside， baicalein and wogonin， and extraction rate as evaluation indexes. BP neural network modeling was used to optimize the network model and water extraction process using the results of 9 groups of orthogonal tests as test and training data， the water addition multiple， decocting time and extraction times as input nodes， and the comprehensive score as output nodes. Then the two analysis methods were compared by verification test to find the best water extraction process parameters. RESULTS The water extraction technology optimized by the orthogonal test was 8-fold water， extracting 3 times， extracting for 1 h each time. Comprehensive score was 96.84 （RSD＝0.90%）. The optimal water extraction technology obtained by BP neural network modeling included 12-fold water， extracting 4 times， extracting for 0.5 h each time. The comprehensive score was 92.72 （RSD＝0.77%）， which was slightly lower than that of the orthogonal test. CONCLUSIONS The water extraction technology of Xiangqin jiere granules is optimized successfully in the study， which includes adding 8-fold water， extracting 3 times， and extracting for 1 hour each time.

An Atrial Fibrillation Classification Method Study Based on BP Neural Network and SVM / 中国医疗器械杂志

Atrial fibrillation is a common arrhythmia, and its diagnosis is interfered by many factors. In order to achieve applicability in diagnosis and improve the level of automatic analysis of atrial fibrillation to the level of experts, the automatic detection of atrial fibrillation is very important. This study proposes an automatic detection algorithm for atrial fibrillation based on BP neural network (back propagation network) and support vector machine (SVM). The electrocardiogram (ECG) segments in the MIT-BIH atrial fibrillation database are divided into 10, 32, 64, and 128 heartbeats, respectively, and the Lorentz value, Shannon entropy, K-S test value and exponential moving average value are calculated. These four characteristic parameters are used as the input of SVM and BP neural network for classification and testing, and the label given by experts in the MIT-BIH atrial fibrillation database is used as the reference output. Among them, the use of atrial fibrillation in the MIT-BIH database, the first 18 cases of data are used as the training set, and the last 7 cases of data are used as the test set. The results show that the accuracy rate of 92% is obtained in the classification of 10 heartbeats, and the accuracy rate of 98% is obtained in the latter three categories. The sensitivity and specificity are both above 97.7%, which has certain applicability. Further validation and improvement in clinical ECG data will be done in next study.

Prediction of CW chord after cataract surgery from IOL Master 700 measurement data based on SVR algorithm and BP neural network / 国际眼科杂志(Guoji Yanke Zazhi)

AIM: To observe the changes in the Chang-Warning chord(CW chord)before and after cataract surgery using the IOL Master 700 and predict the CW chord using an artificial intelligence prediction model and preoperative measurement data.METHODS: The analysis was conducted on the preoperative and postoperative IOL Master 700 measurements of 304 cataract patients. This included astigmatism vector value, average keratometry, axial length, anterior chamber depth, lens thickness, corneal central thickness, white-to-white, the position of the Purkinje reflex I image relative to the corneal center and pupil center, and the CW chord. A prediction model based on the SVR algorithm and the BP neural network algorithm was established to predict the postoperative CW chord using the preoperative CW chord and ocular biological parameters.RESULTS: The X component of the CW chord showed a slight shift in the temporal direction in both the left and right eyes after cataract surgery, while the Y component changed little. The SVR model, using the preoperative CW chord and other preoperative biometric parameters as input data, was able to predict the X and Y components of the CW chord more accurately than the BP neural network.CONCLUSION: The CW chord can be directly measured with a coaxial fixation light using various biometers, corneal topographers, or tomographers. The use of the SVR algorithm can accurately predict the postoperative CW chord before cataract surgery.

