Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 20 de 522
Filter
1.
China Pharmacy ; (12): 225-229, 2022.
Article in Chinese | WPRIM | ID: wpr-913115

ABSTRACT

OBJE CTIVE To mine and analyze t he cardiac adverse drug reaction (ADR)signals induced by febuxostat in post-marketing experience ,and to provide reference for rational drug use in clinic. METHODS Reporting odds ratio (ROR) method was used to mine the ADR signals induced by febuxostat from the FDA Adverse Event Reporting System during the first quarter of 2009 to the fourth quarter of 2020;the information of cardiac disease signals was counted and analyzed. RESULTS A total of 209 ADR signals were detected in 8 282 adverse drug event (ADE)reports with febuxostat as the primary suspected drug , involving 27 cardiac signals and 754 ADE reports. The most reported signals were symptoms (262 reports),including dizziness , oedema peripheral,chest pain ,palpitations and gravitational oedema and so on ,followed by coronary atherosclerotic heart disease signal,heart failure signal ,arrhythmia signal ,sudden cardiac death signal (233,157,90,12 reports,respectively). More than half of the signals were mentioned in the drug instructions ,while the unmentioned signals were mainly kinds of cardiac failure , arrhythmia and extrasystoles ,etc. The patients with cardiac ADEs who received febuxostat were more male than female ,and the age was 60 and over ;the drug dosage was mostly 40 mg/d or 80 mg/d as recommended in the drug instructions ,and cardiac ADEs mostly occurred within 1 month of medication. CONCLUSIONS Routine attention should be paid to the cardiac safety of febuxostat during medication ,further evaluation and validation of febuxostat-induced cardiac ADR signals are still needed.

2.
Acta de Otorrinolaringología Cir. Cabeza cuello. ; 50(1): 36-44, 2022. ilus, tab, graf
Article in Spanish | LILACS, COLNAL | ID: biblio-1363378

ABSTRACT

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.


Subject(s)
Humans , Data Mining
3.
Arq. bras. med. vet. zootec. (Online) ; 73(6): 1391-1402, Nov.-Dec. 2021. tab, graf, ilus
Article in English | LILACS, VETINDEX | ID: biblio-1355689

ABSTRACT

This study was carried out for two purposes: comparing performances of Regression Tree and Automatic Linear Modeling and determining optimum sample size for these methods under different experimental conditions. A comprehensive Monte Carlo Simulation Study was designed for these purposes. Results of simulation study showed that percentage of explained variation estimates of both Regression Tree and Automatic Linear Modeling was influenced by sample size, number of variables, and structure of variance-covariance matrix. Automatic Linear Modeling had higher performance than Regression Tree under all experimental conditions. It was concluded that the Regression Tree required much larger samples to make stable estimates when comparing to Automatic Linear Modeling.(AU)


Este estudo foi realizado com dois objetivos: comparar os desempenhos da Árvore de Regressão e da Modelagem Linear Automática e determinar o tamanho ideal da amostra para estes métodos sob diferentes condições experimentais. Um abrangente Estudo de Simulação de Monte Carlo foi projetado para estes propósitos. Os resultados do estudo de simulação mostraram que a porcentagem de estimativas de variação explicada tanto da Árvore de Regressão como da Modelagem Linear Automática foi influenciada pelo tamanho da amostra, número de variáveis e estrutura da matriz de variância-covariância. A Modelagem Linear Automática teve um desempenho superior ao da Árvore de Regressão em todas as condições experimentais. Concluiu-se que a Árvore de Regressão exigia amostras muito maiores para fazer estimativas estáveis quando comparada à Modelagem Linear Automática.(AU)


Subject(s)
Linear Models , Monte Carlo Method , Regression Analysis , Data Analysis , Simulation Technique/methods
4.
Rev. bras. med. esporte ; 27(spe2): 20-22, Apr.-June 2021. tab, graf
Article in English | LILACS | ID: biblio-1280090

ABSTRACT

ABSTRACT In 2008, our country successfully held the Olympic Games, where China won the most gold medals. After these Olympic Games, China has also become a world sports power. Our country's table tennis, diving, skating and other sports are also in the leading ranks in the world. In this study, according to the current training status of Chinese football players, we used data mining algorithm to analyze the unawareness of acceleration and speed of Chinese athletes in the running process. In this study, these indicators were quantified and analyzed, which has successfully promoted the training level of Chinese football players.


RESUMO Em 2008, nosso país sediou os Jogos Olímpicos, em que a China ganhou a maior parte das medalhas de ouro. Após os Jogos Olímpicos, a China também se tornou uma potência esportiva mundial. O tênis de mesa, o salto ornamental, a patinação e outros esportes também estão em posições de liderança. Neste estudo, de acordo com o atual estado de treinamento dos jogadores de futebol chineses, usamos o algoritmo de mineração de dados para analisar a falta de aceleração e velocidade dos atletas chineses na corrida. No estudo, esses indicadores foram quantificados e analisados, elevando o nível do treinamento os jogadores de futebol chineses.


RESUMEN En 2008, China celebró con éxito los Juegos Olímpicos.China ganó la mayoría de las medallas de oro en los Juegos Olímpicos.Después de los Juegos Olímpicos, China también se ha convertido en una potencia deportiva mundial.El tenis de mesa, el buceo y el patinaje sobre hielo en China también están en la posición de liderazgo en el mundo.De acuerdo con la situación actual del entrenamiento de los jugadores de Fútbol en nuestro país, este trabajo analiza la falta de percepción de la aceleración y velocidad de los jugadores de Fútbol en el proceso de correr con el algoritmo de minería.Y en los resultados de la investigación, el análisis cuantitativo de estos indicadores ha mejorado con éxito el nivel de entrenamiento de los jugadores de fútbol chinos.


Subject(s)
Humans , Running/physiology , Soccer/physiology , Velocity Measurement/methods , Athletic Performance/physiology , Algorithms
5.
Rev. peru. biol. (Impr.) ; 28(1): e17867, Jan-Mar 2021. tab, graf
Article in English | LILACS-Express | LILACS | ID: biblio-1289877

ABSTRACT

Abstract Genetic diversity is an important component of biodiversity, and it is crucial for current efforts to protect and sustainably manage several organisms and habitats. As far as we know, there is only one work describing Peruvian genetic information stored in public databases. We aimed to update this previous work searching in four public databases that stored digital sequence information: Nucleotide, BioProject, PATRIC, BOLD. With this information, we comment on the contribution of Peruvian institutions during recent years. In Nucleotide, the largest database, Bacteria are the most sequenced organisms by Peruvian institutions (70.60%), pathogenic bacteria such as Pasteurella multocida, Neisseria meningitidis, and Vibrio parahaemolyticus were the most abundant. We found no sequence records from the Archaea domain. In BioProject, the most common sequence belongs to Salmonella enterica subsp. enterica serovar Infantis. In PATRIC, a database of pathogenic agents, Mycobacterium tuberculosis and Yersinia pestis had the highest number of entries. Finally, in BOLD, an exclusively Eukaryotic database, Chordata (Aves and Actinopterygii), Angiospermae, and Arthropoda (Insecta, and Arachnida) were the most frequent records. Our results would indicate research preferences of Peruvian institutions, focusing on infectious diseases and some Eukaryotic phyla. Although there has been a significant increase of DNA information submitted by Peruvian institutions since the last report, the genetic diversity reflected in these databases remains inconsistent with the diversity in the country. More efforts must be made to obtain genetic information from more underestimated taxonomic groups and to promote more genetic research in regional Peruvian institutions.


Resumen La diversidad genética es una componente importante de la biodiversidad y es crucial para los esfuerzos actuales de proteger y gestionar de manera sostenible varios organismos y hábitats. Hasta donde sabemos, solo hay un trabajo que describe la información genética peruana almacenada en bases de datos públicas. Nuestro objetivo fue actualizar este trabajo previo buscando en cuatro bases de datos públicas que almacenaban información de secuencias digitales: Nucleotide, BioProject, PATRIC, BOLD. Con esta información analizamos la contribución de las instituciones peruanas durante los últimos años. En Nucleotide, la base de datos más grande, las bacterias fueron los organismos más secuenciados por las instituciones peruanas (70.60%), las bacterias patógenas como Pasteurella multocida, Neisseria meningitidis y Vibrio parahaemolyticus fueron las más abundantes. No encontramos registros de secuencias del dominio Archaea. En BioProject, la secuencia más común pertenece a Salmonella enterica subsp. enterica serovar Infantis. En PATRIC, una base de datos de agentes patógenos, Mycobacterium tuberculosis y Yersinia pestis tuvieron el mayor número de entradas. Finalmente, en BOLD, una base de datos exclusivamente eucariota, Chordata (Aves y Actinopterygii), Angiospermae y Arthropoda (Insecta y Arachnida) fueron los registros más frecuentes. Nuestros resultados indicarían las preferencias de investigación de las instituciones peruanas, centrándose en enfermedades infecciosas y algunos filos eucariotas. Aunque ha habido un aumento significativo de la información de ADN enviada por las instituciones peruanas desde el último informe, la diversidad genética reflejada en estas bases de datos sigue siendo inconsistente con la diversidad del país. Se deben realizar más esfuerzos para obtener información genética de grupos taxonómicos más subestimados y promover más investigación genética en las instituciones regionales peruanas.

