An interpretability model for syndrome differentiation of HBV-ACLF in traditional Chinese medicine using small-sample imbalanced data

Objective Clinical medical record data associated with hepatitis B-related acute-on-chronic liver failure(HBV-ACLF)generally have small sample sizes and a class imbalance.However,most machine learning models are designed based on balanced data and lack interpretability.This study aimed to propose a traditional Chinese medicine(TCM)diagnostic model for HBV-ACLF based on the TCM syndrome differentiation and treatment theory,which is clinically interpretable and highly accurate.Methods We collected medical records from 261 patients diagnosed with HBV-ACLF,including three syndromes:Yang jaundice(214 cases),Yang-Yin jaundice(41 cases),and Yin jaundice(6 cases).To avoid overfitting of the machine learning model,we excluded the cases of Yin jaundice.After data standardization and cleaning,we obtained 255 relevant medical records of Yang jaundice and Yang-Yin jaundice.To address the class imbalance issue,we employed the oversampling method and five machine learning methods,including logistic regression(LR),support vector machine(SVM),decision tree(DT),random forest(RF),and extreme gradient boosting(XGBoost)to construct the syndrome diagnosis models.This study used precision,F1 score,the area under the receiver operating characteristic(ROC)curve(AUC),and accuracy as model evaluation metrics.The model with the best classification performance was selected to extract the diagnostic rule,and its clinical significance was thoroughly analyzed.Furthermore,we proposed a novel multiple-round stable rule extraction(MRSRE)method to obtain a stable rule set of features that can exhibit the model’s clinical interpretability.Results The precision of the five machine learning models built using oversampled balanced data exceeded 0.90.Among these models,the accuracy of RF classification of syndrome types was 0.92,and the mean F1 scores of the two categories of Yang jaundice and Yang-Yin jaundice were 0.93 and 0.94,respectively.Additionally,the AUC was 0.98.The extraction rules of the RF syndrome differentiation model based on the MRSRE method revealed that the common features of Yang jaundice and Yang-Yin jaundice were wiry pulse,yellowing of the urine,skin,and eyes,normal tongue body,healthy sublingual vessel,nausea,oil loathing,and poor appetite.The main features of Yang jaundice were a red tongue body and thickened sublingual vessels,whereas those of Yang-Yin jaundice were a dark tongue body,pale white tongue body,white tongue coating,lack of strength,slippery pulse,light red tongue body,slimy tongue coating,and abdominal distension.This is aligned with the classifications made by TCM experts based on TCM syndrome differentiation and treatment theory.Conclusion Our model can be utilized for differentiating HBV-ACLF syndromes,which has the potential to be applied to generate other clinically interpretable models with high accuracy on clinical data characterized by small sample sizes and a class imbalance.

Study on prescription medication mode and mechanism of traditional Chinese medicine in the treatment of noncritical COVID-19 based on data mining

Background:As of 2023,coronavirus disease 2019(COVID-19)is still spreading globally.Therefore,we aim to integrate non-critical COVID-19 high-frequency and high-targeting Chinese medicines to provide a reference for clinical prescriptions to improve COVID-19-related symptoms.Materials and methods:The information on non-critical COVID-19 high-frequency Chinese medicines in the diagnosis and treatment of COVID-19 was obtained by the TCM inheritance support platform.Using network pharmacology and molecular docking technology,high-targeting Chinese medicines with good docking activity with COVID-19 receptors angiotensin-converting enzyme-II(ACE2),3CLpro and tyrosine-protein kinase receptor UFO(AXL)were obtained.A new prescription for non-critical COVID-19 was established by integrating high-frequency and high-targeting Chinese medicines.Rats with acute lung injury induced by lipopolysaccharide were used as the experimental model.The histopathological changes in the lungs of rats in each group were observed by hematoxylin-eosin staining.The lung coefficient of rats was measured.The levels of IL-6,TNF-α,and IL-1βin serum were detected by enzyme-linked immunosorbent assay.The mRNA and protein levels of ACE2 and AXL in lung tissue were detected by real-time quantitative polymerase chain reaction and western blot.Results:Through data mining,it was found that there were 39 high-frequency traditional Chinese medicines for non-critical COVID-19 in the diagnosis and treatment guidelines.According to network pharmacology and molecular docking,30 highly targeted traditional Chinese drugs for COVID-19 were found.The new prescriptions for non-critical COVID-19 were comprehensively obtained,including Glycyrrhizae Radix,Ephedra Herba,Amygdalus Communis Vas,Gypsum Fibrosum,Descurainiae Semen,Atractylodes Lancea,Scutellariae Radix,Amomum Tsao-Ko Crevostet,Forsythiae Fructus,Pogostemon cablin,Magnolia Officinalis.Compared with the LPS-induced lung injury model group,the medium dose of the new prescription group had significantly alleviated pathological changes in lung tissue,decreased lung coefficient,decreased contents of IL-6,TNF-αand IL-1β,and increased mRNA and protein expression of ACE2 and AXL(P<0.05).Conclusion:Based on data mining,network pharmacology and molecular docking technology,the new prescription for non-critical COVID-19 established by this method has an anti-inflammatory effect on rats with acute lung injury induced by lipopolysaccharide and can provide a reference for clinicians to alleviate the symptoms related to non-critical COVID-19.

