Your browser doesn't support javascript.
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 7.193
Filtrar
1.
Zhongguo Zhong Yao Za Zhi ; 44(15): 3135-3142, 2019 Aug.
Artigo em Chinês | MEDLINE | ID: mdl-31602864

RESUMO

This research is launched to look for the medication rules and characteristics of Tibetan medicine in the treatment of gZav-Grib( apoplexy sequelae). HIS records of gZav-Grib patients were selected from the Tibetan Hospital of Tibet Autonomous Region and Tibetan Hospital of the city of Naqu. SPSS Modeler,Gephi and other data mining and visualization software were used to study the actual law of drug use in the treatment of gZav-Grib in Tibetan medicine. Finally,479 cases of gZav-Grib patients in Tibetan medicine were included. Their average age is 63 and average hospital stay was 32 days. In total,82 Tibetan medicine prescriptions were used for treating gZav-Grib. The frequency in the front is Twenty-flavor Chenxiang Pills( 338 times),Ruyi Zhenbao Pills( 322 times),and Seventy-flavor Zhenzhu Pills( 315 times). According to the regularity of Tebitan medicine,they were applied in different time periods including the early morning,morning,noon,and evening,for example,in the early morning: Seventy-flavor Zhenzhu Pills,morning: Ruyi Zhenbao Pills,noon: Eighteen-flavor Dujuan Pills,evening: Twenty-flavor Chenxiang Pills. In the clinical joint,18 groups were found in the 10% support and 70% confidence. There are two prescriptions confidence more than 80% which nature focus on Gan,Ruan,Xi,Liang,Dun,Han,Wen. gZav-Grib of Tibetan medicine can be divided into two types: r Lung-Grib type and k Hrag-Grib type,in which the medicine of r Lung-Grib type takes Seventy-flavor Zhenzhu Pills as the core prescription,while the medicine of k Hrag-Grib type takes Ruyi Zhenbao Pills as the core prescription. It is found that the treatment of gZav-Grib by Tibetan medicine is mainly dominated by the treatment idea about " Therapeutic r Lung and blood,Consideration of venous diseases". Treatment functions is promoting the circulation of Qi,clearing blood heat and getting rid of bad blood,achieving the purpose of treating both principal secondary aspect of gZav-Grib. The research methods based on the HIS can't only optimize the Tibetan treating gZav-Grib sequela treatment plan and rule of medication,but also provide the scientific basis for Tibetan medicine treat gZav-Grib.


Assuntos
Medicina Tradicional Tibetana , Acidente Vascular Cerebral/complicações , Acidente Vascular Cerebral/tratamento farmacológico , Mineração de Dados , Humanos , Registros Médicos , Software , Tibet
2.
Zhongguo Zhong Yao Za Zhi ; 44(15): 3143-3150, 2019 Aug.
Artigo em Chinês | MEDLINE | ID: mdl-31602865

RESUMO

This study aimed to explore the rule of Tibetan medicine in clinical treatment of hypertension( k Hrag-rLung-stod-vtshangs) and analyze the characteristics of its prescriptions. One hundred and thirty-seven cases of hypertension treated Tibetan medicine were collected. Data mining,Gephi,Cytoscape and other methods and software were used to analyze the characteristics of Tibetan medicine. The results showed that there were 44 cases of r Lung-type hypertension in clinical medical records,while 57 cases of k Hrag-type hypertension. There were 103 treatment prescriptions. The frequency of these prescriptions covered Twenty-five Yuganzi Pills( 96 times),Seventy Pearl Pills( 80 times),Eight Chenxiang Pills( 75 times),and Sanwei Ganlu Powder( 62 times),and they were highly correlated,with confidence greater than 95%. There were 332 prescriptions involved in the prescriptions which is core prescription medicines. This study first proposed the dosage analysis method of Tibetan medicine prescription medicines,and obtained the more dosage of Chebulae Fructus,Phyllanthi Fructus,Aucklandiae Radix,Aquilariae Lignum Resinatum and so on. The correlation analysis of the prescription medicines found that Carthami Flos,Myristicae Semen,Bambusae Concretio Silicea,Caryophylli Flos,Amomi Fructus Rotundus led by Tsaoko Fructus had a high correlation and a confidence greater than 75%. These herbs were guaranteed when Tibetan medicine was used in combination. The key drugs for protecting viscera and regulating the three gastric fires. The prescription is mainly cold,blunt,sparse and rough. Its efficacy focuses on the pathogenesis of blood fever,blood stickiness and venous blockage caused by heat,sharpness,odor and stickiness. It mainly treats Tibetan medicine diseases such as k Hrag-r Lung-stod-vtshangs and k Hrag-vpel( polyemia). It is suggested that Tibetan medicine has a three-in-one invisible treatment principle of " clearing blood-heat,opening vessel and regulating stomach-fire" in the treatment of hypertension,which attributed to both cardiovascular function and gastrointestinal metabolic function. This may be a significant and invisible knowledge of Tibetan medicine in the treatment of hypertension.


