Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 20 de 746
Filtrar
1.
BMC Bioinformatics ; 21(1): 252, 2020 Jun 18.
Artigo em Inglês | MEDLINE | ID: mdl-32552728

RESUMO

BACKGROUND: Many disease causing genes have been identified through different methods, but there have been no uniform annotations of biomedical named entity (bio-NE) of the disease phenotypes of these genes yet. Furthermore, semantic similarity comparison between two bio-NE annotations has become important for data integration or system genetics analysis. RESULTS: The package pyMeSHSim recognizes bio-NEs by using MetaMap which produces Unified Medical Language System (UMLS) concepts in natural language process. To map the UMLS concepts to Medical Subject Headings (MeSH), pyMeSHSim is embedded with a house-made dataset containing the main headings (MHs), supplementary concept records (SCRs), and their relations in MeSH. Based on the dataset, pyMeSHSim implemented four information content (IC)-based algorithms and one graph-based algorithm to measure the semantic similarity between two MeSH terms. To evaluate its performance, we used pyMeSHSim to parse OMIM and GWAS phenotypes. The pyMeSHSim introduced SCRs and the curation strategy of non-MeSH-synonymous UMLS concepts, which improved the performance of pyMeSHSim in the recognition of OMIM phenotypes. In the curation of 461 GWAS phenotypes, pyMeSHSim showed recall > 0.94, precision > 0.56, and F1 > 0.70, demonstrating better performance than the state-of-the-art tools DNorm and TaggerOne in recognizing MeSH terms from short biomedical phrases. The semantic similarity in MeSH terms recognized by pyMeSHSim and the previous manual work was calculated by pyMeSHSim and another semantic analysis tool meshes, respectively. The result indicated that the correlation of semantic similarity analysed by two tools reached as high as 0.89-0.99. CONCLUSIONS: The integrative MeSH tool pyMeSHSim embedded with the MeSH MHs and SCRs realized the bio-NE recognition, normalization, and comparison in biomedical text-mining.


Assuntos
Medical Subject Headings , Semântica , Unified Medical Language System/normas , Humanos
2.
Stud Health Technol Inform ; 270: 208-212, 2020 Jun 16.
Artigo em Inglês | MEDLINE | ID: mdl-32570376

RESUMO

This paper presents five document retrieval systems for a small (few thousands) and domain specific corpora (weekly peer-reviewed medical journals published in French) as well as an evaluation methodology to quantify the models performance. The proposed methodology does not rely on external annotations and therefore can be used as an ad hoc evaluation procedure for most document retrieval tasks. Statistical models and vector space models are empirically compared on a synthetic document retrieval task. For our dataset size and specificities the statistical approaches consistently performed better than its vector space counterparts.


Assuntos
Armazenamento e Recuperação da Informação/métodos , Idioma , Medical Subject Headings , Modelos Estatísticos , Processamento de Linguagem Natural , Humanos
3.
Biomed Khim ; 66(1): 7-17, 2020 Jan.
Artigo em Russo | MEDLINE | ID: mdl-32116222

RESUMO

This paper proposes a method of comparative analysis of scientific trajectories based on bibliographic profiles. The bibliographic profile ("meshprint") is a list of MeSH terms (key terms used to index articles in the PubMed), indicating the relative frequency of occurrence of each term in the scientist's articles. Comparison of personalized bibliographic profiles can be represented in the form of a semantic network, where the nodes are the names of scientists, and the relationships are proportional to the calculated measures of similarity of bibliographic profiles. The proposed method was used to analyze the semantic network of scientists united by the academic school of the academician A.I. Archakov. The results of the work allowed us to show the relationship between the scientific trajectories of one scientific school and to correlate the results with world trends.