Research progress of taste masking and evaluation technology of medicine / 中国药科大学学报

@#Most drugs taste bitter and irritating, resulting in poor compliance of patients, and the bad odor affects the therapeutic effect. The successful research and development of a drug should not only conform to the five quality characteristics of effectiveness, stability, safety, uniformity and economy, but also the compliance of patients to drugs with bad odor. The development of taste masking techniques is critical for bitter drugs.This review describes the principles, advantages and drawbacks of traditional taste masking techniques, and introduces the mechanism and application of novel taste masking techniques, such as melt granulation, hot melt extrusion, 3D printing, drug complex preparation, and bitter taste inhibitors. The in vitro evaluation methods of drug taste masking effect, such as functional magnetic resonance imaging, in vitro dissolution, and electronic tongue technology, are described. And introduce in vivo evaluation methods, such as animal and human taste, in the field of taste masking effect. A new strategy of BP neural network prediction model for drug taste evaluation is proposed, with a view to providing theoretical reference for the future research on drug taste masking.

Risk predictive models of healthcare-seeking delay among imported malaria patients in Jiangsu Province based on the machine learning / 中国血吸虫病防治杂志

Objective To create risk predictive models of healthcare-seeking delay among imported malaria patients in Jiangsu Province based on machine learning algorithms, so as to provide insights into early identification of imported malaria cases in Jiangsu Province. Methods Case investigation, first symptoms and time of initial diagnosis of imported malaria patients in Jiangsu Province in 2019 were captured from Infectious Disease Report Information Management System and Parasitic Disease Prevention and Control Information Management System of Chinese Center for Disease Control and Prevention. The risk predictive models of healthcare-seeking delay among imported malaria patients were created with the back propagation (BP) neural network model, logistic regression model, random forest model and Bayesian model using thirteen factors as independent variables, including occupation, species of malaria parasite, main clinical manifestations, presence of complications, severity of disease, age, duration of residing abroad, frequency of malaria parasite infections abroad, incubation period, level of institution at initial diagnosis, country of origin, number of individuals travelling with patients and way to go abroad, and time of healthcare-seeking delay as a dependent variable. Logistic regression model was visualized using a nomogram, and the nomogram was evaluated using calibration curves. In addition, the efficiency of the four models for prediction of risk of healthcare-seeking delay among imported malaria patients was evaluated using the area under curve (AUC) of receiver operating characteristic curve (ROC). The importance of each characteristic was quantified and attributed by using SHAP to examine the positive and negative effects of the value of each characteristic on the predictive efficiency. Results A total of 244 imported malaria patients were enrolled, including 100 cases (40.98%) with the duration from onset of first symptoms to time of initial diagnosis that exceeded 24 hours. Logistic regression analysis identified a history of malaria parasite infection [odds ratio (OR) = 3.075, 95% confidential interval (CI): (1.597, 5.923)], long incubation period [OR = 1.010, 95% CI: (1.001, 1.018)] and seeking healthcare in provincial or municipal medical facilities [OR = 12.550, 95% CI: (1.158, 135.963)] as risk factors for delay in seeking healthcare among imported malaria cases. BP neural network modeling showed that duration of residing abroad, incubation period and age posed great impacts on delay in healthcare-seek among imported malaria patients. Random forest modeling showed that the top five factors with the greatest impact on healthcare-seeking delay included main clinical manifestations, the way to go abroad, incubation period, duration of residing abroad and age among imported malaria patients, and Bayesian modeling revealed that the top five factors affecting healthcare-seeking delay among imported malaria patients included level of institutions at initial diagnosis, age, country of origin, history of malaria parasite infection and individuals travelling with imported malaria patients. ROC curve analysis showed higher overall performance of the BP neural network model and the logistic regression model for prediction of the risk of healthcare-seeking delay among imported malaria patients (Z = 2.700 to 4.641, all P values < 0.01), with no statistically significant difference in the AUC among four models (Z = 1.209, P > 0.05). The sensitivity (71.00%) and Youden index (43.92%) of the logistic regression model was higher than those of the BP neural network (63.00% and 36.61%, respectively), and the specificity of the BP neural network model (73.61%) was higher than that of the logistic regression model (72.92%). Conclusions Imported malaria cases with long duration of residing abroad, a history of malaria parasite infection, long incubation period, advanced age and seeking healthcare in provincial or municipal medical institutions have a high likelihood of delay in healthcare-seeking in Jiangsu Province. The models created based on the logistic regression and BP neural network show a high efficiency for prediction of the risk of healthcare-seeking among imported malaria patients in Jiangsu Province, which may provide insights into health management of imported malaria patients.