In the wave of big data,can traditional medicine for the diagnosis and treatment of skeletal disorders be given a new lease of life?

In recent years,big data has become a buzzword in the internet sector,gradually being used in various industries and fields,and has already yielded considerable benefits in e-commerce.In the past few years,big data has become increasingly important in healthcare based on the massive volume of clinical data and the increasing demand for personalized medicine.Traditional medicine,one of humanity’s fabulous creations,has also contributed actively to preventing and controlling new epidemics.With the development of the Internet,AI,cloud computing,the Internet of Things,and other high technologies in recent years,new vitality has been injected into the development of traditional medicine.It has also provided strong support for conventional medicine to play a more excellent value.Traditional medicine is now flourishing and gradually moving into the era of big data.Recently,there has been an increasing number of medical studies related to big data,but more studies are focused on cancer survival and cancer metastasis,which may be related to the fact that there are more free databases related to oncology,similar to the studies on big data related to skeletal diseases,but there are not many studies on the linkage between traditional medicine and big data for skeletal diseases.So,how will the field of big data and traditional medicine combine and diagnose or treat skeletal-related diseases in the future?How can traditional medicine in skeletal disorders ride the current fast-growing big data train?Will big data bring a new lease of life to traditional medicine in skeletal disorders?This review intends to systematically elaborate on the current and future research in the direction of big data in relation to diagnosing and treating skeletal diseases in traditional medicine.

Network pharmacology and data analysis method to explore the traditional Chinese medicine regulates ferroptosis key genes in the occurrence and prognosis of lupus nephritis

Purpose:To explore the traditional Chinese medicine(TCM)regulates ferroptosis key genes in the occurrence and development of lupus nephritis(LN)based on biological information database.Patients and methods:Ferroptosis related genes were identified based on FerrDb database and literature retrieval.Used the OMIM,Gene Cards,Drug Bank to obtain the targets of LN.Cytoscapes 3.8.2 software and STRING database were used to analyze protein-protein interaction(PPI)network.Metacape software and Weishengxin were used to analyze the gene ontology(GO)classification and Kyoto encyclopedia of genes and genomes(KEGG)pathway enrichment analysis.UniProt Database and Traditional Chinese Systems Pharmacology Database and Analysis Platform analysis platform were used to obtain the data table of key TCM and related targets.Cytoscapes 3.8.2 software was used to analyze the PPI network.Results:A total of 401 ferroptosis-related genes,361 LN related genes and 21“Ferroptosis-LN”intersection genes were obtained.Ferroptosis in the occurrence and prognosis of LN mainly involved the inflammatory response,cell activation,positive regulation of chemokine production and it was mainly involved in necroptosis,inflammatory bowel disease,ferroptosis and other pathways.A total of 412 TCMs containing key genes of“Ferroptosis-LN”were acquired.The most key genes were contained in Mahuang,Gehua,Baiguo,Chuanniuxi,Jinyinhua.15 key genes of“TCM-LN”were obtained.5 ferroptosis-related key genes in LN regulated by TCM were obtained,which were IL1β,TLR4,IFNG,STAT3 and HMOX1.Conclusion:TCM,such as Mahuang,Gehua,Baiguo,Chuanniuxi,Jinyinhua,may affect the occurrence and development of LN through the key ferroptosis genes,such as IL1B,TLR4,IFNG,STAT3 and HMOX1.

The basic core traditional C hinese medicine for the prevention and treatment of COVID-19 and its active mechanisms

Background:COVID-19 has had a dramatic impact on human health,economies,societies,and livelihoods around the world.Traditional Chinese medicine(TCM)formulae have played an important role in the prevention and treatment of COVID-19.WHO evaluated the role of TCM in treating of COVID-19 and encouraged other countries to promote the use of TCM formulae.However,the key is to find the basic core traditional Chinese medicine(BC-TCM)among those formulae.Methods:For the first time,we mined the data of TCM formulae in CNIPA and analyzed herb characteristics and association rules.We then determined the BC-TCM and screened main compounds and therapeutic targets.Finally,the potential molecular mechanisms were explored by using enrichment analyses and molecular docking.Results:This study screened 123 patented TCM formulae,including 312 herbs.According to frequency statistics and association rules,nine herbs(Gan Cao,Jin Yinhua,Guang Huoxiang,Fu Ling,Huang Qi,Jie Geng,Lian Qiao,Cang Zhu,Ku Xingren)were selected as the BC-TCM.The BC-TCM involved 166 main compounds and 48 therapeutic targets.The active compounds Hederagenin,Spinasterol,Beta-sitosterol,and Liquiritin had high binding activity to the COVID-19 targets 3CL,ACE2,and core targets RELA,HSP90AA1,STAT3,MAPK3,and TP53 according to molecular docking results.Interestingly,Hederagenin might be a potential compound for the prevention and treatment of COVID-19.Conclusion:Our research predicted and confirmed the preventive therapeutic effect of BC-TCM on COVID-19.This has the potential to broaden the scope of TCM,guide people in using clinical formulae,and provide valuable insights for future TCM discovery research.

Trends in research on osteoarthritis of the knee in conventional medicine:a bibliometric analysis based on big data from 1990-2022

Background:Osteoarthritis of the knee(KOA)is a chronic degenerative disease.KOA is a growing concern due to its high incidence and the pain and other burdens it places on patients.Traditional medicine is a health care model with a long history that includes nature-based treatments,psycho-psychological types of treatments,and more.Traditional medicine is also more effective in diagnosing and treating KOA,and it has never stopped researching KOA.There are no bibliometric studies analyzing articles on the traditional medical diagnosis and management of KOA.This study aimed to comprehensively analyze and analyze the general trends in the study of KOA in traditional medicine from a bibliometric perspective.Methods:All articles reporting on KOA and traditional medicine from 1 January 1990 to 01 November 2022 were obtained from the Web of Science Core.Some software such as CiteSpace,VOS Viewer and Scimago Graphica were used to analyse the publications,which included authors,citations,journals,references,countries where studies were published,institutions and research keywords.The final visualisations were produced using this data.Results:A total of 769 articles were searched.Peijian Tong was identified as the most contributing and published author in the field,and medicine was identified as the most reputable journal in the field of traditional medicine and osteoarthritis of the knee.China is a global leader in the field and a centre of collaboration in the field,with a major concentration of traditional medicine in Asia,which is consistent with the evidence that traditional medicine originated in Asia.According to the data,“osteoarthritis”,“knee osteoarthritis”,“pain”,and“knee”and“hip”were identified as hot keywords for research in this area.Conclusions:The results of this bibliometric study provide a snapshot of the current state of clinical research in the treatment of KOA in traditional medicine and are well placed to envisage future hotspots and possible trends,and may help to provide researchers with more than enough information with a view to guiding the cutting edge of research in this field and the infinite possibilities for the future.

A retrospective study on professor Gui-Qi Xuan’s experience in traditional Chinese medicine treatment on attention-deficit hyperactivity disorder: based on data mining and network pharmacology

Background:To investigate the clinical medication approach of Professor Guiqi Xuan(Prof.Xuan)in treating pediatric patients with attention-deficit hyperactivity disorder(ADHD)and the potential mechanism of the core herbal prescription.Methods:Following medical record information pretreatment,the Traditional Chinese Medicine(TCM)inheritance computing platform system V3.0 was utilized to analyze the standardized data.The associate rules were summarized to identify the core prescription for treating ADHD.The extracted core herbal prescription’s active compounds and potential targets were used to establish a protein-protein interaction network of active ingredient-disease targets.Cytoscape 3.9.1 software was used to analyze the network’s topological parameters to obtain the key active ingredients and their targets.The Bioconductor data package of R4.0.2 was used to analyze the gene ontology biological functions and Kyoto Encyclopedia of Genes and Genomes pathways of key targets.Results:Two hundred and twenty-seven entries derived from TCM record information were selected.Through data mining,it was found that 62.5%of pediatric patients had short-tempered behavior,nearly half had sleep problems,and 30%-40%had picky eating and polyphagia issues.The highest-frequency syndrome type was kidney deficiency and liver hyperactivity.Deficiency,fire,phlegm,and dyspeptic food were the main pathological factors for ADHD.Prof.Xuan’s treatment of ADHD mainly focused on replenishing kidney essence and subduing Yang(active,external,ascending,warm,bright,functional and excited pertain to Yang).The core herbal prescription for ADHD included Yuan-zhi,Yi-zhi,Gui-jia,Bai-shao,Long-chi,Ci-shi,Shi-chang-pu,Yu-jin,Fu-shen,and Huang-jing.The protein-protein interaction network showed that MAOA,ADRB2,FOS,MAOB,and SLC6A3 were the five key targets essential in treating ADHD with core herbal prescriptions.The gene ontology biological function of crucial targets mainly involved G protein-coupled amine receptor activity,catecholamine binding,and neurotransmitter transmembrane transporter activity.Analysis of Kyoto Encyclopedia of Genes and Genomes pathways showed that the dopaminergic synapse signaling and neuroactive ligand-receptor interaction pathways were significantly enriched and may be the primary routes for the main treatment of ADHD.Conclusion:Prof.Xuan’s treatment of ADHD has achieved satisfactory clinical effects by supplementing the kidney,replenishing the essence,opening the orifices,nourishing the Yin(static,internal,descending,cold,dim,organic,depressed and pertain to Yin),and subduing the Yang.The major prescription predominantly affects catecholamine binding,neuroactive ligand-receptor interaction,G protein-coupled amine receptor function,and signaling pathways for dopaminergic synapses.Our findings showed that the methodology and software used in this research could explore and analyze the mechanism behind Prof.Xuan’s clinical medication rule for treating ADHD in children.

Identifying medication regularity of traditional Chinese medicine and potential pharmacological mechanism of Jiedu Sangen decoction in colorectal cancer treatment by data mining and network pharmacology

Objective:Colorectal cancer(CRC)is one of the most common malignancies in the world,and traditional Chinese medicine(TCM)is widely used in its treatment in China.However,the medication rules of TCM for CRC treatment remain unclear.Therefore,data mining combined with network pharmacology was utilized to establish treatment principles and rules.Methods:The CRC cases treated at Zhejiang Provincial Hospital of Chinese Medicine from January 1,2016 to October 31,2021 were analyzed using data mining methods.UPLC-Q/TOF-MS analysis was performed to identify the chemical composition of Jiedu Sangen decoction(JSD).Network pharmacology was used to reveal the therapeutic mechanism of JSD.Results:A total of 312 cases 2,998 prescriptions that met the inclusion criteria used 343 kinds of traditional Chinese medicines.The nature of the herbs used in treatment was mainly warm and mild.The taste was mainly sweet,bitter,and pungent.The meridian tropisms were mainly the spleen meridian,followed by lung and stomach meridians.Tonifying and replenishing herbs were the most frequently used in treatment.High-frequency herbs were classified into 11 categories by cluster analysis,and 42 association rules were obtained by association rule analysis.Combined with complex network analysis,3 core prescriptions for clinical CRC treatment were obtained.Jiedu Sangen decoction contains 64 chemical ingredients,out of which 31 active ingredients were identified,including polydatin,caffeic acid,and glutamic acid,along with 130 potential targets such as AKT1,SRC,and MAPK1.Jiedu Sangen decoction may play a role in regulating inflammation,immunity,metabolism,and hormones in the development of CRC via pathways such as the relaxin signaling pathway,IL-17 signaling pathway,prolactin signaling pathway,and T cell receptor signaling pathway.Conclusions:This study summarizes the treatment and medication principles for clinical CRC treatment,promoting the inheritance and development of the traditional Chinese medical experience.

Research progress of data mining in the treatment of hypertension by traditional Chinese medicine

With the gradual development of data mining technology,more and more data mining software emerges as the times require,and the data mining methods are diversified,which provides a strong support in the study of the treatment of hypertension by traditional Chinese medicine.This research systematically introduces the advantages,disadvantages and application examples of data mining software such as SPSS,TCM inheritance support platform,TCM clinical research information sharing system and data mining methods such as cluster analysis,bayesian network,system evaluation.It is expected to enhance the practical application of data mining in the study of prevention,diagnosis and medication rule of TCM treatment of hypertension,and provide reference for the development of new software and new technology.

Based on the national patent database to explore the rule of traditional Chinese medicine in the treatment of hyperlipidemia

Objective:To explore the medication law of traditional Chinese medicine compound patent for hyperlipidemia,and to provide reference for the research and development of traditional Chinese medicine new drugs for clinical treatment of hyperlipidemia.Methods:All compound TCM patents related to the treatment of hyperlipidemia were searched and extracted from the national patent database(http://epub.sipo.gov.cn)from the establishment of the database to 10st,March 2021.The data was established by the TCM Inheritance Support System(V2.5)and Microsoft Excel 2010 Softwore,and used to conduct TCM syndromes,frequency statistics,four nature and five flavors of traditional Chinese medicine,meridian attribution statistics.IBM SPSS statistics 20 software was used for drug clustering analysis,IBM SPSS modeler 18.2.2 software was used for association rules and web visualization analysis.Results:Totally 284 compound TCM patents were included,involving 577 kinds of Chinese medicine,and the most common syndrome was Yin deficiency of liver and kidney syndrome(74 times,accounting for 26.06%).The most ten common Chinese materiamedica was Hawthorn,Salvia miltiorrhiza,Alismaorientalis,Cassia seed,Polygonummultiflorum,Licorice,Poriacocos,chinese rhubarb,dried tangerine peel,Radix Paeoniae Alba.The top three appeared frequently in drug categories were tonifying deficiency medicine,activating blood-circulation and dissipating blood-stasis medicine,and heat-clearing medicine,respectively.The top two of its drug properties were warm and cold;the top three drug tastes were sweet,bitterness and pungent;the top two meridians were liver and spleen meridian,respectively.Seven drug groups were obtained by cluster analysis,and 16 were obtained by association rule analysis,including 5 drug pairs and 11 three drug groups.Conclusion:Through the data mining of the patent of traditional Chinese medicine compound prescription for regulating and treating hyperlipidemia,it is concluded that the fundamental pathogenesis of the disease is deficiency of viscera function and obstruction of phlegm and blood stasis.The clinical methods are tonifying the liver and kidney,activating blood circulation and removing stasis,resolving phlegm and removing dampness.Traditional Chinese medicine is mostly used for tonifying deficiency,activating blood circulation,removing stasis,resolving phlegm and removing dampness.This paper provides a reference for the research and development of traditional Chinese medicine for hyperlipidemia.

Research based on data mining compatibility of traditional Chinese medicine with Professor WANG Dong-mei in the treatment of primary dysmenorrhea

Objective:To study the law of compatibility of traditional Chinese medicine in the treatment of primary dysmenorrhea by Professor WANG Dong-mei.Methods:This study collected the Professor WANG Dong-mei’s prescriptions for primary dysmenorrhea cases in the outpatient department,to establish a database by Excel 2015,and to use IBM SPSS statistics 24.0 and SPSS Clementine 12.0 software for clustering analysis and association rules data mining analysis.Results:A total of 106 cases were included,106 prescriptions were collected,114 kinds of drugs were used,nd the cumulative frequency of drug use was 1876 times;the top three drugs were white peony(89 times),Xiangfu(77 times),red peony(75 times);the drugs with the most drug properties and taste frequency were warm and sweet drugs,which were mainly liver meridian;four common pair-used drug groups were Xiangfu yanhusuo,angelica white peony etc.and six groups were common clustering groups.Conclusion:Professor WANG Dong-mei usually chooses the drugs of sweet,warm or spicy in the treatment of primary dysmenorrhea.In addition to the natural efficacy,Prof.Wang also considers modern pharmacological effect in the specific drug selection.The commonly used prescription combination is Shaofu Zhuyu Decoction,which embodies Professor WANG Dong-mei's academic thought of treating primary dysmenorrhea"mainly by warming and regulating qi and blood",and for patients with reproductive needs,in addition to promoting blood circulation and relieving pain,she also adds menstruation regulating and pregnancy aiding drugs,which can not only improve the symptoms of primary dysmenorrhea,but also meet their fertility desire.

Analysis of the rule of medication of compound Chinese traditional patent medicine for digestive system tumors based on data mining

Objective:Based on the data mining method,explore the medication rules of Chinese patent medicines for the treatment of digestive system tumors.Method:Based on the"Chinese Traditional Medicine Prescription Database"in https://db.yaozh.com/,collect Chinese patent medicines for the treatment of digestive system tumors,establish an Excel table,and use the ancient and modern medical case cloud platform(V2.2.1)to perform frequency statistics,association rules,and drugs on the data Clustering and complex network analysis.Results:A total of 36 Chinese patent medicines for the treatment of digestive system tumors were screened.The medicinal properties were mainly warm and cold,the taste was bitter and sweet,and the meridians were mainly liver and spleen meridians.High frequency Chinese medicine include Astragalus,Scutellaria-barbata,Ginseng,Curcuma,Triangle,Atractylodes,Hedyotis diffusa,etc.Correlation analysis obtained 17 drug combinations,High-frequency drug pairs include Scutellaria-barbata-Astragalus,Ginseng-Astragalus,Curcuma-Astragalus,Scutellaria-barbata-Curcuma,etc.Cluster analysis found 3 types of drugs.The core drug network is composed of 27 drugs,and the core compatibility network consists of 3 groups of drugs.Conclusion:The Chinese patent compound medicine for the treatment of digestive system tumors has the characteristics of combining cold and warming,replenishing and reducing treatment,and treating the liver and spleen at the same time.The medicine is mainly used to replenish qi and invigorate the spleen,promote blood circulation and remove blood stasis,and clear away heat and detoxification.Replenish qi,nourish yin,invigorate blood,and detoxify are mainly compatible with each other,reflecting the pathogenesis characteristics of"deficiency,stasis,and toxin"in digestive system tumors.Data mining can provide references for the prescription and compatibility of Chinese patent medicines.

A study of medication rules of traditional Chinese medicine in the treatment of pre diabetes based on data mining

Background:To summarize the concerted application and prescription rules of traditional Chinese medicine in the treatment of pre diabetes.Methods:Microsoft Excel 2010 was used to summarize the categories,nature,flavour and channel tropism of drugs.The cluster analysis of high-frequency drugs was carried out by SPSS 22.0,and the association rules of high-frequency drugs were analyzed by Apriori algorithm provided by SPSS modeler 14.0.Results:One hundred and forty-six references were included,including 153 prescriptions and 131 drugs.Their frequency of use is listed in the following order.The top 3 categories of drugs were“Tonifying,Heat-Clearing”,diuresis and“Diffusing Dampness”drugs.The top 5 drugs were Huangqi(Astragali radix),Fuling(Poria),Huanglian(Coptidis rhizoma),Shanyao(Dioscoreae rhizoma),Gegen(Puerariae lobatae radix).The top 3 channel tropism of drugs were spleen,stomach and lung.The top 3 nature of drugs were cold,warm and calm.The top 3 flavour of drugs were sweet,bitter and pungent.The cluster analysis of high-frequency drugs showed that it could be classified into 4 categories:“Benefiting Qi”for promoting production of fluid,“Clearing Heat”and“Eliminating Dampness”,“Nourishing Yin”and“Clearing Heat”,and“Invigorating Spleen”for“Diffusing Dampness”.The results of association rule analysis showed that the combination with the highest degree of confidence and support was Poria-Chenpi(Citri reticulatae pericarpium)-Banxia(Pinelliae rhizoma)-Baizhu(Atractylodis macrocephalae rhizoma)and the combination with the highest frequency was Astragali radix-Puerariae lobatae radix.Conclusion:The pre diabetes is due to deficiency.The disease location is spleen and stomach and the pathological factor is phlegm-damp,that is why benefiting qi and invigorating spleen is regarded as the key link of clinical treatment.

Computer Handling of Chemical and Biological Data of Traditional Chinese Medicines

A specialty database has been established at The Hong Kong University of Science and Technology to handle the chemical and biological data of medicinal plants and other natural products from scientific literatures. Designed as a relational system capable of analyzing, comparing, and correlating data, the system can retrieve information in assimilated tabular formats. The database can provide information supports to researchers in the fields of medicinal chemistry, biochemistry, pharmacology, botany and other disciplines of natural products research.

Analysis on medication rule of traditional Chinese medicine treating chemotherapy-induced diarrhea based on traditional Chinese medicine(TCM) inheritance computing platform system

Objective:To dig deeper into the traditional Chinese medicine treatment rules of chemotherapy-induced diarrhea with traditional Chinese medicine(TCM)inheritance computing platform system.Methods:Taking“traditional Chinese medicine”,“chemotherapy”and“diarrhea”as the theme words,comprehensive search of the database of CNKI,Wanfang and VIP from its inception to November 2020 was conduct-ed.The formulas of external treatment of traditional Chinese medicine for chemotherapy-induced diarrhea were included and the association rule,clustering and factor analysis were carried out.Results:A total of 145 papers,57 prescriptions meeting the inclusion criteria were collected,among which high-frequency drugs including Baizhu(Atractylodis macrocephalae rhizoma),Fuling(Poria),Dangshen(Codonopsisradix),Huanglian(Coptidis rhizoma),Zhigancao(Glycyrrhizae radix et rhizoma praeparata cum melle)were the most commonly used.The confidence level was set as 0.7 and the support level was set as 10,12 core compatibility groups were obtained,and 6 categories were cluster analyzed.Conclusion:The principle of external treatment of chemotherapy-induced diarrhea is mainly“restore deficiency and benefiting qi”,“benefiting water infiltration and dampness”,“clearing heat”and“inducing astringency”.Prescription combination and new prescription combination based on traditional Chinese medicine(TCM)inheritance computing platform system can be used as reference for clinicians and applied in primary hospitals.

Analysis on the medication rules and mechanisms of action of traditional Chinese medicine in treating cervical cancer

Objective: To summarize the rule of application of traditional Chinese medicine (TCM) in the prevention and treatment of cervical cancer, and to explore the molecular mechanism of the compatibility of core herbs. Methods: Collect relevant literatures on cervical cancer in Chinese National Knowledgey Ifrastructure (CNKI), use TCM inheritance platform system (TCMISSV2.5) for association rules and complex system entropy clustering analysis;use BATMAN-TCM online analysis tools to construct target-pathway-disease network to reveal the underlying mechanisms of action. Results: Among the 78 prescriptions selected, a total of 172 Chinese medicines were used, and the five most frequently used herbs were Huang-bo (Phellodendri Chinrnsis Cortex), Fu-ling (Poria Cocos), Huang-qi (Hedysarum Multijugum Maxim.), Bai-hua-she-she-cao (Hedyotis Diffusae Herba) and Gan-cao (Licorice). Bai-hua-she-she-cao (Hedyotis Diffusae Herba) and Huang-qi (Hedysarum Multijugum Maxim.), Bai-hua-she-she-cao (Hedyotis Diffusae Herba) and Fu-ling (Poria Cocos), Bai-zhu (Atractylodes Macrocephala Koidz.) and Fu-ling (Poria Cocos) are the three most commonly used medicine match. In addition, through cluster analysis, a total of 4 core herbs compatibility and 2 new prescriptions were excavated. Herbs in the new prescriptions which are used to clearing heat-toxin and removing dampness were most frequently used. Through the analysis of the signal pathway of high frequency Chinese medicines, we found that neuroactive ligand-receptor interaction pathway may play important roles. Conclusion: The core Chinese medicines for the prevention and treatment of cervical cancer are mainly clearing heat-toxin and removing dampness. The core Chinese medicines may play their anti-cervical cancer by interfering with the neuroactive ligand-receptor interaction signaling pathway.

A study on the rule of Chinese medicine use against influenza virus based on data mining

Background:To summarize the rules of the use of traditional Chinese medicine against influenza virus in the high-quality literatures of core journals,and to provide guidance for the prevention and treatment of influenza.Methods:Excel 2010 and ancient and modern medical case cloud platform(2.5V)were used to summarize the categories,nature,flavour and channel tropism of drugs.The cluster analysis of high-frequency drugs was carried out by SPSS 22.0,and the association rules of high-frequency drugs were analyzed by Apriori algorithm provided by SPSS modeler 18.0.Results:One thousand one hundred and thirty-one articles from core journals were retrieved and 135 articles were screened out,including 109 prescriptions and 170 drugs,with a total frequency of 1,655 times.The 3 most frequently appeared herbs were Gancao(Glycyrrhizae radix et rhizoma),Jinyinhua(Lonicerae japonicae flos)and Lianqiao(Forsythiae fructus).The top 3 efficacy were“Heat-Clearing(remove heat from the body surface and inside)”drugs,drugs for“Relieving Exterior Disorder(treat fever,chills and headaches caused by pathogenic substances in the air)”,and“Phlegm Relieving Cough Antiasthmatic Medicine(relieves respiratory cough and sputum symptoms)”drugs.The top 3 nature of drugs were cold,warm and flat.The top 3 flavour of drugs were bitter,spicy and sweet.The top 5 channel tropism of drugs were“Lung”,“Stomach”,“Heart”,“Spleen”,“Liver”.Association rule yields 20 drug pairs,Jingjie(Schizonepetae herba),Forsythiae fructus,Lonicerae japonicae flos,Niubangzi(Arctii fructus),Mahuang(Ephedrae herba)and Glycyrrhizae radix et rhizoma were commonly used concerted application;four new methods were obtained by cluster analysis.Conclusion:The use of traditional Chinese medicine against influenza virus has a certain regularity,which provides an important reference value for the prevention and treatment of influenza.

Regularity of syndrome differentiation and treatment of traditional Chinese medicine for Henoch-Schonlein purpura based on data mining techniques

Objective:This study aims to explore the regularity of syndrome differentiation and treatment of traditional Chinese medicine(TCM)for allergic purpura.Methods:CNKI,Weipu Chinese science and technology database,wanfang medical network database,and Chinese biomedical literature database were searched for eligible studies.Medical records including complete patient personal information,patient symptoms,TCM syndromes,treatment,and medication were included.The data was analyzed using the Chinese medicine heritage support platform provided by the Chinese Academy of Chinese medicine(V2.5).Results:Differentiation of health gas camp blood was the most commonly used method of differentiation of symptoms and signs in famous veteran TCM.The treatment included cooling blood,activating blood circulation,clearing heat and detoxifying toxins,removing blood stasis and stopping bleeding.Honeysuckle,Forsythia suspensa,cicada slough and other drugs were interrelated.Potential drug pair combinations and drug networks showed the basic drug composition of Qingying Decoction.According to the entropy cluster analysis,28 core drug combination and 12 new formulations were obtained.Conclusion:The regularity of syndrome differentiation and treatment of traditional Chinese medicine for Henoch-Schonlein purpura based on the famous and old TCM doctors was complex.Further researches are still needed.

Study on medication laws of traditional Chinese medicine of 340 cases of COVID-19 based on data mining

Objective:To analyze the prescription rules of traditional Chinese medicine for patients with COVID-19 in Wuhan Third Hospital, and summarize the disease characteristics and clinical treatment ideas, in order to learn from the treatment of this disease by traditional Chinese medicine.Methods: This study established a cloud database based on the ancient and modern medical cases to mine the rules of medication with analyses of frequency of drug used, association analysis, cluster analysis, complex network and other methods.Results:Of 340 COVID-19 patients discharged from our hospital, 143 males and 197 females with male: female = 0.73: 1, and there were 167 patients over 60 years old, and the majority of clinical illnesses were mainly middle-aged and elderly people. Most of them had dry cough, anorexia, fatigue, etc. The traditional Chinese medicine for the treatment of COVID-19 involves a total of 204 flavors. The most frequent use is Fuling of 225 times. The treatment of traditional Chinese medicines is mainly involved with flavors such as warm, spicy and sweet. Mainly detoxification, dampness and phlegm, Qingfei Paidu Decoction is a common clinical prescription, of which the core drugs are Huoxiang, Fabanxia, Chenpi, Baizhu, Cangzhu, Fuling, Chaihu, Huangqin, Xingren, and Gancao.Conclusion: Through this study, the patients with COVID-19 in our hospital are mainly middle-aged and elderly people, and the etiology is characterized by "cold, wet, poisonous, and epidemic". Wetness is the most important core of the disease.

Study on technical efficiency of traditional Chinese medicine industry of the Belt and Road Initiative based on environmental complexity

Background:Based on the principle of“joint consultation,co-building,and sharing”,with the aim of creating an energetic new model of economic growth,the Belt and Road Initiative achieves connectivity and mutual benefit.However,the degree of coordinated development of innovation subjects directly affects the improvement and optimization of the Belt and Road Initiative’s strategy implementation environment,and technology efficiency needs improvement.Methods:In this study,a data envelopment analysis model based on the environmental noise elimination algorithm(traditional Chinese medicine-Belt and Road Initiative)was used to identify the technical efficiency of the traditional Chinese medicine industry of Belt and Road Initiative by eliminating the impact of environmental factors.Results:Pure technical ineffectiveness,regional impact,and environmental factors represented by policy responses have a non-linear impact on technical efficiency.The overall technical efficiency of the traditional Chinese medicine industry in the countries along the route shows a trend of annual increases,technical efficiency and scale efficiency are relatively high,and operational efficiency is influenced by the degree of response of the countries along the route and its supporting policies.Conclusion:Pure technical inefficiency is the main factor affecting total technical loss.Geographical advantage is the key factor in operational efficiency.External environmental factors have a significant influence on the operational efficiency of the traditional Chinese medicine industry.