6.
Rev. bras. estud. popul ; 38: e0152, 2021. tab, graf
Article in Portuguese | LILACS-Express | LILACS | ID: biblio-1288522

ABSTRACT

Resumo O artigo identifica e discute fatores escolares que mais influenciam a qualidade do ensino médio no Brasil: rendimento escolar, infraestrutura ou prática docente. Foram utilizados os dados do Censo Escolar e do Exame Nacional do Ensino Médio. A técnica de mineração de dados levantou características-chave para o bom desempenho escolar. Um modelo de regressão logística identificou os fatores escolares que mais influenciam o desempenho escolar dos alunos da rede pública de ensino médio regular no Brasil. Investigaram-se, também, os diferenciais de desempenho escolar de alunos do ensino médio segundo o tipo de escola e tipo de ensino, bem como os diferenciais interestaduais, considerando o sistema público de ensino médio regular. Os resultados apontam que alunos de escolas estaduais estão em desvantagem e que os de escolas privadas e federais possuem desempenho semelhante, quando considerado apenas o tipo de escola. Ao se levar em conta também o tipo de ensino, os alunos do ensino regular das escolas federais apresentam o melhor desempenho, cerca de 1,3 vez maior do que o dos alunos das escolas estaduais. Não há grandes disparidades interestaduais, embora os resultados apontem diferenciação regional. Dentre os fatores escolares, a qualificação docente se mostrou o fator mais impactante no desempenho escolar.


Abstract This paper identifies and discusses school factors that most influence the quality of secondary education in Brazil: school performance, infrastructure, and teaching practice. We used data from the School Census and the National High School Exam (ENEM). The data mining technique has raised key characteristics for good school performance. A logistic regression model identified school characteristics that most influence the school performance of public high school students in Brazil. School performance was also investigated according to the type of school and type of education; and interstate differentials, considering the regular public high school system. Results show that students from state schools are at a disadvantage and that those from private and federal schools have similar performance when considering only the type of school. When considering the type of education as well, regular school students from federal schools have the best performance, about 1.3 times higher than that of state schools students. There are no major interstate disparities, although the results point to regional differentiation. Among school factors, teacher qualification proved to be the most impacting factor on school performance.


Resumen El presente artículo identifica y discute los factores escolares que más influyen en la calidad de la educación secundaria en Brasil: desempeño escolar, infraestructura o práctica docente. Para ello se utilizaron datos del censo escolar y del examen nacional de secundaria. La técnica de minería de datos ha planteado características clave para un buen desempeño escolar, y un modelo de regresión logística identificó los factores escolares que más influyen en el desempeño escolar de los estudiantes de la escuela secundaria pública en Brasil. También se investigaron las diferencias de desempeño escolar de los estudiantes de secundaria según el tipo de escuela y el tipo de educación, y diferenciales interestatales, considerando el sistema público de la escuela secundaria regular. Los resultados muestran que los estudiantes de las escuelas estatales están en desventaja y que los de las escuelas privadas y federales tienen un desempeño similar al considerar solo el tipo de escuela, pero al considerar también el tipo de educación los estudiantes de escuelas regulares de las escuelas federales tienen el mejor desempeño, aproximadamente 1,3 veces más alto que el de los estudiantes de las escuelas estatales. No hay grandes disparidades interestatales, aunque los resultados apuntan a una diferenciación regional. Entre los factores escolares, la calificación de los maestros resultó ser el factor más impactante en el desempeño escolar.