Comparison of the predictive performance of Logistic regression, BP neural network and support vector machine model for the risk of acute exacerbation of readmission in elderly patients with chronic obstructive pulmonary disease within 30 days / 中华危重病急救医学

Objective:To compare the effectiveness of Logistic regression, BP neural network and support vector machine models in the prediction of 30-day risk of readmission in elderly patients with an exacerbation of chronic obstructive pulmonary disease (COPD) and to provide a scientific basis for the screening and prevention of high-risk patients with readmission.Methods:The COPD patient survey questionnaire was made, including the general data questionnaire, modified Medical Research Council dyspnea scale (mMRC), activities of daily living (ADL), the geriatric depression scale, the mini nutritional assessment-short form (MNA-SF) and COPD assessment test (CAT). Elderly COPD patients were selected from the department of respiratory medicine of 13 general hospitals in Ningxia from April 2019 to August 2020 by convenience sampling method, and they were followed up 30 days after discharge. To explore the risk factors of patient readmission, Logistic regression model, BP neural network model and support vector machine models were constructed based on the risk factors. According to the ratio of the training set to the testing set of 7∶3, the model was divided into the training set sample and the testing set sample. The prediction efficiency of the model was compared by the precision rate, recall rate and accuracy rate, F1 index and the area under the receiver operator characteristic curve (AUC).Results:A total of 1 120 patients were investigated, including 879 non-readmission patients and 241 readmission patients. Univariate regression analysis showed that there were statistically significant differences in age, education level, smoking status, proportion of diabetes and coronary heart disease, hospitalization times of acute exacerbation of COPD in the past 1 year, seasonal factors and long-term home oxygen therapy, regular medication, proportion of rehabilitation exercise, course of disease, ADL, depression status, mMRC, nutritional status between non-readmission patients and readmission patients. Binary Logistic regression analysis showed that education level, smoking status, coronary heart disease, hospitalization times of acute exacerbation of COPD in the past 1 year, seasonal factors, whether long-term home oxygen therapy, whether regular medication, nutritional status were the risk factors for 30-day acute exacerbation of readmission in elderly patients with COPD. The training set showed that the accuracy rate of Logistic regression model, BP neural network model and support vector machine models were 70.95%, 76.51% and 84.78%, respectively. The recall rates were 79.55%, 86.36% and 88.64%, respectively. The accuracy rates were 87.81%, 90.81% and 93.82%, respectively. F1 indexes were 0.75, 0.81 and 0.87, respectively. The AUC were 0.850, 0.893 and 0.921, respectively. The testing set showed that the precision rate of Logistic regression model, BP neural network model and support vector machine model were 78.38%, 80.65% and 88.57%, respectively. The recall rates were 70.73%, 60.98% and 75.61%, respectively. The accuracy rates were 85.82%, 84.40% and 90.07%, respectively. F1 indexes were 0.74, 0.69 and 0.82, respectively. The AUC were 0.814, 0.775 and 0.858, respectively.Conclusion:Comparing with Logistic regression and BP neural network, support vector machine model has better prediction effect, and can effectively predict the risk of acute exacerbation of readmission in elderly patients with COPD within 30 days.

