Modelo predictivo de enfermedad cardiovascular basado en inteligencia artificial en la atención primaria de salud / A Predictive Model for Cardiovascular Disease based on Artificial Intelligence in Primary Health Care

Introducción: En Cuba y en el resto del mundo, las enfermedades cardiovasculares son reconocidas como un problema de salud pública mayúsculo y creciente, que provoca una alta mortalidad. Objetivo: Diseñar un modelo predictivo para estimar el riesgo de enfermedad cardiovascular basado en técnicas de inteligencia artificial. Métodos: La fuente de datos fue una cohorte prospectiva que incluyó 1633 pacientes, seguidos durante 10 años, fue utilizada la herramienta de minería de datos Weka, se emplearon técnicas de selección de atributos para obtener un subconjunto más reducido de variables significativas, para generar los modelos fueron aplicados: el algoritmo de reglas JRip y el meta algoritmo Attribute Selected Classifier, usando como clasificadores el J48 y el Multilayer Perceptron. Se compararon los modelos obtenidos y se aplicaron las métricas más usadas para clases desbalanceadas. Resultados: El atributo más significativo fue el antecedente de hipertensión arterial, seguido por el colesterol de lipoproteínas de alta densidad y de baja densidad, la proteína c reactiva de alta sensibilidad y la tensión arterial sistólica, de estos atributos se derivaron todas las reglas de predicción, los algoritmos fueron efectivos para generar el modelo, el mejor desempeño fue con el Multilayer Perceptron, con una tasa de verdaderos positivos del 95,2 por ciento un área bajo la curva ROC de 0,987 en la validación cruzada. Conclusiones: Fue diseñado un modelo predictivo mediante técnicas de inteligencia artificial, lo que constituye un valioso recurso orientado a la prevención de las enfermedades cardiovasculares en la atención primaria de salud(AU)

Introduction: In Cuba and in the rest of the world, cardiovascular diseases are recognized as a major and growing public health problem, which causes high mortality. Objective: To design a predictive model to estimate the risk of cardiovascular disease based on artificial intelligence techniques. Methods: The data source was a prospective cohort including 1633 patients, followed for 10 years. The data mining tool Weka was used and attribute selection techniques were employed to obtain a smaller subset of significant variables. To generate the models, the rule algorithm JRip and the meta-algorithm Attribute Selected Classifier were applied, using J48 and Multilayer Perceptron as classifiers. The obtained models were compared and the most used metrics for unbalanced classes were applied. Results: The most significant attribute was history of arterial hypertension, followed by high and low density lipoprotein cholesterol, high sensitivity c-reactive protein and systolic blood pressure; all the prediction rules were derived from these attributes. The algorithms were effective to generate the model. The best performance was obtained using the Multilayer Perceptron, with a true positive rate of 95.2percent and an area under the ROC curve of 0.987 in the cross validation. Conclusions: A predictive model was designed using artificial intelligence techniques; it is a valuable resource oriented to the prevention of cardiovascular diseases in primary health care(AU)

Analysis and prospects of common problems in clinical data mining of traditional Chinese medicine prescriptions / 中国中药杂志

Mining data from traditional Chinese medicine(TCM) prescriptions is one of the important methods for inheriting the experience of famous doctors and developing new drugs. However, current research work has problems such as to be optimized research plans and non-standard statistics. The main problems and corresponding solutions summarized by the research mainly include four aspects.(1)The research plan design needs to consider the efficacy and quality of individual cases.(2)The significance of the difference in confidence order of association rules needs to be further considered, and the lift should not be ignored.(3)The clustering analysis steps are complex. The selection of clustering variables should comprehensively consider factors such as the frequency of TCM, network topology parameters, and practical application significance. The selection of distance calculation and clustering methods should be improved based on the characteristics of TCM clinical data. Jaccard distance and its improvement plan should be given attention in the future. A single, unexplained clustering result should not be presented, but the final clustering plan should be selected based on a comprehensive consideration of TCM clinical characteristics and objective evaluation indicators for clustering.(4)When calculating correlation coefficients, algorithms that are only suitable for continuous variables should not be applied to binary variables. This article explained the connotations of the above problems based on the characteristics of TCM clinical research and statistical principles and proposed corresponding suggestions to provide important references for future data mining research work.

Acupoint selection rules of staging, syndrome types, and symptoms of acupuncture for peripheral facial paralysis based on data mining / 中国针灸