7.
Rev. baiana enferm ; 35: e38740, 2021. tab, graf
Article in Portuguese | LILACS, BDENF | ID: biblio-1155739

ABSTRACT

Objetivo analisar as publicações de usuários do Twitter direcionadas à campanha de valorização da Enfermagem, impulsionadas pelos termos #LuteComoUmaEnfermeira e #EnfermagemEuValorizo. Método pesquisa quantitativa, fundamentada nos métodos digitais. A busca foi realizada utilizando as hashtags #LuteComoUmaEnfermeira e #EnfermagemEuValorizo para extração de tweets. Foram selecionados para análise 2.613 tweets. Resultados 22,5% das publicações localizam-se na região Sudeste do país e 9,3% na região Nordeste. Houve mais de 18 mil interações (curtidas e compartilhamentos), sendo que os autores das postagens atingem um público estimado de cerca 7 milhões de pessoas. O conteúdo das postagens versava principalmente sobre a regulamentação da jornada de trabalho, Equipamentos de Proteção Individual, combate ao COVID-19, defesa da força de trabalho majoritariamente feminina e luta por direitos. Conclusão a realização da campanha virtual teve visibilidade importante no território nacional e apresentou grande visibilidade à profissão em número e alcance na Internet.


Objetivo analizar las publicaciones de los usuarios de Twitter dirigidas a la campaña de valoración de la Enfermería, impulsada por los términos #LuteComoUmaEnfermeira y #EnfermagemEuValorizo. Método investigación cuantitativa, basada en métodos digitales. La búsqueda se llevó a cabo utilizando los hashtags #LuteComoUmaEnfermeira y #EnfermagemEuValorizo para la extracción de tweets. Resultados el 22,5% de las publicaciones se localizan en la región Sudeste del país y el 9,3% en la región Nordeste. Hubo más de 18.000 interacciones (curtidas y compartidas), y los autores de los mensajes llegaron a un público estimado de unos 7 millones de personas. El contenido de los puestos se refería principalmente a la regulación de los horarios de trabajo, el equipo de protección personal, la lucha contra el COVID-19, la defensa de la fuerza de trabajo mayoritariamente femenina y la lucha por los derechos. Conclusión la realización de la campaña virtual tuvo una importante visibilidad en el territorio nacional y presentó una gran visibilidad a la profesión en número y alcance en Internet.


Objective analyze the publications of Twitter users directed to the campaign of valuation of Nursing, driven by the terms #LuteComoUmaEnfermeira and #EnfermagemEuValorizo. Method quantitative research, based on digital methods. The search was realized using the hashtags #LuteComoUmaEnfermeira and #EnfermagemEuValorizo for tweets extraction. 2,613 tweets were selected for analysis. Results 22.5% of publications are located in the Brazilian Southeast region and 9.3% in the Northeast region. There were more than 18,000 interactions (likes and shares), and the authors of the posts reach an estimated audience of about 7 million people). The content of the posts mainly related to the regulation of working hours, Personal Protective Equipment, the fight against COVID-19, the defense of the majority female workforce and the fight for rights. Conclusion the realization of the virtual campaign had important visibility in the national territory and presented great visibility to the profession in number and reach on the Internet.


Subject(s)
Humans , Coronavirus Infections , Data Mining , Social Media , COVID-19/history , Nurse Practitioners , Nursing Informatics
8.
Article in Chinese | WPRIM | ID: wpr-847137

ABSTRACT

BACKGROUND: The possible causes of osteochondroarthritis have been identified as cartilage degeneration, autophagy, mechanical changes, cartilage hypertrophy, internal immunity, oxidative stress, and pain. OBJECTIVE: To explore the pathogenesis of osteoarthritis that is a degenerative disease of articular cartilage caused by a variety of factors. METHODS: GSE51588 and GSE19060, the chip data sets related to osteoarthritis in GEO database, were retrieved, and differential genes were analyzed with the help of R language. miRDB, miRTarbase and starBase databases were used to predict the targeted miRNAs of osteoarthritis related mRNAs respectively, and miRNA-mRNA regulatory network was constructed. GeneMANIA and FUNRICH were used to analyze the mRNAs mentioned in the regulatory network. lncRNA-miRNA-mRNA ceRNA regulatory network was constructed by retrieving LncRNADisease database and osteoarthiritis related IncRNA, using Starbase database to predict their miRNAs. RESULTS AND CONCLUSION: A total of 11 significantly differentially expressed mRNAs were screened by R language analysis. Through the cross-mapping of miRDB, miRTarbase and starBase and the predicted targeted miRNAs and the above 11 differentially expressed mRNAs, 290 miRNAs were identified to be involved in the construction of the miRNA-mRNA regulatory network related to osteoarthritis. Fifteen incRNAs related to the pathogenesis of osteoarthritis were retrieved in the LncRNADisease database, 270 miRNAs were predicted using Starbase database, and the lncRNA-miRNA-mRNA ceRNA regulatory network consisting of 5 IncRNAs, 106 miRNAs and 8 mRNAs was constructed. Seven major biological processes and two major signaling pathways were obtained through FUNRICH. Finding from our further analysis indicate that differentially expressed mRNA is mainly related to the biological processes of protein metabolism, cell communication, signal transduction, immune response, metabolism, energy pathway and cell growth. By participating in the pathogenesis of osteoarthritis, it provides ideas for the determination of therapeutic targets for osteoarthritis.

9.
Article in Chinese | WPRIM | ID: wpr-921758

ABSTRACT

Solid preparations account for more than 50% of traditional Chinese medicines(TCM). TCM powder is an important raw material for solid preparations of TCM. Its powder properties directly affect the quality of solid preparations, and even clinical safety and effectiveness. Particle design technology based on the characteristics of powder in TCM is an important means to improve and enhance the quality of solid preparations. This study summarized the relevant principles, methods, characteristics, classification, equipment, and other elements of particle design technology in recent years, analyzed the difficulties in its application in the field of TCM powder, and proposed the strategies in conjunction with the development of computer data mining. The present study is expected to provide a reference for the suitability of particle design in the field of TCM powder.


Subject(s)
Drugs, Chinese Herbal , Medicine, Chinese Traditional , Powders , Technology
10.
Article in Chinese | WPRIM | ID: wpr-921667

ABSTRACT

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.


Subject(s)
Data Mining , Drugs, Chinese Herbal , Humans , Medicine, Chinese Traditional , Prescriptions , Syndrome
11.
Chinese Acupuncture & Moxibustion ; (12): 1399-1403, 2021.
Article in Chinese | WPRIM | ID: wpr-921065

ABSTRACT

OBJECTIVE@#To explore the characteristics and rule of clinical acupoint selection in treatment of acute exacerbation of chronic obstructive pulmonary disease (AECOPD).@*METHODS@#The clinical articles of acupuncture in treatment of AECOPD were retrieved from the databases of PubMed, EMbase, Cochrane Library, Web of Science, CNKI, Wanfang, VIP and SinoMed, from the date of establishment to July 15, 2020. The articles were screened in accordance with the inclusion and exclusion criteria, the prescriptions of acupuncture and the relevant information of the acupoints and meridians were extracted to establish the database. The data mining methods i.e. Apriori association rule analysis and cluster analysis were used to analyse the using frequency, involving meridians, acupoint distributions, association rules and cluster of selected acupoints.@*RESULTS@#A total of 54 articles were included, 67 acupuncture prescriptions were extracted, 69 acupoints were involved and the total using frequency was 475 times. The top 5 acupoints in frequency were Danzhong (CV 17), Feishu (BL 13), Zusanli (ST 36), Fenglong (ST 40) and Dingchuan (EX-B1). The main involved meridians were bladder meridian of foot-@*CONCLUSION@#The local acupoints and acupoints along meridians are the main acupuncture prescriptions for AECOPD, and the special points are the predominated selection. The acupoint compatibility embodies the therapeutic principle of "strengthening vital


Subject(s)
Acupuncture Points , Acupuncture Therapy , Data Mining , Humans , Meridians , Pulmonary Disease, Chronic Obstructive/therapy
12.
Chinese Acupuncture & Moxibustion ; (12): 1166-1170, 2021.
Article in Chinese | WPRIM | ID: wpr-921027

ABSTRACT

OBJECTIVE@#To analyze the rules of acupoint and medication selection of acupoint application therapy for functional constipation (FC) by data mining technology.@*METHODS@#The clinical research literature regarding acupoint application therapy for FC from published to February 26, 2020 was searched in CNKI, VIP, Wanfang, SinoMed and PubMed. The prescriptions were extracted, and by using SPSS24.0 and SPSS Modeler14.0 software, the use of high-frequency acupoints and medication was summarized. The association rule analysis, cluster analysis and core prescription analysis of acupoints and medication were analyzed.@*RESULTS@#A total of 122 prescriptions of acupoint application therapy were included, involving 32 acupoints. The core prescription of acupoints was Tianshu (ST 25), Dachangshu (BL 25), Shenque (CV 8) and Guanyuan (CV 4). The high-frequency meridians mainly included conception vessel, @*CONCLUSION@#The use of local acupoint and regulating-


Subject(s)
Acupuncture Points , Acupuncture Therapy , Constipation/drug therapy , Data Mining , Humans , Meridians
13.
Article in Chinese | WPRIM | ID: wpr-912438

ABSTRACT

With the development and application of high-throughput sequencing and multi-omics techniques, more and more biomarkers have been excavated and used in disease diagnosis, risk stratification, treatment response evaluation and prognosis predication. Machine learning has certain advantages in mining and evaluating of tumor markers due to the capacity of dealing with complicated data and building models. This article summarized common machine learning methods, and detailed current applications of machine learning in mining of tumor markers. Additionally, our review aimed to provide the advantages and disadvantages of different machine learning methods in mining of tumor markers.

14.
Article in Chinese | WPRIM | ID: wpr-879061

ABSTRACT

To explore prescription medication regularity in the treatment of Alzheimer's disease with traditional Chinese medicine(TCM). With Alzheimer's disease or senile dementia as the subject, collecting and sorting out the journal papers in CNKI were collected as the data source to establish the literature research database of Alzheimer's disease prescriptions, and then the association rule analysis, factor analysis and systematic cluster analysis on the included TCM were conducted. Among the 113 prescriptions included in the standard, the single herb Acori Tatarinowii Rhizoma was the most common. The herbs were mainly warm and flat among four pro-perties, mainly sweet, bitter and spicy among five flavors. The drugs were mainly distributed in five internal organs, and the most commonly used drugs were deficiency tonifying drugs as well as blood activating and stasis removing drugs. In the association rule analysis, it was found that there were 6 drug pairs with the highest association strength. Eight common factors were extracted from the factor analysis, and they were classified into 6 categories in the systematic cluster analysis. The results have shown that the overall principles in treating Alzheimer's disease with modern Chinese medicine are tonifying deficiency, invigorating circulation, activating blood and dispelling phlegm.


Subject(s)
Alzheimer Disease/drug therapy , Data Mining , Drugs, Chinese Herbal/therapeutic use , Humans , Medicine, Chinese Traditional , Prescriptions
15.
Article in Chinese | WPRIM | ID: wpr-877680

ABSTRACT

Based on the data mining technology, the rules of acupoint selection and prescription were analyzed for impotence treated with acupuncture and moxibustion in ancient recorded in


Subject(s)
Acupuncture Points , Acupuncture Therapy , Data Mining , Erectile Dysfunction , Humans , Male , Meridians , Moxibustion , Technology
16.
Article in Chinese | WPRIM | ID: wpr-877620

ABSTRACT

OBJECTIVE@#To explore the rule of point selection in treatment of cerebral palsy with acupuncture in preschool children.@*METHODS@#Based on the electronic medical records of Xi'an Encephalopathy Hospital of TCM, through structuring medical record text, acupuncture prescriptions were extracted. Using the data mining tools of the ancient and modern medical record cloud platform V2.2.3 and the clinical effective prescription and molecular mechanism analysis system of traditional Chinese medicine V2.0, the cluster analysis and complex network analysis were conducted on acupuncture prescriptions.@*RESULTS@#Of 1584 acupuncture prescriptions for cerebral palsy in children, there were 84 acupoints and stimulating areas of scalp acupuncture, of which, foot-motor-sensory area, balance area and Sanyinjiao (SP 6) were the top 3 acupoints with the highest use rate. With cluster analysis, 5 groups of common supplementary acupoints and stimulating areas were found, named, Weizhong (BL 40) and Waiguan (TE 5), Shousanli (LI 10), Xingjian (LR 2), Xuanzhong (GB 39) and Chengfu (BL 36), foot-motor-sensory area, balance area and Sanyinjiao (SP 6), Xuehai (SP 10) and Fenglong (ST 40), Pishu (BL 20), motor area and Yanglingquan (GB 34). With complex network analysis on core prescriptions, 13 core acupoints and stimulating areas of scalp acupuncture were obtained, including 3 core main points, i.e. Sanyinjiao (SP 6), balance area and foot-motor-sensory area and 10 sub-core points, i.e. Taichong (LR 3), motor area, Xuehai (SP 10), Ganshu (BL 18), Pishu (BL 20), Yanglingquan (GB 34), Sishencong (EX-HN 1), Baihui (GV 20), Fengchi (GB 20) and Shenshu (BL 23).@*CONCLUSION@#In treatment of acupuncture for cerebral palsy in preschool children, the core prescriptions reveal the simultaneous treatment of exterior and interior, the mutual regulation of


Subject(s)
Acupuncture Points , Acupuncture Therapy , Cerebral Palsy/therapy , Child, Preschool , Data Mining , Electronic Health Records , Humans
17.
China Pharmacy ; (12): 406-412, 2021.
Article in Chinese | WPRIM | ID: wpr-873479

ABSTRACT

OBJECTIVE:To provide reference for constructing and improving the pharmacovigilance signal management sys - tem in China by comparing signal management system among the European Union (EU),the United States (U. S. )and Japan. METHODS:Literature analysis method was used to systematically compare the similarities and differences on definitions ,sources, detection methods and management process of pharmacovigilance signals among EU ,U. S. and Japan. Some suggestions were put forward for pharmacovigilance management in China. RESULTS & CONCLUSIONS :Regulatory authorities of the EU ,U. S. and Japan did not have a uniform definition on signals ;EU drug administration adopted the definition of the eighth working group of Council for International Organizations of Medical Sciences ,FDA adopted its own definition ,while the Japanese regulatory agency had no clear definition. Currently ,post-marketing surveillance still relied mainly on spontaneous reporting systems ;EU,U. S. and Japan had carried out the signal detection based on the spontaneous reporting system ;EU mainly adopted the proportional reporting ratio method ,U. S. mainly adopts the multiple gamma Poisson Shrinker ,and Japan mainly adopted the reporting ratio method. EU had special guidelines for signal management process ,while the U. S. and Japan did not. It is recommended to accelerate the deve- lopment of the legal and regulatory framework on pharmacovigilance in China ,draw up guidelines on pharmacovigilance practices , strengthen the active ADR surveillance and promote the application of data mining techniques in signal detection field ,for accelerat - ing the standardization and internationalization of China ’s pharmacovigilance work.

18.
Psicol. soc. (Online) ; 33: e227258, 2021.
Article in Portuguese | LILACS-Express | LILACS, INDEXPSI | ID: biblio-1250538

ABSTRACT

Resumo Neste artigo, discutimos um novo regime de poder, nomeado de Governamentalidade Algorítmica por Antoinette Rouvroy e Thomas Berns, que, crescentemente, vem operando na condução de nossas condutas. Diferentemente do poder disciplinar e da biopolítica, tal governamentalidade não tem por centro de gravidade os indivíduos ou as populações. Antes, por meio da mineração de dados e da produção de perfis, age tanto no nível infra-individual quanto supra-individual. Para problematizá-la, analisamos e colocamos em questão um dos seus modos de operação, os sistemas de recomendação e, dentre eles, focalizamos o caso da Netflix. Por fim, tensionamos os efeitos que os algoritmos que lhe constituem podem ter em nossos modos de subjetivação, já que, não raro, tendem a excluir de nossas experiências aquilo que é da ordem do imprevisto e que é capaz de fazer com que algo nos aconteça e nos transforme.


Resumen En este artículo, discutimos un nuevo régimen de poder que Antoinette Rouvroy y Thomas Berns llamaron Gobernanza Algorítmica y que, de forma creciente, opera en la conducción de nuestras conductas. A diferencia del poder disciplinario y de la biopolítica, esa gobernanza no tiene por centro de gravedad a los individuos o poblaciones. Más bien, por medio de la minería de datos y de la producción de perfiles, actúa tanto en el plano infraindividual como en el supraindividual. Para problematizarla, analizamos y cuestionamos uno de sus modos de operación, los sistemas de recomendaciones y, entre ellos, nos detenemos en el caso de Netflix. Por último, calibramos los efectos que los algoritmos que la constituyen pueden tener en nuestros modos de subjetivación, pues, a menudo, tienden a excluir de nuestras experiencias lo que es del orden de lo imprevisto y, como tal, puede hacer que algo nos ocurra y nos transforme.


Abstract In this article, we discuss a new power regime, named Algorithmic Governmentality (AG) by Antoinette Rouvroy and Thomas Berns, and that has increasingly been operating in conducting our behavior. Unlike the disciplinary power and biopolitics, such governmentality does not have individuals or populations as its gravity center. Rather, through data mining and profile generation, the AG acts both in the infra-individual level and in the supra-individual one. In order to problematize it, we analyzed and put into question one of its operating modes, the recommendation systems; and, among them, we focused on Netflix's case. Lastly, we tensioned the effects that its constituent algorithms can have in our subjectivation modes, since it is not rare that they tend to exclude from our experiences the things that are unpredictable and could make something happen to us and transforme us.

19.
REME rev. min. enferm ; 25: [e:1362], 2021. tab
Article in Portuguese | LILACS, BDENF | ID: biblio-1287718

ABSTRACT

RESUMO Objetivo: relatar experiências de estratégias do uso da mineração de dados em dois cenários de práticas de Enfermagem. Descrição da experiência: em ambas as experiências foi utilizado o algoritmo Apriori para descoberta de regras de associação e identificado as situações de exceção. A primeira experiência utilizou dados provenientes de óbitos infantis da região metropolitana de Curitiba - PR. Na segunda experiência utilizaram-se prontuários de pacientes atendidos por enfermeiros na classificação de risco em um hospital particular de Curitiba - PR. O primeiro estudo identificou 374 regras gerais e o segundo, 108 regras gerais, ambos com suas respectivas regras de exceção. Conclusão: a aplicação do Knowledge Discovery in Databases pode ser demonstrada e efetivada em dois cenários distintos, a fim de contribuir para a tomada de decisão pelo gestor. Espera-se que o relato reforce a importância do ensino da informática em Enfermagem como ferramenta de apoio à decisão.


RESUMEN Objetivo: reportar experiencias de estrategias de uso de minería de datos en dos escenarios de prácticas de enfermería. Descripción del experimento: en ambos experimentos se utilizó el algoritmo Apriori para descubrir reglas de asociación e identificar situaciones excepcionales. El primer experimento utilizó datos de muertes infantiles en la región metropolitana de Curitiba-PR. En el segundo experimento, se utilizaron los registros médicos de los pacientes atendidos por enfermeros en la clasificación de riesgo en un hospital privado de Curitiba-PR. El primer estudio identificó 374 reglas generales y el segundo 108 reglas generales, ambas con sus respectivas reglas de excepción. Conclusión: la aplicación del Knowledge Discovery in Databases se puede demostrar e implementar en dos escenarios diferentes, con el fin de contribuir a la toma de decisiones por parte del gerente. Se espera que el informe refuerce la importancia de la enseñanza de la informática en enfermería como herramienta de apoyo a la toma de decisiones.


ABSTRACT Objective: to report experiences of data mining use strategies in two Nursing practice settings. Description of the experience: in both experiences, the Apriori algorithm was used to discover association rules and to identify exception situations. The first experience used data from infant deaths in the metropolitan region of Curitiba, PR. In the second experience, medical records of patients assisted by nurses were used in the risk classification at a private hospital in Curitiba -PR. The first study identified 374general rules and the second, 108, both with their respective exception rules. Conclusion: the application of Knowledge Discovery in Databases can be demonstrated and carried out in two different settings, in order to contribute to decision-making by the manager. It is expected that the report reinforces the importance of teaching Nursing Informatics as a decision-making support tool.


Subject(s)
Humans , Decision Making, Computer-Assisted , Nursing Informatics , Databases, Bibliographic , Data Mining
20.
Rev. cuba. invest. bioméd ; 40(supl.1): e1614, 2021. tab, graf
Article in Spanish | LILACS, CUMED | ID: biblio-1289470

ABSTRACT

Uno de los desafíos que los programadores tienen que enfrentar es la alta dimensión de grupos de datos. El proceso de reconocimiento de patrones en imagen y la minería de datos para los volúmenes grandes de información son ejemplos de ellos, optimizar la cantidad de veces que se recorre el conjunto de datos, disminuye el tiempo de procesamiento. Éste documento tiene el objetivo de caracterizar el algoritmo de tres pasos (S3), paralelo a K-medias, como una alternativa para afrontar la alta dimensión del conjunto de datos, en la clasificación no supervisada de imagen. Para el análisis de la concurrencia, se escoge, flujo de datos y el esquema instrucción única con datos múltiples. El resultado obtenido confirma que la concurrencia en ambos es posible, S3 no depende de la selección inicial de los representantes y puede ser el proceso de escogimiento de los primeros vectores centrales en K-medias. S3 es una alternativa a ser tenida en cuenta en la clasificación no supervisada de imágenes médicas y procesos de minería de datos(AU)


One of the challenges to be faced by programmers is the large dimensions of data groups. The process of pattern recognition in images and data mining for great volumes of information is an example. Optimizing the number of times that the set of data is run saves processing time. The purpose of the study was to characterize the three-step (S3) algorithm, parallel to k-means, as an alternative to cope with the large dimension of the data set in unsupervised image classification. Concurrence analysis is based on data flow and the single instruction multiple data scheme. The result obtained confirms that concurrence of both is possible. S3 does not depend on initial selection of representatives, and may be the process for selection of the first central vectors in k-means. S3 is an alternative to be considered in the unsupervised classification of medical images and data mining(AU)


Subject(s)
Humans , Algorithms , Image Processing, Computer-Assisted/methods , Records
SELECTION OF CITATIONS
SEARCH DETAIL