Analysis of hospitalization cost and influencing factors of diabetic patients in rural areas of Hunan Province-- Take Wugang as an example / 公共卫生与预防医学

Objective To analyze the composition and influencing factors of hospitalization expenses for diabetic patients，and to provide reference for effective control of medical expenses. Methods The hospitalization cost data of diabetes patients in rural areas of Wugang from 2013 to 2017 were collected. Structural change analysis，non-parametric test and BP (Back Propagation)neural network model were used to analyze the hospitalization expenses and influencing factors. Results The top three components of hospitalization expenses were drug cost (50.02%), examination cost (15.35%) and laboratory cost (12.06%). The contribution rates of structural change of hospitalization expenses were the examination fee (41.00%), drug fee (34.92%) and treatment fee (13.41%), respectively. Factors affecting the total hospitalization cost of diabetic patients included length of stay, operation or not, hospital level, age, discharge year, complication or not and gender (P<0.05), among which length of stay had the greatest impact (sensitivity value was 0.669). Conclusion The hospitalization expenses of patients with diabetes is affected by a variety of factors. It is suggested to optimize the composition of hospitalization expenses by improving the price mechanism of medical services, and to control and reasonably reduce hospitalization expenses by implementing standardized management of clinical pathways, implementing two-way referral and strengthening tertiary prevention.

Identification of curcumin content in raw and vinegar-processed rhizomes of Curcuma kwangsiensis based on electronic nose combined with back propagation neural network / 中国中药杂志

This study aimed to establish a rapid and accurate method for identification of raw and vinegar-processed rhizomes of Curcuma kwangsiensis, in order to predict the content of curcumin compounds for scientific evaluation. A complete set of bionics recognition mode was adopted. The digital odor signal of raw and vinegar-processed rhizomes of Curcuma kwangsiensis were obtained by e-nose, and analyzed by back propagation(BP) neural network algorithm, with the accuracy, the sensitivity and specificity in discriminant model, correlation coefficient as well as the mean square error in regression model as the evaluation indexes. The experimental results showed that the three indexes of the e-nose signal discrimination model established by the neural network algorithm were 100% in training set, correction set and prediction set, which were obviously better than the traditional decision tree, naive bayes, support vector machine, K nearest neighbor and boost classification, and could accurately differentiate the raw and vinegar products. Correlation coefficient and mean square error of the regression model in prediction set were 0.974 8 and 0.117 5 respectively, and could well predict curcumin compounds content in Curcuma kwangsiensis, and demonstrate the superiority of the simulation biometrics model in the analysis of traditional Chinese medicine. By BP neural network algorithm, e-nose odor fingerprint could quickly, conveniently and accurately realize the discrimination and regression, which suggested that more bionics information acquisition and identification patterns could be combined in the field of traditional Chinese medicine, so as to provide ideas and methods for the rapid evaluation and stan-dardization of the quality of traditional Chinese medicine.

The classification model of type 2 diabetic peripheral neuropathy was studied based on GA-BP neural network model / 解放军医学杂志

Objective: To establish the genetic algorithm optimizing back-propagation (GA-BP) neural network model based on the clinical examination index for diagnosing type 2 diabetic peripheral neuropathy (DPN), and evaluate its diagnostic performance. Methods: A total of 2240 DPN patients and 2632 non-DPN patients were collected from the Hospital affiliated to Chongqing Medical University from January to December 2016, and univariate analysis was performed for 41 clinical test indicators of the two groups of patients with SPSS 21.0. Thirty-seven items of statistically significant variables were selected to establish the decision tree and Bayesian model with R software, MATLAB 2014a software was employed to establish the BP neural network and GA-BP neural network model, the advantages and disadvantages of these four models were compared with various evaluation parameters. Results: Using decision tree, the Bayesian, BP neural network and GA-BP neural network for 4872 cases of observation object model, the decision tree of The test sample accuracy with decision tree model was 93.4%, with Bayesian model was 70.0%, with BP neural network model was 98.9%, and with GA-BP neural network model was 99.5%. The areas under the ROC curve were 0.93, 0.72, 0.99 and 0.99, respectively. The Youden Indexes were 0.87, 0.59, 0.98 and 0.98, respectively. Conclusion: The GA-BP neural network established in present paper has a good computer-aided diagnosis function for type 2 diabetic peripheral neuropathy, but further clinical trials are still needed.