Assuntos
Algoritmos , Bibliometria , Medical Subject Headings , Editoração/tendências , PubMed
4.
J Cancer Res Clin Oncol ; 146(4): 985-1001, 2020 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-31955287

RESUMO

PURPOSE: Oral mucositis is a common, painful side effect of cancer treatment-be it locoregional (e.g. irradiation) or systemic (e. g. chemotherapy). Phytotherapy is often used by patients to alleviate symptoms. However, knowledge on which medical plants are recommended by literature about Traditional European Medicine (TEM), their effect(s) on symptoms and their efficacy is severely lacking. Therefore, we developed a novel approach to assess traditional knowledge of herbals used in TEM and searched the online databases for studies reporting effects of these plants. METHODS: At first, online research did not yield a satisfying number of studies (MESH terms: "mucositis" OR "stomatitis" AND "herbal" OR "herbal medicine"). Trials were labelled by the country conducting the study. In parallel, we compiled a list of 78 plants recommended for treating oral mucositis by screening 14 books on TEM. Then, a "hit list" of the plants most often mentioned was composed and used further for a second online investigation using the Latin plant designations as MESH term. Studies of both online searches were pooled for analysis. RESULTS: There is a gap between traditional knowledge and trials investigating medical plants used by TEM. Overall, herbal remedies alleviate oral mucositis and especially, gingivitis well. There is good evidence for using Matricaria recutita L., Salvia officinalis L., Calendula officinalis L. and Thymus spp. L. for treating oral mucositis. CONCLUSION: Clinical trials investigating medical plants known in TEM are rare. However, following our research strategy, we could extrapolate four plants with good evidence for alleviating symptoms of oral mucositis and gingivitis.


Assuntos
Fitoterapia/métodos , Plantas Medicinais , Estomatite/tratamento farmacológico , Antineoplásicos/efeitos adversos , Europa (Continente) , Humanos , Armazenamento e Recuperação da Informação , Medical Subject Headings , Neoplasias/tratamento farmacológico , Estomatite/induzido quimicamente , Revisões Sistemáticas como Assunto
5.
Medicine (Baltimore) ; 98(43): e17631, 2019 Oct.
Artigo em Inglês | MEDLINE | ID: mdl-31651878

RESUMO

BACKGROUND: Many authors are concerned which types of peer-review articles can be cited most in academics and who were the highest-cited authors in a scientific discipline. The prerequisites are determined by: (1) classifying article types; and (2) quantifying co-author contributions. We aimed to apply Medical Subject Headings (MeSH) with social network analysis (SNA) and an authorship-weighted scheme (AWS) to meet the prerequisites above and then demonstrate the applications for scholars. METHODS: By searching the PubMed database (pubmed.com), we used the keyword "Medicine" [journal] and downloaded 5,636 articles published from 2012 to 2016. A total number of 9,758 were cited in Pubmed Central (PMC). Ten MeSH terms were separated to represent the journal types of clusters using SNA to compare the difference in bibliometric indices, that is, h, g, and x as well as author impact factor(AIF). The methods of Kendall coefficient of concordance (W) and one-way ANOVA were performed to verify the internal consistency of indices and the difference across MeSH clusters. Visual representations with dashboards were shown on Google Maps. RESULTS: We found that Kendall W is 0.97 (χ = 26.22, df = 9, P < .001) congruent with internal consistency on metrics across MeSH clusters. Both article types of methods and therapeutic use show higher frequencies than other 8 counterparts. The author Klaus Lechner (Austria) earns the highest research achievement(the mean of core articles on g = Ag = 15.35, AIF = 21, x = 3.92, h = 1) with one paper (PMID: 22732949, 2012), which was cited 23 times in 2017 and the preceding 5 years. CONCLUSION: Publishing article type with study methodology and design might lead to a higher IF. Both classifying article types and quantifying co-author contributions can be accommodated to other scientific disciplines. As such, which type of articles and who contributes most to a specific journal can be evaluated in the future.


Assuntos
Autoria , Bibliometria , Medical Subject Headings , Publicações Periódicas como Assunto , Análise por Conglomerados , Humanos , PubMed , Editoração
6.
Pediatr. aten. prim ; 21(83): 313-318, jul.-sept. 2019. ilus
Artigo em Espanhol | IBECS | ID: ibc-188653

RESUMO

Una palabra clave es una palabra o frase corta que se utiliza para describir el contenido del trabajo, empleando términos de lenguaje natural. Por su parte, los descriptores son términos normalizados que utiliza el documentalista para clasificar el trabajo, empleando un lenguaje controlado mucho más específico que el natural. Los descriptores se agrupan en diccionarios llamados tesauros, tales como el MeSH de la National Library of Medicine o el Diccionario de Descriptores en Ciencias de la Salud de la Biblioteca Virtual en Salud. Se describe la importancia de la correcta elección de descriptores y palabras clave, así como las fuentes de dónde obtenerlos


A keyword is a word or short phrase that is used to describe the content of a study, using natural language terms. On the other hand, descriptors are standardized terms that documentalists use to index the study, using a controlled language that is much more specific than the natural one. Descriptors are grouped into dictionaries called thesauri, such as the MeSH of the National Library of Medicine or the Diccionario de Descriptores en Ciencias de la Salud of the Biblioteca Virtual en Salud. We describe the importance of the correct choice of descriptors and keywords, as well as the sources of where to obtain them


Assuntos
Medical Subject Headings , Vocabulário Controlado , Terminologia como Assunto , Indexação e Redação de Resumos/métodos
7.
Recurso educacional aberto em Espanhol | CVSP - Regional | ID: oer-3854

RESUMO

Descriptores primários; Descriptores secundários; Precodificados: Tipos de publicación; Ensayo clínico (TP)


Assuntos
Medical Subject Headings , LILACS
8.
Recurso educacional aberto em Espanhol | CVSP - Regional | ID: oer-3855

RESUMO

Resumem de los cambios Calificadores eliminados Descriptores Precoordinados - cambios descriptores eliminados Nuevos Descriptores Nuevos Tipos de Publicaciones


Assuntos
Medical Subject Headings , LILACS
9.
PLoS One ; 14(8): e0220648, 2019.
Artigo em Inglês | MEDLINE | ID: mdl-31404084

RESUMO

Hierarchical organisation is a prevalent feature of many complex networks appearing in nature and society. A relating interesting, yet less studied question is how does a hierarchical network evolve over time? Here we take a data driven approach and examine the time evolution of the network between the Medical Subject Headings (MeSH) provided by the National Center for Biotechnology Information (NCBI, part of the U. S. National Library of Medicine). The network between the MeSH terms is organised into 16 different, yearly updated hierarchies such as "Anatomy", "Diseases", "Chemicals and Drugs", etc. The natural representation of these hierarchies is given by directed acyclic graphs, composed of links pointing from nodes higher in the hierarchy towards nodes in lower levels. Due to the yearly updates, the structure of these networks is subject to constant evolution: new MeSH terms can appear, terms becoming obsolete can be deleted or be merged with other terms, and also already existing parts of the network may be rewired. We examine various statistical properties of the time evolution, with a special focus on the attachment and detachment mechanisms of the links, and find a few general features that are characteristic for all MeSH hierarchies. According to the results, the hierarchies investigated display an interesting interplay between non-uniform preference with respect to multiple different topological and hierarchical properties.


Assuntos
Medical Subject Headings , PubMed , Modelos Estatísticos , Fatores de Tempo
10.
Stud Health Technol Inform ; 264: 5-9, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31437874

RESUMO

Eliciting semantic similarity between concepts remains a challenging task. Recent approaches founded on embedding vectors have gained in popularity as they have risen to efficiently capture semantic relationships. The underlying idea is that two words that have close meaning gather similar contexts. In this study, we propose a new neural network model, named MeSH-gram, which relies on a straightforward approach that extends the skip-gram neural network model by considering MeSH (Medical Subject Headings) descriptors instead of words. Trained on publicly available PubMed/MEDLINE corpus, MeSH-gram is evaluated on reference standards manually annotated for semantic similarity. MeSH-gram is first compared to skip-gram with vectors of size 300 and at several windows' contexts. A deeper comparison is performed with twenty existing models. All the obtained results with Spearman's rank correlations between human scores and computed similarities show that MeSH-gram (i) outperforms the skip-gram model and (ii) is comparable to the best methods that need more computation and external resources.


Assuntos
Medical Subject Headings , Redes Neurais de Computação , Semântica , Humanos , MEDLINE , PubMed
11.
Stud Health Technol Inform ; 264: 1490-1491, 2019 Aug 21.
Artigo em Inglês | MEDLINE | ID: mdl-31438196

RESUMO

Statistical analysis of Medical Subject Headings (MeSH) descriptors to improve biomedical literature search is an active research area. Existing tools have limited interactive visualizations that are accessible to researchers investigating how their hypotheses compare to trends in the research literature. We present a web application that computes and provides an interactive visualization of basic frequencies and co-occurrence statistics of MeSH descriptors associated with a PubMed query.


Assuntos
Internet , MEDLINE , Medical Subject Headings , PubMed
12.
Medicine (Baltimore) ; 98(32): e16782, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31393404

RESUMO

INTRODUCTION: Over the past 10 years, epilepsy genetics has made dramatic progress. This study aimed to analyze the knowledge structure and the advancement of epilepsy genetics over the past decade based on co-word analysis of medical subject headings (MeSH) terms. METHODS: Scientific publications focusing on epilepsy genetics from the PubMed database (January 2009-December 2018) were retrieved. Bibliometric information was analyzed quantitatively using Bibliographic Item Co-Occurrence Matrix Builder (BICOMB) software. A knowledge social network analysis and publication trend based on the high-frequency MeSH terms was built using VOSviewer. RESULTS: According to the search strategy, a total of 5185 papers were included. Among all the extracted MeSH terms, 86 high-frequency MeSH terms were identified. Hot spots were clustered into 5 categories including: "ion channel diseases," "beyond ion channel diseases," "experimental research & epigenetics," "single nucleotide polymorphism & pharmacogenetics," and "genetic techniques". "Epilepsy," "mutation," and "seizures," were located at the center of the knowledge network. "Ion channel diseases" are typically in the most prominent position of epilepsy genetics research. "Beyond ion channel diseases" and "genetic techniques," however, have gradually grown into research cores and trends, such as "intellectual disability," "infantile spasms," "phenotype," "exome," " deoxyribonucleic acid (DNA) copy number variations," and "application of next-generation sequencing." While ion channel genes such as "SCN1A," "KCNQ2," "SCN2A," "SCN8A" accounted for nearly half of epilepsy genes in MeSH terms, a number of additional beyond ion channel genes like "CDKL5," "STXBP1," "PCDH19," "PRRT2," "LGI1," "ALDH7A1," "MECP2," "EPM2A," "ARX," "SLC2A1," and more were becoming increasingly popular. In contrast, gene therapies, treatment outcome, and genotype-phenotype correlations were still in their early stages of research. CONCLUSION: This co-word analysis provides an overview of epilepsy genetics research over the past decade. The 5 research categories display publication hot spots and trends in epilepsy genetics research which could consequently supply some direction for geneticists and epileptologists when launching new projects.


Assuntos
Bibliometria , Epilepsia/genética , Medical Subject Headings/estatística & dados numéricos , Epigenômica/métodos , Humanos , Canais Iônicos/genética , Mutação , Testes Farmacogenômicos/métodos , Fenótipo , Convulsões/genética
14.
J Med Libr Assoc ; 107(3): 333-340, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31258439

RESUMO

Objective: The PubMed Clinical Study Category filters are subdivided into "Broad" and "Narrow" versions that are designed to maximize either sensitivity or specificity by using two different sets of keywords and Medical Subject Headings (MeSH). A searcher might assume that all items retrieved by Narrow would also be found by Broad, but there are occasions when some [Filter name]/Narrow citations are missed when using [Filter name]/Broad alone. This study quantifies the size of this effect. Methods: For each of the five Clinical Study Categories, PubMed was searched for citations matching the query Filter/Narrow NOT Filter/Broad. This number was compared with that for Filter/Broad to compute the number of Narrow citations missed per 1,000 Broad. This process was repeated for the MeSH terms for "Medicine" and "Diseases," as well as for a set of individual test searches. Results: The Clinical Study Category filters for Etiology, Clinical Prediction Guides, Diagnosis, and Prognosis all showed notable numbers of Filter/Narrow citations that were missed when searching Filter/Broad alone. This was particularly true for Prognosis, where a searcher could easily miss one Prognosis/Narrow citation for every ten Prognosis/Broad citations retrieved. Conclusions: Users of the Clinical Study Category filters (except for Therapy) should consider combining Filter/Narrow together with Filter/Broad in their search strategy. This is particularly true when using Prognosis/Broad, as otherwise there is a substantial risk of missing potentially relevant citations.


Assuntos
Coleta de Dados/métodos , Armazenamento e Recuperação da Informação/métodos , Medical Subject Headings , PubMed , Ferramenta de Busca/normas , Sensibilidade e Especificidade , Humanos
15.
J Med Libr Assoc ; 107(3): 364-373, 2019 Jul.
Artigo em Inglês | MEDLINE | ID: mdl-31258442

RESUMO

Objective: Hypothetically, content in MEDLINE records is consistent across multiple platforms. Though platforms have different interfaces and requirements for query syntax, results should be similar when the syntax is controlled for across the platforms. The authors investigated how search result counts varied when searching records among five MEDLINE platforms. Methods: We created 29 sets of search queries targeting various metadata fields and operators. Within search sets, we adapted 5 distinct, compatible queries to search 5 MEDLINE platforms (PubMed, ProQuest, EBSCOhost, Web of Science, and Ovid), totaling 145 final queries. The 5 queries were designed to be logically and semantically equivalent and were modified only to match platform syntax requirements. We analyzed the result counts and compared PubMed's MEDLINE result counts to result counts from the other platforms. We identified outliers by measuring the result count deviations using modified z-scores centered around PubMed's MEDLINE results. Results: Web of Science and ProQuest searches were the most likely to deviate from the equivalent PubMed searches. EBSCOhost and Ovid were less likely to deviate from PubMed searches. Ovid's results were the most consistent with PubMed's but appeared to apply an indexing algorithm that resulted in lower retrieval sets among equivalent searches in PubMed. Web of Science exhibited problems with exploding or not exploding Medical Subject Headings (MeSH) terms. Conclusion: Platform enhancements among interfaces affect record retrieval and challenge the expectation that MEDLINE platforms should, by default, be treated as MEDLINE. Substantial inconsistencies in search result counts, as demonstrated here, should raise concerns about the impact of platform-specific influences on search results.


Assuntos
Indexação e Redação de Resumos/estatística & dados numéricos , Armazenamento e Recuperação da Informação/métodos , MEDLINE/estatística & dados numéricos , Medical Subject Headings/estatística & dados numéricos , PubMed/estatística & dados numéricos , Algoritmos , Humanos , Armazenamento e Recuperação da Informação/estatística & dados numéricos , Reprodutibilidade dos Testes
16.
Diagn. tratamento ; 24(2): [59-63], abr - jun 2019. tab, fig
Artigo em Português | LILACS | ID: biblio-1015338

RESUMO

Introdução: Com o crescimento contínuo das informações disponíveis na área da saúde, é fundamental que o profissional da saúde desenvolva habilidades e competências para realizar buscas de evidências cientificas. Objetivo: Apresentar as principais bases da área da saúde e os mecanismos de busca específicos para cada uma delas. Métodos: Estudo descritivo desenvolvido na Disciplina de Medicina Baseada em Evidências da Escola Paulista de Medicina (EPM), Universidade Federal de São Paulo (Unifesp). Resultados: Este estudo apresentou os quatro passos do processo de busca em uma base de dados científica da área da saúde: (1) identificação da pergunta estruturada por meio dos acrônimos PICO/PECO, (2) escolha da base de dados (3) escolha e uso dos descritores em saúde apropriados para cada base (DeCS/MeSH/EMTREE) e (4) escolha e uso dos operadores booleanos (AND/OR/AND NOT). Conclusão: O processo de elaboração de uma estratégia de busca para bases de dados da área da saúde pode ser estruturado em quatro passos iniciais, que vão da identificação da pergunta estruturada ao uso dos operadores booleanos. Apropriar-se destes passos é fundamental para conseguir elaborar uma estratégia de busca adequada, capaz de recuperar os estudos de interesse e que abordem realmente a pergunta proposta.


Assuntos
Epidemiologia Descritiva , Bases de Dados Bibliográficas , Medicina Baseada em Evidências , Medical Subject Headings , Metodologia , Ferramenta de Busca
17.
Yearb Med Inform ; 28(1): 27-34, 2019 Aug.
Artigo em Inglês | MEDLINE | ID: mdl-31022748

RESUMO

INTRODUCTION: Artificial intelligence (AI) is widespread in many areas, including medicine. However, it is unclear what exactly AI encompasses. This paper aims to provide an improved understanding of medical AI and its constituent fields, and their interplay with knowledge representation (KR). METHODS: We followed a Wittgensteinian approach ("meaning by usage") applied to content metadata labels, using the Medical Subject Headings (MeSH) thesaurus to classify the field. To understand and characterize medical AI and the role of KR, we analyzed: (1) the proportion of papers in MEDLINE related to KR and various AI fields; (2) the interplay among KR and AI fields and overlaps among the AI fields; (3) interconnectedness of fields; and (4) phrase frequency and collocation based on a corpus of abstracts. RESULTS: Data from over eighty thousand papers showed a steep, six-fold surge in the last 30 years. This growth happened in an escalating and cascading way. A corpus of 246,308 total words containing 21,842 unique words showed several hundred occurrences of notions such as robotics, fuzzy logic, neural networks, machine learning and expert systems in the phrase frequency analysis. Collocation analysis shows that fuzzy logic seems to be the most often collocated notion. Neural networks and machine learning are also used in the conceptual neighborhood of KR. Robotics is more isolated. CONCLUSIONS: Authors note an escalation of published AI studies in medicine. Knowledge representation is one of the smaller areas, but also the most interconnected, and provides a common cognitive layer for other areas.


Assuntos
Inteligência Artificial/estatística & dados numéricos , Bibliometria , Bases de Conhecimento , Inteligência Artificial/tendências , MEDLINE/estatística & dados numéricos , Informática Médica , Medical Subject Headings , Robótica/estatística & dados numéricos
18.
J Med Libr Assoc ; 107(2): 210-221, 2019 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-31019390

RESUMO

Objectives: Errors in search strategies negatively affect the quality and validity of systematic reviews. The primary objective of this study was to evaluate searches performed in MEDLINE/PubMed to identify errors and determine their effects on information retrieval. Methods: A PubMed search was conducted using the systematic review filter to identify articles that were published in January of 2018. Systematic reviews or meta-analyses were selected from a systematic search for literature containing reproducible and explicit search strategies in MEDLINE/PubMed. Data were extracted from these studies related to ten types of errors and to the terms and phrases search modes. Results: The study included 137 systematic reviews in which the number of search strategies containing some type of error was very high (92.7%). Errors that affected recall were the most frequent (78.1%), and the most common search errors involved missing terms in both natural language and controlled language and those related to Medical Subject Headings (MeSH) search terms and the non-retrieval of their more specific terms. Conclusions: To improve the quality of searches and avoid errors, it is essential to plan the search strategy carefully, which includes consulting the MeSH database to identify the concepts and choose all appropriate terms, both descriptors and synonyms, and combining search techniques in the free-text and controlled-language fields, truncating the terms appropriately to retrieve all their variants.


Assuntos
Armazenamento e Recuperação da Informação/métodos , Literatura de Revisão como Assunto , Erro Experimental , Humanos , Medical Subject Headings , Processamento de Linguagem Natural
19.
J Am Med Inform Assoc ; 26(5): 438-446, 2019 05 01.
Artigo em Inglês | MEDLINE | ID: mdl-30811548

RESUMO

OBJECTIVE: In biomedicine, there is a wealth of information hidden in unstructured narratives such as research articles and clinical reports. To exploit these data properly, a word sense disambiguation (WSD) algorithm prevents downstream difficulties in the natural language processing applications pipeline. Supervised WSD algorithms largely outperform un- or semisupervised and knowledge-based methods; however, they train 1 separate classifier for each ambiguous term, necessitating a large number of expert-labeled training data, an unattainable goal in medical informatics. To alleviate this need, a single model that shares statistical strength across all instances and scales well with the vocabulary size is desirable. MATERIALS AND METHODS: Built on recent advances in deep learning, our deepBioWSD model leverages 1 single bidirectional long short-term memory network that makes sense prediction for any ambiguous term. In the model, first, the Unified Medical Language System sense embeddings will be computed using their text definitions; and then, after initializing the network with these embeddings, it will be trained on all (available) training data collectively. This method also considers a novel technique for automatic collection of training data from PubMed to (pre)train the network in an unsupervised manner. RESULTS: We use the MSH WSD dataset to compare WSD algorithms, with macro and micro accuracies employed as evaluation metrics. deepBioWSD outperforms existing models in biomedical text WSD by achieving the state-of-the-art performance of 96.82% for macro accuracy. CONCLUSIONS: Apart from the disambiguation improvement and unsupervised training, deepBioWSD depends on considerably less number of expert-labeled data as it learns the target and the context terms jointly. These merit deepBioWSD to be conveniently deployable in real-time biomedical applications.


Assuntos
Mineração de Dados/métodos , Aprendizado Profundo , Processamento de Linguagem Natural , Redes Neurais de Computação , Vocabulário Controlado , Algoritmos , Ontologias Biológicas , Conjuntos de Dados como Assunto , Medical Subject Headings , Systematized Nomenclature of Medicine , Unified Medical Language System
20.
Z Rheumatol ; 78(2): 155-172, 2019 Mar.
Artigo em Alemão | MEDLINE | ID: mdl-30756138

RESUMO

In order to identify current (and relevant) evidence for a specific clinical question within the unmanageable amount of information available, solid skills in performing a systematic literature search are essential. An efficient approach is to search a biomedical database containing relevant literature citations of study reports. The best known database is MEDLINE, which is searchable for free via the PubMed interface. In this article, we explain step by step how to perform a systematic literature search via PubMed by means of an example research question in the field of ophthalmology. First, we demonstrate how to translate the clinical problem into a well-framed and searchable research question, how to identify relevant search terms and how to conduct a text word search and a search with keywords in medical subject headings (MeSH) terms. We then show how to limit the number of search results if the search yields too many irrelevant hits and how to increase the number in the case of too few citations. Finally, we summarize all essential principles that guide a literature search via PubMed.


Assuntos
Armazenamento e Recuperação da Informação , Medical Subject Headings , Revisões Sistemáticas como Assunto , Bases de Dados Factuais , Humanos , MEDLINE , PubMed
SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA