Application of an extreme learning machine network with particle swarm optimization in syndrome classification of primary liver cancer / 中西医结合学报

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.

Meta-analysis of Oral Chinese Medicine for Adjuvant Treatment of Primary Hepatic Carcinoma and Screening of Basic Chinese Herbs / 中国实验方剂学杂志

Objective:To systematically evaluate the efficacy of oral Chinese herbal prescriptions combined with transcatheter arterial chemoembolization （TACE） against primary hepatic carcinoma （PHC） and screen the basic Chinese herbs，in order to provide certain reference for clinical medication. Method:The randomized controlled trials concerning the treatment of PHC with oral Chinese herbal prescriptions plus TACE were retrieved from CBM，China National Knowledge Infrastructure （CNKI），Chongqing Weipu Database for Chinese Technical Periodicals （VIP），and Wanfang Data Knowledge Service Platform.The quality of the included trials was evaluated by Cochrane handbook，and the Meta-analysis was performed using RevMan 5.3.The enumeration data were expressed by odds ratio （OR），the measurement data by mean difference （MD） or standardized mean difference （SMD），and the effect size by 95% confidence interval （CI）.The data of oral Chinese herbal prescriptions involved in trials were sorted out and subjected to association rule analysis and frequency analysis based on the Traditional Chinese Medicine Inheritance Support System （TCMISS），for exploring the basic Chinese herbs and their dosages against PHC. Result:A total of 75 randomized controlled trials were included，involving 7 406 cases. As revealed by the Meta-analysis，oral Chinese herbal prescriptions combined with TACE was significantly better than TACE alone in improving the short-term curative effect ［OR=2.05，95%CI（1.83，2.29）］，decreasing alpha fetoprotein （AFP） ［MD=-59.02，95%CI（-79.03，-39.01）］，ameliorating liver function ［SMD=-1.23，95%CI（-1.58，-0.88）］，boosting immunity ［SMD=1.08，95%CI（0.84，1.32）］，adjusting Karnofsky Performance Status （KPS） scale score ［OR=2.7，95%CI（1.11，11.02）］，elevating survival rate ［OR=2.31，95%CI（1.96，2.71）］，and reducing adverse reactions ［OR=0.38，95%CI（0.34，0.43）］.Data mining results showed that the basic Chinese herbs against PHC were Bupleuri Radix，Paeoniae Alba Radix，Atractylodis Macrocephalae Rhizoma，Poria，and Glycyrrhizae Radix et Rhizoma，with their clinical dosages listed as follows：6-15 g for Bupleuri Radix，10-15 g for Paeoniae Alba Radix，9-15 g for Atractylodis Macrocephalae Rhizoma，10-15 g for Poria，and 3-10 g for Glycyrrhizae Radix et Rhizoma. Conclusion:The oral Chinese herbal prescriptions combined with TACE produce better effects in treatment of PHC as compared with TACE alone.These five basic Chinese herbs have anti-cancer effect，and their dosages are within the ranges stipulated in 2020 edition of <italic>Chinese Pharmacopoeia.</italic>This Meta-analysis has provided certain reference for clinical medication.

Application and progress of data mining in study of compatibility law of traditional Chinese medicine / 中国中药杂志

Data mining is an important method to obtain the key information from a large amount of data, and it is widely applied in the research on the modernization of traditional Chinese medicine(TCM). The compatibility law of herbs is a key issue in the research of TCM prescriptions. This reflects the flexibility and effectiveness of TCM prescriptions, and it is also a crucial link to the development of TCM modernization. Therefore, it is the core purpose of the research on TCM prescriptions to find the compatibility law of herbs and clarify the scientific connotation. Data mining, as an effective method and an important approach, has formed a standardized system in the research of compatibility law of herbs, which can reveal the relationship between different Chinese herbs and summarize the internal rules in compatibility. Two hundred and twenty two effective papers were sorted out and categorized in this article. The results showed that data mining was mainly applied in finding the core Chinese herb pairs, summarizing the utility and attributes of TCM prescriptions, revealing the relationship between prescriptions, Chinese herbs and syndromes, finding the optimal dose of Chinese herbs, and producing the new prescriptions. The problems of data mining in research of herbs compatibility rules were summarized, and its development and trend in current researches were discussed in this article to provide useful references for the in-depth study of data mining in the compatibility law of Chinese herbs.