Researches on the illness risk of essential hypertension complicated with coronary heart disease based on machine learning algorithm / 解放军医学杂志

[Abstract] Objective To study a model of screening the risk factors of essential hypertension complicated with coronary heart disease and establishing the individual risk classification, and provide a computer-aided diagnostic methods for disease occurrence. Methods To collect 70 clinical information including 2791 patients with essential hypertension complicated with coronary heart disease and 2135 patients with simple essential hypertension diagnosed from January 1, 2014 to May 31, 2019 in Chongqing Medical University medical big data platform, screen out the indicators with statistical differences in single factor analysis. With R3.6.1 to construct logistic regression classification model and 3 machine learning models of BP neural network, random forest and extreme gradient rise (XGBoost), then compare the relevant parameters of various models and select the optimal classification model. Results According to the univariate analysis, 44 indexes with statistical difference were selected and included in logistic regression classification model and machine learning model. The classification accuracy in test set of logistic regression classification model, BP neural network model, random forest model, XGBoost model was 0.852, 0.968, 0.966 and 0.976, respectively, and the area under the work characteristic curve (AUC) of the subjects was 0.853, 0.970, 0.967 and 0.977, respectively. Applying XGBoost model with optimal performance to clinical practice of cardiology in the University Town Hospital of Chongqing Medical University. The diagnostic sensitivity was 1.000, specificity was 0.912, accuracy was 0.926, and AUC was 0.956. Conclusion Establishment of XGBoost model has a good auxiliary diagnostic function for essential hypertension complicated with coronary heart disease, and has achieved good results in clinical practice.

Quantitative study on medicinal properties of traditional Chinese medicine based on BP neural network / 中草药

Objective: It is difficult to accurately grasp the essential characteristics of medicinal properties of traditional Chinese medicine due to the abstraction and vagueness. This paper proposes a Quantitative Model of Traditional Chinese Medicine's Properties based on BP Neural Network (QM-BP Model) to train and realize quantitative representations of Chinese herbal medicine (CHM). Methods: Data for analysis were obtained and organized by conceptual analysis. Sample pairs of the associations were obtained based on the relationships of CHM and their efficacy. Then a QM-BP model with three-tier structure in form of CHM-drug vector-efficacy was constructed, initialized and trained according to prior organized CHM data. Finally, rules of correlation of CHM and their efficacy was obtained by training dataset with drug vectors representing quantitative attributes of CHM. Results: Based on the training of QM-BP model, 474 TCM and 528 effects included in the textbook of TCM were trained and combined based on the training of QM-BP model. It was found that the BP drug vectors representing drug properties after training reflected the attribute characteristics of CHM better than the initial quantitative values. In addition, as BP drug vector and word vector have similar properties, the BP drug vectors for CHM with similar efficacy was relatively close in Euclidean distance while the CHM with different efficacies were relatively far in Euclidean distance. Conclusion: In this paper, a BP neural network was adopted to construct a medicine vector training model. Based on the correlation between the medicinal properties and efficacy of TCM, the quantified values of the medicinal properties were modified to represent medicinal properties more accurately. In future work, the QM-BP model can be applied to the analysis of herb pairs and prescriptions to analyze the rules of combination related to medicinal properties and the compatibility within prescriptions.

Study on Risk Assessment Model of in Diagnostic Reagent Adverse Events Based on BP Neural Network / 中国医疗器械杂志

OBJECTIVE@#To modify the monitoring process and means of adverse events diagnostic reagents,improve the quantity and quality of adverse events reported ,and reduce the workload of regulatory authorities,eventually ensure the safety and effectiveness of diagnostic reagents.@*METHODS@#The pre-filtering risk assessment system based on BP neural network was used to evaluate the adverse events of diagnostic reagents.According to the evaluation results,the administrative supervision departments took corresponding countermeasures.@*RESULTS@#The BP neural network learned the historical data,and the risk evaluation results of the adverse events were basically consistent with the expert group.@*CONCLUSIONS@#BP neural network can be used to evaluate the risk of adverse events and achieve risk signal aggregation of adverse events.