Assuntos
Hipertensão/tratamento farmacológico , Medicina Tradicional Tibetana , Mineração de Dados , Humanos , Registros Médicos , Software
3.
Zhongguo Zhong Yao Za Zhi ; 44(16): 3415-3422, 2019 Aug.
Artigo em Chinês | MEDLINE | ID: mdl-31602903

RESUMO

Growing clinical evidence shows that a partial rheumatoid arthritis( RA) patient treated with Tripterygium Glycosides Tablets( TGT) may fail to achieve clinical improvement. It is of great clinical significance to predict the therapeutic effect of TGT in RA. Therefore,the aim of the current study was to identify potential biomarkers for TGT treatment in RA. Affymetrix EG1.0 arrays were applied to detect gene expression in peripheral blood mononuclear cells obtained from 6 RA patients( 3 responders and 3 non-responders) treated with TGT. By integrating differential expression data analysis and biomolecular network analysis,360 mRNAs( 185 up-regulated and 175 down-regulated) and 24 miRNAs( 7 up-regulated and 17 down-regulated) which were differentially expressed between TGT responder and non-responder groups were identified. A total of 206 candidate target genes for the differentially expressed miRNAs were obtained based on miRanada and Target Scan databases,and then the miRNA target gene coexpression network and miRNA-mediated gene signal transduction network were constructed. Following the network analyses,three candidate miRNAs biomarkers( hsa-miR-4720-5 p,hsa-miR-374 b-5 p,hsa-miR-185-3 p) were identified as candidate biomarkers predicting individual response to TGT. Partialleast-squares( PLS) was applied to construct a model for predicting response to TGT based on the expression levels of the candidate gene biomarkers in RA patients. The five-fold cross-validation showed that the prediction accuracy( ACC) of this PLS-based model efficacy was 100.00%,100.00%,100.00%,66.67% and 66.67% respectively,and all the area under the receiver operating characteristic curve( AUC) were 1.00,indicating the highly predictive efficiency of this PLS-based model. In conclusion,the integrating transcription data mining and biomolecular network investigation show that hsa-mir-4720-5 p,hsa-mir-374 b-5 p and hsa-mir-185-3 p may be candidate biomarkers predicting individual response to TGT. In addition,the PLS model based on the expression levels of these candidate biomarkers may be helpful for the clinical screen of RA patients,which potentially benefit individualized therapy of RA in a daily clinical setting.


Assuntos
Artrite Reumatoide/tratamento farmacológico , Medicamentos de Ervas Chinesas/uso terapêutico , Glicosídeos/uso terapêutico , MicroRNAs/genética , Tripterygium/química , Biomarcadores , Mineração de Dados , Humanos , Leucócitos Mononucleares , Comprimidos
4.
Zhongguo Zhong Yao Za Zhi ; 44(16): 3526-3532, 2019 Aug.
Artigo em Chinês | MEDLINE | ID: mdl-31602918