OBJECTIVES@#To analyze and explore the acupoint selection rules of different staging, syndrome types, and symptoms of acupuncture for peripheral facial paralysis based on data mining.@*METHODS@#Literature regarding acupuncture for peripheral facial paralysis was retrieved in CNKI, VIP, Wanfang, SinoMed, and PubMed from January 1, 2012, to December 31, 2021. The Traditional Chinese Medicine Inheritance Assistant Platform (V 3.0), SPSS Modeler 18.0, and Cytoscape software were used to analyze the selection of acupoints based on staging, meridian distribution of acupoints, the selection of acupoints based on syndrome types, syndrome types based on staging, and symptom-based acupoint selection. Association rule analysis was performed for each stage and major syndrome types, and co-occurrence network diagrams were generated.@*RESULTS@#A total of 1 695 articles were included, involving 124 acupoints with a total frequency of 5 456 times. Among 1 080 articles related to staging-based acupoint selection, the acute stage had the highest acupoint use frequency (2 224 times) and number (88 acupoints). Among all stages, the acupoints of the stomach meridian of foot-yangming were most frequently used, with Dicang (ST 4)-Yangbai (GB 14) and Dicang (ST 4)-Jiache (ST 6) being the high-frequency acupoint pairs in each stage. The top four syndrome types in terms of acupoint usage frequency were wind-cold syndrome, wind-heat syndrome, qi-blood deficiency syndrome, and liver-gallbladder damp-heat syndrome. Among 521 articles combining staging with symptoms or syndrome types with symptoms for acupoint selection, the symptom "nasolabial groove becoming shallow or disappearing" had the highest frequency of occurrence. The symptoms with the highest acupoint usage frequency and number were "forehead wrinkles becoming shallow or disappearing" and "pain behind the ear" respectively.@*CONCLUSIONS@#Acupoint selection for peripheral facial paralysis primarily focuses on the yang meridians in each stage, supplemented by local acupoints and based on the pathological characteristics. Syndrome differentiation and treatment should be prioritized, combined with local acupoint selection. Clinical acupoint selection can be based on a combination of staging, syndrome types, and symptoms.

Data mining in traditional Chinese medicine product quality review / 中国中药杂志

The traditional Chinese medicine(TCM) enterprises have accumulated a large amount of product quality review(PQR) data. Mining these data can reveal the hidden knowledge in production and helps improve pharmaceutical manufacturing technology. However, there are few studies involving the mining of PQR data and thus enterprises lack the guidance to analyze the data. This study proposed a method to mine the PQR data, which consisted of 4 functional modules: data collection and preprocessing, risk classification of variables, risk evaluation by batches, and the regression analysis of quality. Further, we carried out a case study of the formulation process of a TCM product to illustrate the method. In the case study, the data of 398 batches of products during 2019-2021 were collected, which contained 65 process variables. The risks of variables were classified according to the process performance index. The risk of each batch was analyzed through short-term and long-term evaluation, and the critical variables with the strongest impact on the product quality were identified by partial least square regression. The results showed that 1 variable and 13 batches were of high risk, and the critical process variable was the quality of the intermediates. The proposed method enables enterprises to comprehensively mine the PQR data and helps to enhance the process understanding and improve the quality control.

Tensor decomposition: new strategy for deciphering mechanism of precision medicine for same treatment of different diseases / 中国中药杂志

The aging society has led to a substantial increase in the number of clinical comorbidities. To meet the needs of comorbidity treatment, polypharmacy is widely used in clinical practice. However, polypharmacy has drawbacks such as treatment conflict. Same treatment of different diseases refers to treating different diseases with same treatment. Therefore, the principle of same treatment of different diseases can alleviate the problems caused by polypharmacy. Under the research background of precision medicine, it becomes possible to explore the mechanism of same treatment of different diseases and achieve its clinical application. However, drugs successfully developed in the past have revealed shortcomings in clinical use. To better interpret the mechanism of precision medicine for same treatment of different diseases, under the multi-dimensional attributes including dynamic space and time, omics was performed, and a new strategy of tensor decomposition was proposed. With the characteristics of complete data, tensor decomposition is advantageous in data mining and can fully grasp the connotation of precision treatment of different diseases with same treatment under dynamic spatiotemporal changes. This method is used for drug repositioning in some biocomputations. By taking advantage of the dimensionality reduction of tensor decomposition and integrating the dual influences of time and space, this study achieved accurate target prediction of same treatment of different diseases at each stage, and discovered the mechanism of precision medicine of same treatment for different diseases, providing scientific support for precision prescription and treatment of different diseases with same treatment in clinical practice. This study thus conducted preliminary exploration of the pharmacological mechanism of precision Chinese medicine treatment.

Lean strategy for data mining and continuous improvement of Chinese pharmaceutical process: a case study of sporoderm-removal Ganoderma lucidum spore powder / 中国中药杂志

In the digital transformation of Chinese pharmaceutical industry, how to efficiently govern and analyze industrial data and excavate the valuable information contained therein to guide the production of drug products has always been a research hotspot and application difficulty. Generally, the Chinese pharmaceutical technique is relatively extensive, and the consistency of drug quality needs to be improved. To address this problem, we proposed an optimization method combining advanced calculation tools(e.g., Bayesian network, convolutional neural network, and Pareto multi-objective optimization algorithm) with lean six sigma tools(e.g., Shewhart control chart and process performance index) to dig deeply into historical industrial data and guide the continuous improvement of pharmaceutical processes. Further, we employed this strategy to optimize the manufacturing process of sporoderm-removal Ganoderma lucidum spore powder. After optimization, we preliminarily obtained the possible interval combination of critical parameters to ensure the P_(pk) values of the critical quality properties including moisture, fineness, crude polysaccharide, and total triterpenes of the sporoderm-removal G. lucidum spore powder to be no less than 1.33. The results indicate that the proposed strategy has an industrial application value.