Application of ARIMA model and BP neural network model in prediction of tuberculosis incidence in Gansu Province / 中华疾病控制杂志

Objective To investigate the predictive effect of autoregressive integrated moving average (ARIMA) model and back propagation neural network (BPNN)in the prediction of tuberculosis incidence in Gansu Province, and to select appropriate models to predict the incidence. Methods Based on the data of tuberculosis in Gansu Province from 1997 to 2017, the ARIMA time series model and BP neural network model were established to predict the incidence from 2018 to 2019, and the prediction accuracy and modeling effect of the two models were compared. Results For the incidence of tuberculosis in Gansu Province in 2018 and 2019, the ARIMA model predicted results were 55.1075, 54.5373, MSE=92.24, MAE=7.5313, MAPE=9.26%; BP neural network model predicted results were 62.0132, 73.4460, MSE= 9.6575, MAE = 1.1449, MAPE = 1.68%. Conclusions The BP neural network model has a better predictive effect on the incidence of tuberculosis in Gansu Province, and it shows that the incidence of tuberculosis in Gansu Province will increase slightly from 2018 to 2019.

Multi-index optimization of water extraction process of Siwu Decoction by BP neural network combined with entropy weight method / 中草药

Objective: To optimize the water extraction process of Siwu Decoction by BP neural network combined with orthogonal experiment. Methods: The water amount, the extraction time, and the extraction times were taken as factors. Entropy weight method was used to calculate the comprehensive scores of the multi-indicators of eight active components of 5-hydroxymethylfurfural, chlorogenic acid, caffeic acid, paeoniflorin, ferulic acid, verbascoside, senkyunolide A, and ligustilide in R language environment. Using comprehensive score as an evaluation indicator, the BP neural network model was established by orthogonal experiment design, and the optimal water extraction process of Siwu Decoction was predicted through network training. Results: The optimized extraction process of Siwu Decoction was carried out by adding 8 times of water and extracting 3 times for 1 h. The relative error between the network predicted value and the actual measured value of the test sample was less than 1%. Conclusion: The established mathematical model can analyze and predict the water extraction process of Siwu Decoction. The obtained process is stable and feasible, and can effectively extract the active ingredients in Siwu Decoction.

Optimization of water extraction technology of Yiqi Huoxue Prescription based on orthogonal test design and BP neural network / 中草药

Objective: To optimize the water extraction technology parameters of Yiqi Huoxue Prescription (YHP). Methods: On the basis of single factor experiment, orthogonal experiment design was used to evaluate the transfer rate and extraction yield of salvianolic acid B and hydroxysafflower yellow A by using adding water, extraction time and soaking time as factors. The comprehensive score was obtained by G1-entropy weight method. The optimal water extraction technology was obtained by orthogonal test design, and another method-BP neural network modeling was used to optimize the network model and target optimization. The two analytical methods were compared in the verification experiment to find the optimal water extraction technology parameters of YHP. Results: Based on the comparison of the two analytical methods, it was found that the comprehensive score of the optimal water extraction technology obtained by orthogonal test analysis was slightly higher than that obtained by BP neural network modeling. Therefore, it was finally determined that the optimal water extraction technology parameters of YHP were as follow: water extraction for three times, soaking for 0.5 h, adding water of 20 times, and extracting time for 3.5 h. Conclusion: The optimal water extraction technology of YHP is stable and feasible, which provides new ideas and references for the development and modernization of new drugs of compound Chinese medicine.

A comparison of ARIMA Model, BP Neural Network Model and combined model in health policy evaluation:An empirical study of public hospitals pricing reform / 中国卫生政策研究

Objective:To study the effectiveness of different time series models in the prediction of financial data in public hospitals,with the aim of obtaining a more reliable counterfactual in health policy evaluation. Methods:ARI-MA model,BP neural network and their combination were used for the estimation and prediction of drug revenue and medical service revenue based on a dataset for the period from November,2011 to October,2016 for hospital X before and after Nanjing medical pricing reform. Root mean square error (RMSE) was used to estimate the model accuracy. Results:RMSE of drug revenue from the three models were 692.82,501.44 and 380.80,and of medical service were 184.04,215.63 and 168.65. The findings shows that the combination model was proved to be the most efficient one a-mong the three. The combined model was used to calculate the net loss of drug revenue which was estimated to be 120, 440 million,and the net increase of medical service was estimated to be 185,326 million after the reform,which was 1. 539 times of the drug loss. Conclusions:The revenue data of public hospitals are usually complex with a both linear and non-linear trend. The combination model of ARIMA and BP neural network could solve the problem for once with an acceptable accuracy. However,ARIMA model is simpler to operate as compared to other two models, and also more consistent with the forecasting trend,therefore ARIMA is also recommended in the evaluation for health policies.

Study on Forecasting Ceramic Membrane Fouling in TCM Extracts Based on Improved BP Neural Network / 中国中医药信息杂志

Objective To prevent and treat of ceramic membrane purification of membrane fouling process of TCM extracts; To explore new methods of forecasting membrane fouling degree.Methods BP neural network model was improved. Methods to fast determine the optimal number of neurons in the hidden layer and fast algorithm for optimizing the weight and threshold of BP neural network were studied. Data of 207 groups of TCM extracts were under network training and prediction.ResultsCompared with the models of multiple regression analysis, basic BP neural network and RBF neural network, the error of the improved BP neural network model was less than that of the BP neural network model, and the mean square error was only 0.0057. In addition, the improved BP neural network model performance was more stable. In the 20 random running experiments, the goal of the success rate achieved up to 95%.Conclusion The improved model has a good network performance, the fitting effect and prediction ability, and can forecast the fouling degree of membrane stably and accurately.

Research on early-warning and evaluation of traditional Chinese medicine industry security based on BP neural network / 中草药

Through literature research, the safety evaluation index of traditional Chinese medicine (TCM) industry is identified, missing index value is calculated using the grey system theory, and the index weight is determined by the entropy weight method. The TCM industry safety from 2002 to 2014 was evaluated by grey relational analysis, and the TCM industry security evaluation index data from 2015 to 2020 are predicted using grey prediction and linear regression model method, combining the predicted value with historical data, TCM industry security BP neural network prediction model is established, and TCM industry security from 2015 to 2020 will be early warning. The results show that the next six years, TCM industry in China is safe, only mild prevention.

Cognitive map study of type 2 diabetic nephropathy based on BP neural network model / 中华内分泌代谢杂志

Objective A BP neural network model for diagnosing type 2 diabetic nephropathy based on laboratory tests was developed and evaluated. Methods Patients with type 2 diabetic nephropathy from 5 hospitals of Chongqing,Guizhou and Sichuan Provinces from January 2016 to December 2016 were collected in the study. Totally 89 parameters were analyzed by univariate analysis to identify significant variables by SPSS 19. 0 and MATLAB 2014a. The diagnostic performance of the two methods were compared. Results A total of 477 patients with type 2 diabetic nephropathy and 449 patients of control group were included. Univariate analysis showed that 42 variables had significant difference. Logistic regression analysis showed that 12 variables were included in the optimal regression equation. This BP neural network had 42 input layer nodes,15 hidden layer nodes and 1 output layer nodes. The Youden index of logistic regression analysis and BP neural network(training set and test set) were 0.76,0.89 and 0.83. The accurately diagnosed were 88.12%,94.24%,and 91.34%,the AUC were 0.95,0.98,and 0.96. Conclusion A BP neural network model was developed,which has important accessory diagnostic value for diagnosis of type 2 diabetic nephropathy. But all these conclusions need further validation in clinic.