RESUMO

This paper aims to investigate the effect of oral administration of Tripterygium Glycosides Tablets combined with traditional Chinese medicine on immune inflammatory index in patients with rheumatoid arthritis,in order to explore the compatibility mode of traditional Chinese medicine in the treatment of rheumatoid arthritis. Medical records of hospitalized patients with rheumatology at the First Affiliated Hospital of Anhui University of Traditional Chinese Medicine from June 2012 to December 2017 were collected. The combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine was adopted for the experimental group,while the simply administration of Tripterygium Glycosides Tablets were adopted for the control group. SPSS 21. 0 was used to analyze the changes of general conditions and immune inflammatory metabolic indexes in the two groups of RA patients. The association rules were analyzed by SPSS Clementine 14. 2 software Apriori module,and the random walk model was evaluated by ORACLE 10 g tool. The results showed that a total of 1 220 patients with rheumatoid arthritis met the requirements of this study,including 322 in the experimental group and 898 in the control group. Before treatment,there was no significant difference in age and duration between the two groups. The difference value of Ig A,Ig G,RF,CCP-AB,hs-CRP and ESR in the two groups of RA patients decreased before and after treatment,and the experimental group was superior to the control group in reduction of Ig A,Ig G,RF,CCP-AB,hs-CRP and ESR.The control group was superior to the experimental group in reduction of Ig M( P<0. 01 or P<0. 05). Compared with before treatment,ALT,AST,ALP,GGT,CREA,BUN,b-MG,MA,TRU and Ig U all increased,with statistically significant differences( P<0. 01).The UA of the two groups of RA patients decreased after treatment,with statistically significant differences( P<0. 01). The experimental group was superior to the control group in reduction of UA,with statistically significant differences( P < 0. 05 or P < 0. 01). The herbs adopted in the prescriptions of 1 220 patients were mainly classified into four categories,namely spleen-sweating herbs,blood-activating and stasis-relieving herbs,phlegm and phlegm-relieving herbs,and heat-clearing and antidote herbs. The results of association rule analysis indicated a significant correlation between the single-flavored Tripterygium Glycosides Tablets,oral Chinese medicine and immune inflammation,and improvement of liver and kidney function indexes. The results of the random walk model analysis indicated that the experimental group's Ig M and hs-CRP were superior to those of the control group in terms of random fluctuation maximum,walking positive growth rate,comprehensive evaluation index increasing rate,comprehensive improvement rate,comprehensive evaluation index recording times,and expected improvement value. The results of this study showed that the single administration of Tripterygium Glycosides Tablets can effectively improve the immune inflammatory metabolic index of patients with rheumatoid arthritis,and the combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine could alleviate the immune inflammatory index of RA patients and reduce liver and kidney dysfunction compared with simple oral administration. The comprehensive evaluation Ig M and hs-CRP in the group of combined administration of Tripterygium Glycosides Tablets and traditional Chinese medicine were better than those in the group of the Tripterygium Glycosides Tablets. There was a long-term correlation between the comprehensive evaluation index and the intervention measures of the two groups of patients.


Assuntos
Artrite Reumatoide/tratamento farmacológico , Mineração de Dados , Medicamentos de Ervas Chinesas/farmacologia , Glicosídeos/farmacologia , Tripterygium/química , Humanos , Rim/efeitos dos fármacos , Fígado/efeitos dos fármacos , Medicina Tradicional Chinesa , Comprimidos
5.
Medicine (Baltimore) ; 98(42): e17504, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-31626105

RESUMO

Mental disorders are important diseases with a high prevalence rate in the general population. Common mental disorders are complex diseases with high heritability, and their pathogenesis is the result of interactions between genetic and environmental factors. However, the relationship between mental disorders and genes is complex and difficult to evaluate. Additionally, some mental disorders involve numerous genes, and a single gene can also be associated with different types of mental disorders.This study used text mining (including word frequency analysis, cluster analysis, and association analysis) of the PubMed database to identify genes related to mental disorders.Word frequency analysis revealed 52 high-frequency genes important in studies of mental disorders. Cluster analysis showed that 5-HTT, SLC6A4, and MAOA are common genetic factors in most mental disorders; the intra-group genes in each cluster were highly correlated. Some mental disorders may have common genetic factors; for example, there may be common genetic factors between 'Affective Disorders' and 'Schizophrenia.' Association analysis revealed 35 frequent itemsets and 25 association rules, indicating close associations among genes. The results of association rules showed that CCK, MAOA, and 5-HTT are the most closely related.We used text mining technology to analyze genes related to mental disorders to further summarize and clarify the relationships between mental disorders and genes as well as identify potential relationships, providing a foundation for future experiments. The results of the associative analysis also provide a reference for multi-gene studies of mental disorders.


Assuntos
Mineração de Dados/métodos , Transtornos Mentais/genética , Análise por Conglomerados , Bases de Dados Factuais , Predisposição Genética para Doença/genética , Humanos , Monoaminoxidase/análise , PubMed , Proteínas da Membrana Plasmática de Transporte de Serotonina/análise
6.
BMC Bioinformatics ; 20(1): 459, 2019 Sep 06.
Artigo em Inglês | MEDLINE | ID: mdl-31492112

RESUMO

BACKGROUND: Automatic extraction of biomedical events from literature is an important task in the understanding biological systems, allowing for faster update of the latest discoveries automatically. Detecting trigger words which indicate events is a critical step in the process of event extraction, because following steps depend on the recognized triggers. The task in this study is to identify event triggers from the literature across multiple levels of biological organization. In order to achieve high performances, the machine learning based approaches, such as neural networks, must be trained on a dataset with plentiful annotations. However, annotations might be difficult to obtain on the multiple levels, and annotated resources have so far mainly focused on the relations and processes at the molecular level. In this work, we aim to apply transfer learning for multiple-level trigger recognition, in which a source dataset with sufficient annotations on the molecular level is utilized to improve performance on a target domain with insufficient annotations and more trigger types. RESULTS: We propose a generalized cross-domain neural network transfer learning architecture and approach, which can share as much knowledge as possible between the source and target domains, especially when their label sets overlap. In the experiments, MLEE corpus is used to train and test the proposed model to recognize the multiple-level triggers as a target dataset. Two different corpora having the varying degrees of overlapping labels with MLEE from the BioNLP'09 and BioNLP'11 Shared Tasks are used as source datasets, respectively. Regardless of the degree of overlap, our proposed approach achieves recognition improvement. Moreover, its performance exceeds previously reported results of other leading systems on the same MLEE corpus. CONCLUSIONS: The proposed transfer learning method can further improve the performance compared with the traditional method, when the labels of the source and target datasets overlap. The most essential reason is that our approach has changed the way parameters are shared. The vertical sharing replaces the horizontal sharing, which brings more sharable parameters. Hence, these more shared parameters between networks improve the performance and generalization of the model on the target domain effectively.


Assuntos
Pesquisa Biomédica , Mineração de Dados/métodos , Redes Neurais (Computação)
7.
J Environ Manage ; 250: 109454, 2019 Nov 15.
Artigo em Inglês | MEDLINE | ID: mdl-31514001

RESUMO

In this paper, meteorological parameters, electric field strength and transmitters' output power measured during six months in a TV/FM station. There are 13 frequencies in FM and UHF frequency bands in pilot broadcast station. The analysis of results were carried out using data mining techniques. In addition, a prediction model on the basis of a Neural Network is identified. The electric field is affected by distance between the antenna and the receiver point, transmitters' output power and meteorological constituents of air pressure, temperature and humidity. The meteorological parameters and transmitters' power are used as inputs and the electric field is used as the output. After data acquisition, preprocessing is performed and the Neural Network of a multilayer perceptron model is applied. In addition, Multi Linear Regression is performed. In evaluation, the performance of the proposed techniques is based on the root mean square error (RMSE) property. The least MSE obtained for the proposed model based on Neural Network amounted to 0.198 while the least MSE of Regression was 0.280. The results showed that for a given input of the atmospheric parameters as well as the transmitter power, the intensity of electric field can be predicted as well as the determining the relationship between the atmospheric parameters, transmitters' power and electric field strength. The statistical and correlation analysis used to assess the relation between each parameter and signal strength concluded that the temperature and wind direction have an inverted linear relationship with the signal level while the others have a direct linear relationship.


Assuntos
Meteorologia , Redes Neurais (Computação) , Mineração de Dados , Monitoramento Ambiental , Modelos Lineares , Vento
8.
Isr Med Assoc J ; 21(7): 503, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31507131

RESUMO

BACKGROUND: Benign rolandic epilepsy or benign childhood epilepsy with centrotemporal spikes (BCECTS) is a common childhood epileptic syndrome. The syndrome resolves in adolescence, but 1-7% of patients have an atypical presentation, some of which require aggressive medical treatment. Early treatment may prevent complications and neurocognitive deterioration. Variants include Landau-Kleffner syndrome (LKS) and electrical status epilepticus during sleep (ESES). OBJECTIVES: To determine data driven identification of risk factors and characterization of new subtypes of BCECTS based on anontology. To use data mining analysis and correlation between the identified groups and known clinical variants. METHODS: We conducted a retrospective cohort study comprised of 104 patients with a diagnosis of BCECTS and a minimum of 2 years of follow-up, between the years 2005 and 2017. The medical records were obtained from the epilepsy service unit of the pediatric neurology department at Dana-Dwek Hospital, Tel Aviv Sourasky Medical Center. We developed a BCECTS ontology and performed data preprocessing and analysis using the R Project for Statistical Computing (https://www.r-project.org/) and machine learning tools to identify risk factors and characterize subgroups. RESULTS: The ontology created a uniform and understandable infrastructure for research. With the ontology, a more precise characterization of clinical symptoms and EEG activity of BCECTS was possible. Risk factors for the development of severe atypical presentations were identified: electroencephalography (EEG) with spike wave (P < 0.05), EEG without evidence of left lateralization (P < 0.05), and EEG localization (centrotemporal, frontal, or frontotemporal) (P < 0.01). CONCLUSIONS: Future use of the ontology infrastructure for expanding characterization for multicenter studies as well as future studies of the disease are needed. Identifying subgroups and adapting them to known clinical variants will enable identification of risk factors, improve prediction of disease progression, and facilitate adaptation of more accurate therapy. Early identification and frequent follow-up may have a significant impact on the prognosis of the atypical variants.


Assuntos
Algoritmos , Mineração de Dados , Eletroencefalografia/métodos , Epilepsia Rolândica/diagnóstico , Estudos de Coortes , Epilepsia Rolândica/fisiopatologia , Seguimentos , Humanos , Prognóstico , Estudos Retrospectivos , Fatores de Risco
9.
Stud Health Technol Inform ; 267: 52-58, 2019 Sep 03.
Artigo em Inglês | MEDLINE | ID: mdl-31483254

RESUMO

Fast Healthcare Interoperability Resources (FHIR), an international standard for exchanging digital health data, is increasingly used in health information technology. FHIR promises to facilitate the use of electronic health records (EHRs), enable mobile technologies and make health data accessible to large-scale analytics. Until now, there is no comprehensive review of scientific articles about FHIR and its use in digital health. Here, we aim to address this gap and provide an overview of the main topics associated with FHIR in the scientific literature. For this, we screened all articles about FHIR on Web of Science and PubMed and identified the main topics discussed in these articles. We also explored the temporal trend and geography of publications and performed some basic text mining on article abstracts. We found that the topics most commonly discussed in the articles were related to data models, mobile and web applications as well as medical devices. Since its introduction, the number of publications about FHIR have steadily increased until 2017, indicating an increasing popularity of FHIR in healthcare (in 2018, publication numbers remained stable). In sum, our study provides an overview of the scientific literature about FHIR and its current use in digital health.


Assuntos
Registros Eletrônicos de Saúde , Informática Médica , Mineração de Dados , PubMed
10.
BMC Bioinformatics ; 20(1): 444, 2019 Aug 28.
Artigo em Inglês | MEDLINE | ID: mdl-31455207

RESUMO

BACKGROUND: Mining epistatic loci which affects specific phenotypic traits is an important research issue in the field of biology. Bayesian network (BN) is a graphical model which can express the relationship between genetic loci and phenotype. Until now, it has been widely used into epistasis mining in many research work. However, this method has two disadvantages: low learning efficiency and easy to fall into local optimum. Genetic algorithm has the excellence of rapid global search and avoiding falling into local optimum. It is scalable and easy to integrate with other algorithms. This work proposes an epistasis mining approach based on genetic tabu algorithm and Bayesian network (Epi-GTBN). It uses genetic algorithm into the heuristic search strategy of Bayesian network. The individual structure can be evolved through the genetic operations of selection, crossover and mutation. It can help to find the optimal network structure, and then further to mine the epistasis loci effectively. In order to enhance the diversity of the population and obtain a more effective global optimal solution, we use the tabu search strategy into the operations of crossover and mutation in genetic algorithm. It can help to accelerate the convergence of the algorithm. RESULTS: We compared Epi-GTBN with other recent algorithms using both simulated and real datasets. The experimental results demonstrate that our method has much better epistasis detection accuracy in the case of not affecting the efficiency for different datasets. CONCLUSIONS: The presented methodology (Epi-GTBN) is an effective method for epistasis detection, and it can be seen as an interesting addition to the arsenal used in complex traits analyses.


Assuntos
Algoritmos , Mineração de Dados , Epistasia Genética , Teorema de Bayes , Redes Reguladoras de Genes , Loci Gênicos , Humanos , Degeneração Macular/genética , Modelos Genéticos , Polimorfismo de Nucleotídeo Único/genética
11.
Stud Health Technol Inform ; 264: 153-157, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437904

RESUMO

We describe the process of creating a User Interface Terminology (UIT) with the goal to generate a maximum of German language interface terms that are mapped to the reference terminology SNOMED CT. The purpose is to offer a high coverage of medical jargon in order to optimise semantic annotations of clinical documents by text mining systems. The first step consisted in the creation of an n-gram table to which words and short phrases from the English SNOMED CT description table were automatically extracted and entered. The second step was to fill up the n-gram table with human and machine translations, manually enriched by POS tags. Top-down and bottom-up methods for manual terminology population were used. Grammar rules were formulated and embedded into a term generator, which then created one-to-many German variants per SNOMED CT description. Currently, the German user interface terminology contains 4,425,948 entries, created out of 111,605 German n-grams, assigned to 95,298 English n-grams. With 341,105 active concepts and 542,462 (non FSN) descriptions, it corresponds to an average of 13 interface terms per concept and 8.2 per description. An analysis of the current quality of this resource by blinded human assessment terminology states equivalence regarding term understandability compared to a fully automated Web-based translator, which, however does not yield any synonyms, so that there are good reasons to further develop this semi-automated terminology engineering method and recommend it for other language pairs.


Assuntos
Semântica , Systematized Nomenclature of Medicine , Mineração de Dados , Humanos
12.
Stud Health Technol Inform ; 264: 1554-1555, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438228

RESUMO

This study used descriptive statistical analyses to investigate the payment characteristics and to discuss the regularity of highest paying industries. Payments by 4.70% of highest paying industries (N=446) accounted for 85% of the total (US $72,458,304) in 2014-2016. A tiny minority of highest paying industries control the majority of payments. Large payments from these industries are highly associated with few specific products. Furthermore, payment patterns among the industries include concentration and diversification.


Assuntos
Indústria Farmacêutica , Cirurgia Torácica , Centers for Medicare and Medicaid Services (U.S.) , Mineração de Dados , Gastos em Saúde , Estados Unidos
13.
Stud Health Technol Inform ; 264: 1608-1609, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438255

RESUMO

This demonstration showcase will present a novel open access text mining application called NimbleMiner. NimbleMiner's architecture is language agnostic and it can be potentially applied in multiple languages. The system was applied in a series of recent studies in several languages, including English and Hebrew. The system showed good results in terms of text classification performance when compared to other natural language processing approaches.


Assuntos
Mineração de Dados , Processamento de Linguagem Natural , Linguagem
14.
Stud Health Technol Inform ; 264: 1616-1617, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438259

RESUMO

To explore the current trends and future directions of data mining in nursing, we systematically searched English and Chinese databases (from 1990 to 2017) with data mining and nursing related keywords. We found 407 papers, which increased rapidly in the recent five years. Data mining was the most widely used in clinical nursing (50.6%). Chinese papers focused on exploring new nursing knowledge and rules, while English papers focused on promoting nursing practice by data mining.


Assuntos
Bibliometria , Mineração de Dados , Bases de Dados Factuais
15.
Stud Health Technol Inform ; 264: 83-87, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437890

RESUMO

Semantic standards and human language technologies are key enablers for semantic interoperability across heterogeneous document and data collections in clinical information systems. Data provenance is awarded increasing attention, and it is especially critical where clinical data are automatically extracted from original documents, e.g. by text mining. This paper demonstrates how the output of a commercial clinical text-mining tool can be harmonised with FHIR, the leading clinical information model standard. Character ranges that indicate the origin of an annotation and machine generates confidence values were identified as crucial elements of data provenance in order to enrich text-mining results. We have specified and requested necessary extensions to the FHIR standard and demonstrated how, as a result, important metadata describing processes generating FHIR instances from clinical narratives can be embedded.


Assuntos
Mineração de Dados , Registros Eletrônicos de Saúde , Assistência à Saúde , Humanos , Metadados , Semântica
16.
Stud Health Technol Inform ; 264: 1516-1517, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438209

RESUMO

Scientific challenges based on benchmark data enable the comparison and evaluation of different algorithms and take place regularly in scientific disciplines like medical image processing, text mining or genetics. The idea of a challenge is rarely applied within the eHealth community. Mappathon is a metadata mapping challenge that asks for methods to find corresponding data elements within similar datasets and to correlate data elements among each other.


Assuntos
Metadados , Telemedicina , Algoritmos , Mineração de Dados , Processamento de Imagem Assistida por Computador
17.
BMC Bioinformatics ; 20(1): 426, 2019 Aug 15.
Artigo em Inglês | MEDLINE | ID: mdl-31416413

RESUMO

BACKGROUND: Advances in medical technology have allowed for customized prognosis, diagnosis, and treatment regimens that utilize multiple heterogeneous data sources. Multiple kernel learning (MKL) is well suited for the integration of multiple high throughput data sources. MKL remains to be under-utilized by genomic researchers partly due to the lack of unified guidelines for its use, and benchmark genomic datasets. RESULTS: We provide three implementations of MKL in R. These methods are applied to simulated data to illustrate that MKL can select appropriate models. We also apply MKL to combine clinical information with miRNA gene expression data of ovarian cancer study into a single analysis. Lastly, we show that MKL can identify gene sets that are known to play a role in the prognostic prediction of 15 cancer types using gene expression data from The Cancer Genome Atlas, as well as, identify new gene sets for the future research. CONCLUSION: Multiple kernel learning coupled with modern optimization techniques provides a promising learning tool for building predictive models based on multi-source genomic data. MKL also provides an automated scheme for kernel prioritization and parameter tuning. The methods used in the paper are implemented as an R package called RMKL package, which is freely available for download through CRAN at https://CRAN.R-project.org/package=RMKL .


Assuntos
Algoritmos , Mineração de Dados , Genômica/métodos , Bases de Dados Genéticas , Humanos , MicroRNAs/genética , MicroRNAs/metabolismo , Neoplasias/genética
18.
BMC Bioinformatics ; 20(1): 427, 2019 Aug 16.
Artigo em Inglês | MEDLINE | ID: mdl-31419937

RESUMO

BACKGROUND: Biomedical named entity recognition (BioNER) is a fundamental and essential task for biomedical literature mining, which affects the performance of downstream tasks. Most BioNER models rely on domain-specific features or hand-crafted rules, but extracting features from massive data requires much time and human efforts. To solve this, neural network models are used to automatically learn features. Recently, multi-task learning has been applied successfully to neural network models of biomedical literature mining. For BioNER models, using multi-task learning makes use of features from multiple datasets and improves the performance of models. RESULTS: In experiments, we compared our proposed model with other multi-task models and found our model outperformed the others on datasets of gene, protein, disease categories. We also tested the performance of different dataset pairs to find out the best partners of datasets. Besides, we explored and analyzed the influence of different entity types by using sub-datasets. When dataset size was reduced, our model still produced positive results. CONCLUSION: We propose a novel multi-task model for BioNER with the cross-sharing structure to improve the performance of multi-task models. The cross-sharing structure in our model makes use of features from both datasets in the training procedure. Detailed analysis about best partners of datasets and influence between entity categories can provide guidance of choosing proper dataset pairs for multi-task training. Our implementation is available at https://github.com/JogleLew/bioner-cross-sharing .


Assuntos
Pesquisa Biomédica , Mineração de Dados/métodos , Disseminação de Informação , Algoritmos , Bases de Dados como Assunto , Humanos , Aprendizado de Máquina , Redes Neurais (Computação)
19.
BMC Bioinformatics ; 20(1): 430, 2019 Aug 17.
Artigo em Inglês | MEDLINE | ID: mdl-31419946

RESUMO

*: Background Consisting of dictated free-text documents such as discharge summaries, medical narratives are widely used in medical natural language processing. Relationships between anatomical entities and human body parts are crucial for building medical text mining applications. To achieve this, we establish a mapping system consisting of a Wikipedia-based scoring algorithm and a named entity normalization method (NEN). The mapping system makes full use of information available on Wikipedia, which is a comprehensive Internet medical knowledge base. We also built a new ontology, Tree of Human Body Parts (THBP), from core anatomical parts by referring to anatomical experts and Unified Medical Language Systems (UMLS) to make the mapping system efficacious for clinical treatments. *: Result The gold standard is derived from 50 discharge summaries from our previous work, in which 2,224 anatomical entities are included. The F1-measure of the baseline system is 70.20%, while our algorithm based on Wikipedia achieves 86.67% with the assistance of NEN. *: Conclusions We construct a framework to map anatomical entities to THBP ontology using normalization and a scoring algorithm based on Wikipedia. The proposed framework is proven to be much more effective and efficient than the main baseline system.


Assuntos
Anatomia , Mineração de Dados , Corpo Humano , Bases de Conhecimento , Alta do Paciente , Algoritmos , Humanos
20.
Sheng Wu Yi Xue Gong Cheng Xue Za Zhi ; 36(4): 548-556, 2019 Aug 25.
Artigo em Chinês | MEDLINE | ID: mdl-31441254

RESUMO

Methods for achieving diagnosis of Parkinson's disease (PD) based on speech data mining have been proven effective in recent years. However, due to factors such as the degree of disease of the data collection subjects and the collection equipment and environment, there are different categories of sample aliasing in the sample space of the acquired data set. Samples in the aliased area are difficult to be identified effectively, which seriously affects the classification accuracy of the algorithm. In order to solve this problem, a partition bagging ensemble learning is proposed in this article, which measures the aliasing degree of the sample by designing the the ratio of sample centroid distance metrics and divides the training set into multiple subsets. And then the method of transfer training of misclassified samples is used to adjust the results of subset partitioning. Finally, the optimized weights of each sub-classifier are used to integrate the test results. The experimental results show that the classification accuracy of the proposed method is significantly improved on two public datasets and the increasement of mean accuracy is up to 25.44%. This method not only effectively improves the classification accuracy of PD speech dataset, but also increases the sample utilization rate, providing a new idea for the diagnosis of PD.


Assuntos
Mineração de Dados , Doença de Parkinson/diagnóstico , Fala , Algoritmos , Humanos , Aprendizado de Máquina
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA