ABSTRACT
OBJECTIVE@#By optimizing the extreme learning machine network with particle swarm optimization, we established a syndrome classification and prediction model for primary liver cancer (PLC), classified and predicted the syndrome diagnosis of medical record data for PLC and compared and analyzed the prediction results with different algorithms and the clinical diagnosis results. This paper provides modern technical support for clinical diagnosis and treatment, and improves the objectivity, accuracy and rigor of the classification of traditional Chinese medicine (TCM) syndromes.@*METHODS@#From three top-level TCM hospitals in Nanchang, 10,602 electronic medical records from patients with PLC were collected, dating from January 2009 to May 2020. We removed the electronic medical records of 542 cases of syndromes and adopted the cross-validation method in the remaining 10,060 electronic medical records, which were randomly divided into a training set and a test set. Based on fuzzy mathematics theory, we quantified the syndrome-related factors of TCM symptoms and signs, and information from the TCM four diagnostic methods. Next, using an extreme learning machine network with particle swarm optimization, we constructed a neural network syndrome classification and prediction model that used "TCM symptoms + signs + tongue diagnosis information + pulse diagnosis information" as input, and PLC syndrome as output. This approach was used to mine the nonlinear relationship between clinical data in electronic medical records and different syndrome types. The accuracy rate of classification was used to compare this model to other machine learning classification models.@*RESULTS@#The classification accuracy rate of the model developed here was 86.26%. The classification accuracy rates of models using support vector machine and Bayesian networks were 82.79% and 85.84%, respectively. The classification accuracy rates of the models for all syndromes in this paper were between 82.15% and 93.82%.@*CONCLUSION@#Compared with the case of data processed using traditional binary inputs, the experiment shows that the medical record data processed by fuzzy mathematics was more accurate, and closer to clinical findings. In addition, the model developed here was more refined, more accurate, and quicker than other classification models. This model provides reliable diagnosis for clinical treatment of PLC and a method to study of the rules of syndrome differentiation and treatment in TCM.
Subject(s)
Humans , Bayes Theorem , Liver Neoplasms/diagnosis , Machine Learning , Neural Networks, Computer , SyndromeABSTRACT
Based on the noninvasive detection indeices and fuzzy mathematics method, this paper studied the noninvasive, convenient and economical cardiovascular health assessment system. The health evaluation index of cardiovascular function was built based on the internationally recognized risk factors of cardiovascular disease and the noninvasive detection index. The weight of 12 indexes was completed by the analytic hierarchy process, and the consistency test was passed. The membership function, evaluation matrix and evaluation model were built by fuzzy mathematics. The introducted methods enhanced the scientificity of the evaluation system. Through the Kappa consistency test, McNemer statistical results ( = 0.995 > 0.05) and Kappa values (Kappa = 0.616, < 0.001) suggest that the comprehensive evaluation results of model in this paper are relatively consistent with the clinical, which is of certain scientific significance for the early detection of cardiovascular diseases.
Subject(s)
Humans , Cardiovascular Diseases , Diagnosis , Cardiovascular System , Fuzzy Logic , Models, Cardiovascular , ResearchABSTRACT
Targeting characteristic information processing of TCM pulse diagnosis, this article studied the application of fuzzy mathematics in objectifying pulse diagnosis. By analyzing limitations of traditional analytic methods, this article offered the scientific evidence of using mathematical algorithm in pulse diagnosis. At the same time, combined with actual clinical data, it also verified the correctness of introduction mathematical algorithm in TCM pulse diagnosis.
ABSTRACT
Objective: To study the optimal method for taste-modifying of Jinzhen Oral Liquid (JOL). Methods: Active carbon adsorption method was optimized through L9(34) orthogonal test and with the change rate of concentration of bilirubin as index, and the different taste-modifying prescriptions were evaluated by the fuzzy mathematics synthetic evaluation system. Results: The optimal adsorption conditions were as follows: The pH value of the mixture of Cornu Bubali and artificial Calculus ovis was adjusted to 7.0 at 50 °C with 0.25% activated carbon, and stirring for 10 min. The optimal formula ingredient was as follows: 15.0 mg ethyl maltol, 5.0 g CMC-Na, 1.0 g steviosin, and 0.5 g orange flavor in 1 000 mL JOL. Conclusion: The taste-modifying prescriptions provide great value for further scale production.
ABSTRACT
ObjectiveTo comprehensively evaluate the curative effect ofTCM reating type 2 diabetes with three type dialectical therapy by Fuzzy Mathematics.Methods261 cases of 2 type diabetes were divided into three groups by syndrome differentiation,as follows:type of heat with yin deficiency,type of deficiency of both qi and yin,and type of deficiency of both yin and yang,and received corresponding therapies.The course of treatment was 24 weeks,in the first 12 weeks (period 1),on the basis of western medicine treatment,patients of the three groups were respectively treated by qingrungranules,ziyigranule and shuangtiaogranules.In the next 12 weeks (period 2),all patients were only treated by western medicine.The value of FBG,P2BG,HbAlc,TC,TG,BMI of the two periods were comprehensively evaluated by the methods of fuzzy mathematics.ResultsAt the end of period 1,the total effective rate of the type of heat with yin deficiency was 91.38％,the type of deficiency of both qi and yin was 87.16％,and the type of deficiency of both yin and yang was 83.34％; while at the end of period 2,the total effective rate of the three types was 59.18％,48.65％a nd32.65％ respectively.ConclusionThe effective rate was obviously improved in period 1; while in period 2,the effective rate was decreased.
ABSTRACT
Evaluation of medical assistance capability plays a significant role in improving medical assistance capability and accomplishing a diverse array of military tasks.Based on gray theory and fuzzy mathematics,we put forward a new evaluation model for disaster medical assistance capability,integrating the AHP,the gray cluster analysis and fuzzy evaluation.This model not only reflects the ambiguity of medical assistance capability evaluation but also makes full use of the information,which avoids the flaws caused by single method of fuzzy mathematics.It provides a new way to evaluate disaster medical assistance capability comprehensively and systematically.
ABSTRACT
OBJECTIVE:To construct a fuzzy optimized model based on entropy weight and to discuss the application of the model on the risk management of new drug research&development project.METHODS:Risk management model of new drug research&development projects was established by combining fuzzy mathematics and entropy weight theory.RESULTS:The new drug research&development projects can be optimized and ranked based on the evaluation results on the model.CONCLUSION:The fuzzy optimized entropy weight model can be applied for the evaluation in the risk management of new drug research&development projects,which serves as scientific base for the administrative decision.