Acupoints compatibility rules of acupuncture for depression disease based on data mining technology / 中国针灸

Based on data mining technology, the acupoints compatibility rules of acupuncture for depression diseases were explored. The randomized controlled trial (RCT) articles regarding acupuncture for depression diseases published from establishment of database to September 2nd, 2022 were searched in CNKI database, Wangfang database, VIP database, SinoMed database, PubMed, EMbase, Web of Science and Cochrane Library. The use frequency of acupoints, meridian tropism, selection of special acupoints and acupoint association rules for five common depression diseases, including primary depression, post-stroke depression, menopausal syndrome, psychoneurosis and anxiety disorder, were analyzed by Python programming language. Cytoscape software was used to analyze the acupoint association and the disease-acupoint co-occurrence network. As a result, totally 387 articles were included, and 319 acupoints prescriptions for the above five common depression diseases were extracted, involving 159 acupoints. The use frequency of acupoints was 2 574 times in total. The frequently-used acupoints were Baihui (GV 20), Sanyinjiao (SP 6), Taichong (LR 3), Neiguan (PC 6), Shenmen (HT 7), Yintang (GV 24+), Zusanli (ST 36), Hegu (LI 4), Sishencong (EX-HN 1) and Taixi (KI 3), etc. The frequently involved meridians were the governor vessel, foot-taiyang bladder meridian, foot-taiyin spleen meridian, and foot-jueyin liver meridian. The frequency of the special acupoints from high to low was crossing points, five-shu points, yuan-primary points, back-shu points, luo-connecting points, and eight confluent points, etc, which were often used in combination with "Baihui (GV 20)-Yintang (GV 24+)" (the highest degree of association). At the same time, the analysis of the co-occurrence network of depression diseases and acupoints showed that the core acupoints group of acupuncture for depression diseases were Baihui (GV 20), Taichong (LR 3), Shenmen (HT 7), Zusanli (ST 36), Neiguan (PC 6) and Sanyinjiao (SP 6). In conclusion, acupuncture treatment for depression diseases has gradually formed a rule of acupoint compatibility, with special acupoint as the main body and "unblocking the governor vessel, and regulating the spirit and qi " as the main therapeutic principle.

Acupoint selection rules of acupuncture and moxibustion for post-stroke epilepsy based on data mining technology / 中国针灸

OBJECTIVE@#To analyze the acupoint selection rules of acupuncture and moxibustion for post-stroke epilepsy by data mining technology.@*METHODS@#The literature regarding acupuncture and moxibustion for post-stroke epilepsy included in CNKI, VIP, Wanfang, SinoMed and PubMed databases from the establishment of the database to August 1st 2022 was retrieved. Microsoft Excel 2019 software was used to establish a database to conduct the descriptive analysis of acupoints; SPSS Modeler 18.0 Apriori algorithm was used to conduct association rule analysis; high-frequency acupoint co-occurrence network diagrams were drawn by Cytoscape3.9.0 software; SPSS Statistics 25.0 software was used to perform hierarchical cluster analysis on high-frequency acupoints and a tree diagram was drawn.@*RESULTS@#Totally 39 articles were included, and 63 prescriptions of acupuncture and moxibustion were extracted, involving 56 acupoints, with a total frequency of 516 times; the top three acupoints with the highest frequency of use were Baihui (GV 20), Fenglong (ST 40) and Neiguan (PC 6); the selected meridians were mainly the governor vessel, the hand and foot yangming meridians; the selection of acupoints were mostly in the head, neck and lower limbs; in terms of acupoint compatibility, Hegu (LI 4)-Shuigou (GV 26) and Neiguan (PC 6) had the highest confidence degree; The top 20 high-frequency acupoints could be divided into 4 effective clusters.@*CONCLUSION@#Modern acupuncture and moxibustion treatment for post-stroke epilepsy attaches great importance to the use of yang meridians and meridians with enrich qi and blood; the core prescription is Shuigou (GV 26)-Neiguan (PC 6)-Hegu (LI 4)-Baihui (GV 20). In addition, the combination of distant and near acupoints is highly valued to improve clinical efficacy.

The rules of acupoint selection of acupuncture and moxibustion for aphasia based on data mining / 中国针灸

OBJECTIVE@#To explore the rules of acupoint selection for aphasia treated with acupuncture and moxibustion using data mining technology.@*METHODS@#From January 1, 2000 to April 1, 2022, the articles for clinical researches of acupuncture and moxibustion for aphasia published in CNKI, Wanfang, VIP, SinoMed, PubMed, EMbase were searched. Using Microsoft Excel 2021, the database was set up to analyze the use frequency of acupoint, meridian tropism, acupoint distribution and the use of specific points. SPSS26.0 was adopted for factor analysis, SPSS Modeler 18.0 was for association rule analysis of prescriptions, and Gephi 0.9.5 was to plot the co-occurrence network diagrams of acupoints and meridians.@*RESULTS@#A total of 140 articles were collated, including 146 acupuncture and moxibustion prescriptions and 189 acupoints. The total use frequency of these acupoints was 1 211. Lianquan (CV 23), Jinjin (EX-HN 12), Yuye (EX-HN 13), Baihui (GV 20) and Yamen (GV 15) were the top 5 acupoints of the high use frequency for aphasia treated with acupuncture and moxibustion. Among 189 acupoints collected, the extra points and empirical points were mostly selected. The top 3 involved meridians were the governor vessel, the gallbladder meridian of foot-shaoyang and the conception vessel. These acupoints were mostly distributed on the head, face and neck region. The use frequency of five-shu points was the highest among the specific points. The acupoint combinations of high frequency referred to Yuye (EX-HN 13)-Jinjin (EX-HN 12), Yuye (EX-HN 13)-Lianquan (CV 23)-Jinjin (EX-HN 12), and Fengchi (GB 20)-Yuye (EX-HN 13)-Jinjin (EX-HN 12). Factor analysis extracted 10 common factors for acupoint compatibility in treatment of aphasia with acupuncture and moxibustion.@*CONCLUSION@#In clinical treatment of aphasia with acupuncture and moxibustion, the local acupoints are preferred. The core acupoints include Lianquan (CV 23), Jinjin (EX-HN 12), Yuye (EX-HN 13), Baihui (GV 20) and Yamen (GV 15). The acupoint prescription is modified flexibly according to syndrome differentiation to enhance the therapeutic effect.

STAT3 as a candidate transcriptomic prognosticator of sepsis severity levels

Background@#Sepsis is a life-threatening multiple-organ dysfunction caused by a dysregulated host response to infection and is the leading cause of death in non-cardiac intensive care facilities. Early reliable prediction of sepsis outcomes leads to cost-efficient resource allocation and therapeutic strategies. However, there are still no reliable markers to predict the outcome of patients at the initial stage of sepsis. Analyzing transcription profiles enables researchers to predict early outcomes using transcripts and their expression patterns. Transcriptomic profiling of septic patients has been done recently; however, analysis of prognostic outcomes is still scarce.@*Objective@#This study aimed to determine transcriptional indicators that may be useful in the prognosis of the severity of sepsis.@*Methods@#This is a prospective cohort study of Filipino patients admitted for sepsis at the national tertiary referral hospital in Manila, Philippines. We conducted differentially expressed gene analysis, network analyses, and area under the curve study of publicly available datasets of surviving vs. non-surviving sepsis patients to identify candidate prognosticator markers. Quantitative PCR was used to characterize the expression of each marker. A model using ordinal logistic regression analysis was done to determine which among the markers can best predict the outcome of sepsis severity.@*Results@#We identified ACTB, RAC1, STAT3, and UBQLN1 as candidate mRNA prognosticators. The expression of STAT3, a gene involved in immunosuppression, is inversely correlated with the severity of sepsis.@*Conclusion@#Transcriptomic markers such as STAT3 can predict the severity of patients with sepsis. Early detection of its inverse expression may prompt early and more aggressive management of patients.

Analysis of Medication Rules of Traditional Chinese Medicine for Malaria Treatment Based on Data Mining / 中国医学科学杂志(英文版)

Objective To analyze the medication rules of traditional Chinese medicine (TCM) for malaria treatment.Methods Statistical analysis was conducted on the basic attributes of TCM drugs with regard to property, therapeutic methods, flavor, and meridian tropism. A complex network of TCM drug associations was constructed. Cluster analysis was applied to obtain the core drugs for malaria treatment. The Apriori algorithm was applied to analyze the association rules of these core drugs.Results A total of 357 herbs were used 3,194 times in 461 prescriptions for malaria treatment. Radix Glycyrrhizae (), Rhizoma Pinelliae (), Radix Bupleuri (), and Radix Dichroae () were the frequently used herbs through supplementing, exterior-releasing, heat-clearing, qi-rectifying, and damp-resolving therapeutic methods. Such herbs had warm, natural, and cold herbal properties; pungent, bitter, and sweet flavors; and spleen, lung, and stomach meridian tropisms. Cluster analysis showed 61 core drugs, including Radix Glycyrrhizae, Rhizoma Pinelliae, Radix Bupleuri, and Radix Scutellariae (). Apriori association rule analysis yielded 12 binomial rules (herb pairs) and 6 trinomial rules (herb combinations). Radix Bupleuri plus Radix Scutellariae was the core herbal pair for treating malaria. This pair could be combined with Rhizoma Atractylodis Macrocephalae () for treating warm or cold malaria, combined with Pericarpium Citri Reticulatae () or Radix Dichroae () for treating miasmic malaria, or combined with turtle shells () for treating malaria with splenomegaly.Conclusions TCM can be used to classify and treat malaria in accordance with the different stages of development. As the core herbal pair, Radix Bupleuri and Radix Scutellariae can be combined with other drugs to treat malaria with different syndrome types.

Medication rules of Chinese herbal compound prescriptions for treating angina in national patent database based on multiple data mining / 中国中药杂志

This study explored the medication rules of Chinese herbal compound prescriptions for the treatment of angina based on the Chinese herbal compound patents in the patent database of the China National Intellectual Property Administration. The data of eligible Chinese herbal compound patents for the treatment of angina were collected from the patent database of the China National Intellectual Property Administration from database inception to November 10, 2022, and subjected to data modeling, analysis of main syndromes, medication frequency analysis, cluster analysis, association rule analysis, and data visualization by using Excel 2021, IBM SPSS Statistics 26.0, IBM SPSS Modeler 18.0, Cytoscape 3.9.1, and Rstudio R 4.2.2.2 to explore the medication rules for angina. The study included 636 pieces of patent data for angina that met the inclusion criteria, involving 815 drugs, with a total frequency of 6 586. The most common main syndromes were blood stasis obstructing the heart syndrome(222, 34.91%) and Qi deficiency and blood stasis syndrome(112, 17.61%). The top 10 most frequently used drugs were Salviae Miltiorrhizae Radix et Rhizoma, Chuanxiong Rhizoma, Notoginseng Radix et Rhizoma, Astragali Radix, Angelicae Sinensis Radix, Carthami Flos, Glycyrrhizae Radix et Rhizoma, Ginseng Radix et Rhizoma, Borneolum Syntheticum, and Corydalis Rhizoma. High-frequency drugs included blood-activating and stasis-resolving drugs(1 197, 18.17%) and deficiency-tonifying drugs(809, 12.28%). Cluster analysis identified eight drug combinations, including five new prescriptions suitable for clinical use and new drug development, and three drug pairs. The core drug combination of Salviae Miltiorrhizae Radix et Rhizoma-Chuanxiong Rhizoma-Carthami Flos was identified through the complex co-occurrence network analysis of Chinese medicines. Association rule analysis yielded a total of 17 rules, including 13 drug pairs and 4 tripartite combinations. Common drug pairs included Salviae Miltiorrhizae Radix et Rhizoma-Chuanxiong Rhizoma(support degree 25.79%, confidence coefficient 69.49%, lift 1.30) and Salviae Miltiorrhizae Radix et Rhizoma-Notoginseng Radix et Rhizoma(support degree 22.01%, confidence coefficient 61.95%, lift 1.16). Common tripartite combinations included Salviae Miltiorrhizae Radix et Rhizoma-Chuanxiong Rhizoma-Astragali Radix(support degree 10.85%, confidence coefficient 73.40%, lift 1.37) and Salviae Miltiorrhizae Radix et Rhizoma-Chuanxiong Rhizoma-Notoginseng Radix et Rhizoma(support degree 10.69%, confidence coefficient 79.07%, lift 1.48). The results showed that the underlying pathogenesis of angina involved blood stasis obstructing the heart and Qi deficiency and blood stasis. The overall nature of the disease was characterized as asthenia in origin and sthenia in superficiality. In the prescription formulation, blood-activating and stasis-resolving drugs, such as Salviae Miltiorrhizae Radix et Rhizoma, Chuanxiong Rhizoma, and Carthami Flos were often used to resolve the excess manifestation, which were combined with tonifying drugs such as Astragali Radix, Angelicae Sinensis Radix, Glycyrrhizae Radix et Rhizoma, and Ginseng Radix et Rhizoma to reinforce the deficiency. The syndrome, pathogenesis, disease nature, and medication were consistent with clinical practice. Additionally, the new compound prescriptions and drug combinations derived from the multiple data mining in this study could provide references and insights for the clinical diagnosis and treatment of angina and the development of new drugs.

Prescription and medication rules of traditional Chinese medicine for prevention and treatment of diabetic microangiopathy based on literature mining / 中国中药杂志

This study explored the prescription and medication rules of traditional Chinese medicine(TCM) in the prevention and treatment of diabetic microangiopathy based on literature mining. Relevant literature on TCM against diabetic microangiopathy was searched and prescriptions were collected. Microsoft Excel 2021 software was used to establish a prescription database, and an analysis was conducted on the frequency, properties, flavors, meridian tropism, and efficacy classifications of drugs. Association rule analysis, cluster analysis, and factor analysis were performed using SPSS Modeler 18.0 and SPSS Statistics 26.0 software. The characteristic active components and mechanisms of action of medium-high frequency drugs in the analysis of medication rules were explored through li-terature mining. A total of 1 327 prescriptions were included in this study, involving 411 drugs, with a total frequency reaching 19 154 times. The top five high-frequency drugs were Astragali Radix, Angelicae Sinensis Radix, Poria, Salviae Miltiorrhizae Radix et Rhizoma, and Rehmanniae Radix. The cold and warm drugs were used in combination. Drugs were mainly sweet, followed by bitter and pungent, and acted on the liver meridian. The majority of drugs were effective in tonifying deficiency, clearing heat, activating blood, and resolving stasis. Association rule analysis identified the highly supported drug pair of Astragali Radix-Angelicae Sinensis Radix and the highly confident drug combination of Poria-Alismatis Rhizoma-Corni Fructus. The strongest correlation was found among Astragali Radix, Angelicae Sinensis Radix, Poria, and Salviae Miltiorrhizae Radix et Rhizoma through the complex network analysis. Cluster analysis identified nine categories of drug combinations, while factor analysis identified 16 common factors. The analysis of active components in high-frequency drugs for the treatment of diabetic microangiopathy revealed that these effective components mainly exerted their effects by inhibiting oxidative stress and suppressing inflammatory reactions. The study found that the pathogenesis of diabetic microangiopathy was primarily characterized by deficiency in origin, with a combination of deficiency and excess. Deficiency was manifested as Qi deficiency and blood deficiency, while excess as phlegm-heat and blood stasis. The key organ involved in the pathological changes was the liver. The treatment mainly focused on supplementing Qi and nourishing blood, supplemented by clearing heat, coo-ling blood, activating blood, and dredging collaterals. Commonly used formulas included Danggui Buxue Decoction, Liuwei Dihuang Pills, Erzhi Pills, and Buyang Huanwu Decoction. The mechanisms of action of high-frequency drugs in the treatment of diabetic microangiopathy were often related to the inhibition of oxidative stress and suppression of inflammatory reactions. These findings can provide references for the clinical treatment of diabetic microangiopathy and the development of targeted drugs.

Mechanisms of Chinese Medicine in Gastroesophageal Reflux Disease Treatment: Data Mining and Systematic Pharmacology Study / 中国结合医学杂志

OBJECTIVE@#To identify specific Chinese medicines (CMs) that may benefit patients with gastroesophageal reflux disease (GERD), and explore the action mechanism.@*METHODS@#Domestic and foreign literature on the treatment of GERD with CMs was searched and selected from China National Knowledge Infrastructure, China Science and Technology Journal Database, Wanfang Database, and PubMed from October 1, 2011 to October 1, 2021. Data from all eligible articles were extracted to establish the database of CMs for GERD. Apriori algorithm of data mining techniques was used to analyze the rules of herbs selection and core Chinese medicine formulas were identified. A system pharmacology approach was used to explore the action mechanism of these medicines.@*RESULTS@#A total of 278 prescriptions for GERD were analyzed, including 192 CMs. Results of Apriori algorithm indicated that Evodiae Fructus and Coptidis Rhizoma were the highest confidence combination. A total of 32 active ingredients and 66 targets were screened for the treatment of GERD. Enrichment analysis showed that the mechanisms of action mainly involved pathways in cancer, fluid shear stress and atherosclerosis, advanced glycation end product (AGE), the receptor for AGE signaling pathway in diabetic complications, bladder cancer, and rheumatoid arthritis.@*CONCLUSION@#Evodiae Fructus and Coptidis Rhizoma are the core drugs in the treatment of GERD and the potential mechanism of action of these medicines includes potential target and pathways.

Pelvic Injury Discriminative Model Based on Data Mining Algorithm / 法医学杂志

OBJECTIVES@#To reduce the dimension of characteristic information extracted from pelvic CT images by using principal component analysis (PCA) and partial least squares (PLS) methods. To establish a support vector machine (SVM) classification and identification model to identify if there is pelvic injury by the reduced dimension data and evaluate the feasibility of its application.@*METHODS@#Eighty percent of 146 normal and injured pelvic CT images were randomly selected as training set for model fitting, and the remaining 20% was used as testing set to verify the accuracy of the test, respectively. Through CT image input, preprocessing, feature extraction, feature information dimension reduction, feature selection, parameter selection, model establishment and model comparison, a discriminative model of pelvic injury was established.@*RESULTS@#The PLS dimension reduction method was better than the PCA method and the SVM model was better than the naive Bayesian classifier (NBC) model. The accuracy of the modeling set, leave-one-out cross validation and testing set of the SVM classification model based on 12 PLS factors was 100%, 100% and 93.33%, respectively.@*CONCLUSIONS@#In the evaluation of pelvic injury, the pelvic injury data mining model based on CT images reaches high accuracy, which lays a foundation for automatic and rapid identification of pelvic injuries.

Data Mining Study on Prescription Patterns of Different Dosage Forms of Chinese Herbal Medicines for Treating and Improving Immune-Inflammatory Indices in Patients with Rheumatoid Arthritis / 中国结合医学杂志

OBJECTIVE@#To explore the prescription patterns of different dosage forms of Chinese herbal medicines (CHMs) for the treatment of rheumatoid arthritis (RA) and their effects on immune-inflammatory indices.@*METHODS@#Clinical data were collected from patients with RA in 4 hospitals (3 Class A comprehensive hospitals and 1 Class B comprehensive hospital) in Anhui Province, China, from August 2012 to June 2018 via the electronic medical record gathering system. Following extraction of prescription information, each prescribed herb was quantified and standardized according to the knowledge base to establish a database of RA treatment formulae. The medical records were divided into the granules group and decoction pieces group. Core herbs and their combination patterns were obtained from the two groups of cases using Liquorice software. Changes in immune-inflammatory and hepatic and renal function indices were compared between the two groups using SPSS 23.0 software. The Aprior module of SPSS Clementine 11.1 software was applied to analyse the correlation between CHMs and improvement in indices. Finally, the ORACLE 10 g tool was used to evaluate the random walk model of the immune-inflammatory indices between the two groups.@*RESULTS@#(1) We retrospectively analysed 35,898 prescriptions for 6,829 patients with RA who received CHM treatment. There were 3,816 patients in the granules group and 3,013 in the decoction pieces group. (2) The core herbs were Pi (Spleen)-strengthening and dampness-resolving drugs, blood-activating and stasis-resolving drugs, wind/dampness-dispelling drugs and heat-clearing and detoxifying drugs. (3) Both dosage forms could improve immune-inflammatory indices in RA patients, with similar efficacy and no influence on hepatic or renal function. (4) Herba Siegesbeckiae and Oldenlandia had a stronger association with immune-inflammatory indices in the two groups. (5) The immune-inflammatory indices showed obvious improvement after treatment with granules and decoction pieces of CHMs, and there were long range correlations between the comprehensive evaluation indices and interventions.@*CONCLUSIONS@#The principal CHM treatment methods for RA in four hospitals in Anhui Province are strengthening Pi and resolving dampness, activating blood and resolving stasis, dispelling wind/dampness and clearing heat. Granules and decoction pieces of CHMs have similar efficacy in improving immune-inflammatory indices in RA patients and could be used as treatment options for RA.

Screening and identification of key genes ATP1B3 and ENAH in the progression of hepatocellular carcinoma: based on data mining and clinical validation / 南方医科大学学报

OBJECTIVE@#To explore the marker genes correlated with the prognosis, progression and clinical diagnosis of hepatocellular carcinoma (HCC) based on bioinformatics methods.@*METHODS@#The TCGA-LIHC, GSE84432, GSE143233 and GSE63898 datasets from The Cancer Genome Atlas (TCGA) and Gene Expression Omnibus (GEO) were analyzed. The differentially expressed genes (DEGs) shared by different disease types were obtained using GEO2R and edge R packages, and Gene Ontology (GO) and Kyoto Gene and Genome Encyclopedia (KEGG) enrichment analyses of the DEGs were performed. The expression levels of these DEGs in normal and cancerous tissues were verified in TCGA-LIHC to identify the upregulated genes in HCC. Survival analysis, receiver-operating characteristic (ROC) curve analysis, and correlation analysis between the key genes and the clinical features of the patients were carried out using the R language. The differential expressions of 15 key genes were verified in clinical samples of HCC and adjacent tissues using RT-qPCR.@*RESULTS@#A total of 118 common DEGs were obtained in the database, and among them two genes, namely ATPase Na +/K + transport subunit beta 3 (ATP1B3) and actin regulator (ENAH), showed increased expressions with disease progression. Survival analysis combined with the TCGA-LIHC dataset suggested that high expressions of ATP1B3 and ENAH were both significantly correlated with a poor prognosis of HCC patients (P < 0.05), and their AUC values were 0.821 and 0.933, respectively. A high expression of ATP1B3 was correlated with T stage, pathological stage and pathological grade of the tumors (P < 0.05), while that of ENAH was associated only with an advanced tumor grade (P < 0.05). The results of RT-qPCR showed that ATP1B3 and ENAH were both significantly upregulated in clinical HCC tissues (P < 0.05).@*CONCLUSION@#ATPIB3 and ENAH are both upregulated in HCC, and their high expressions may serve as biomarkers of progression of liver diseases and a poor prognosis of HCC.

Minería de datos para la evaluación del riesgo de malignidad en pacientes con nódulos tiroideos con estudio citológico Bethesda IV / Risk of malignancy evaluation through data mining technic in patients with thyroid nodules with cytology study Bethesda IV

Introducción: en el campo de la salud, cada decisión representa datos, y las técnicas de minería de datos han empezado a ser una metodología prometedora para el análisis de esta información, especialmente en el diseño de los modelos predictivos. Métodos: estudio observacional analítico de pacientes mayores de 15 años, con reporte de punción de aspiración con aguja fina con estudio Bethesda IV, sometidos a manejo quirúrgico en el Hospital de San José de Bogotá. Los datos recogidos de los pacientes se incluyeron en tres grupos: la información sociodemográfica y clínica, los hallazgos en la citología y los reportes de la ecografía. Se realizó el análisis mediante Naive-Bayes, árbol de decisión y redes neuronales. Se usó la herramienta Weka versión 3.8.2. Resultados: de los 427 pacientes, 195 tuvieron resultados de patología de carcinoma de tiroides (45,6 %). Se evidenciaron mejores resultados usando la validación cruzada (10 fold) comparado con partición (66 %), la técnica de Bayes tuvo mejores resultados de clasificación correcta (91,1 %), comparado con la técnica de árbol (87,8 %) y la red neuronal (88,2 %). Conclusiones: el uso de la técnica de Naive Bayes muestra una importante exactitud para determinar la predicción de riesgo de malignidad en los pacientes con estudio citológico Bethesda IV, lo cual permitiría orientar de forma adecuada el manejo quirúrgico de los pacientes

Introduction: In the health field, each decision represents data, and data mining techniques have begun to be a promising methodology for the analysis of this information, especially in the design of predictive models. Methods: Analytical observational study; patients older than 15 years with a report of Bethesda IV after a fine needle aspiration biopsy that undergoing surgical management at the Hospital de San José in Bogotá. The data collected from those patients were included in three groups: sociodemographic-clinical information, cytology findings, and ultrasound reports. Analysis was performed using three technics: Naive Bayes, decision trees, and neural networks. Weka tool version 3.8.2 was used. Results: 195 patients out of 427, had a thyroid carcinoma pathology (45.6%). Better results were evidenced using cross-validation (10 fold) compared with a partition (66%), the Bayes technique had better results of correct classification (91.1%), than the tree technique (87.8%) and neural network (88.2%). Conclusions: The use of the Naive Bayes technique shows an important accuracy to determine the prediction of risk of malignancy in patients with a Bethesda IV cytological study, which would allow an adequate guide to the surgical management of patients.

Data mining-based analysis of formulation rules for prescriptions containing herbal pair Acori Tatarinowii Rhizoma-Polygalae Radix / 中国中药杂志

By the in-depth excavation of prescriptions containing herbal pair Acori Tatarinowii Rhizoma-Polygalae Radix in the Dictionary of Traditional Chinese Medicine Prescriptions, this study analyzed their formulation rules, so as to provide reference for their clinical application and new drug development. First, the prescriptions containing Acori Tatarinowii Rhizoma-Polygalae Radix were collected from the Dictionary of Traditional Chinese Medicine Prescriptions, and their indications, herbal compatibility, and dosage forms were analyzed statistically using the Traditional Chinese Medicine Inheritance Support System(TCMISS). Meanwhile, the formulation rules and common dosage forms for the top four indications(amnesia, palpitation, mania, and epilepsy) sorted by frequency were analyzed with Apriori algorithm. A total of 507 prescriptions containing Acori Tatarinowii Rhizoma-Polygalae Radix were screened out, involving 15 indications(frequency>10) like amnesia, palpitation, mania, and epilepsy. There were 30 commonly used Chinese herbs(frequency≥60), with the Qi-tonifying herbs(Ginseng Radix et Rhizoma and Glycyrrhizae Radix et Rhizome), mind-tranquilizing herbs(Poria and Poria cum Radix Pini), and Yin-nourishing herbs(Angelicae Sinensis Radix and Ophiopogonis Radix) being the core ones. The commonly used dosage forms were honey pill, paste pill, decoction, and powder. These have indicated that the herbal pair Acori Tatarinowii Rhizoma-Polygalae Radix is often combined with Qi-tonifying, Yin-nourishing, and mind-tranquilizing herbs for the treatment of "heart or brain diseases" caused by phlegm production due to spleen deficiency, Qi and blood deficiency, and phlegm-turbidity blocking orifice. In the treatment of amnesia, supplementing essence and replenishing marrow are considered on the basis of tonifying Qi, nourishing Yin, and tranquilizing mind. In the treatment of palpitation and mania, tranquilizing mind is emphasized. In the treatment of epilepsy, the emphasis is placed on resolving phlegm, extinguishing wind, and stopping convulsion.

Formulation regularity of traditional Chinese medicine in treatment of sinusitis based on data mining / 中国中药杂志

Based on the Drugdataexpy and the prescription modern application database, this study explored the formulation regularity of ancient and modern prescriptions for the treatment of sinusitis. The Chinese medicinal prescriptions for the treatment of sinusitis with various syndromes were retrieved from the above databases and the corresponding formulation regularity was investigated by frequency analysis, association rule analysis, and factor analysis. Eighty-seven Chinese medicinal prescriptions were included, involving five syndrome types of sinusitis and 160 Chinese medicine, which were mainly effective in releasing exterior, clearing heat, and tonifying deficiency, and acted on the lung meridian due to cold and warm nature and pungent and bitter flavor or on the spleen meridian due to warm nature and pungent flavor. Seventeen core Chinese medicine were screened out by topological data analysis, including Angelicae Dahuricae Radix, Magnoliae Flos, Glycyrrhizae Radix et Rhizoma, Xanthii Fructus, and Scutellariae Radix. Chinese medicine such as Magnoliae Flos, Angelicae Dahuricae Radix, and Xanthii Fructus were commonly used in the treatment of sinusitis of wind-heat in the lung meridian, while the combination of Glycyrrhizae Radix et Rhizoma, Magnoliae Flos, Angelicae Dahuricae Radix, Chuanxiong Rhizoma, etc. was the key compatibility in treating sinusitis of dampness-heat in the spleen and stomach. Six common factors were extracted from the factor analysis of the above two syndrome types. The findings indicate that the exterior-releasing, heat-clearing, and deficiency-tonifying Chinese medicine with cold and warm nature and pungent flavor are preferential options for the clinical treatment of sinusitis. Treatment should be based on syndrome differentiation and key therapeutic principles should be followed.