Concept Recognition Research Articles

BeCAS: biomedical concept recognition services and visualization

The continuous growth of the biomedical scientific literature has been motivating the development of text-mining tools able to efficiently process all this information. Although numerous domain-specific solutions are available, there is no web-based concept-recognition system that combines the ability to select multiple concept types to annotate, to reference external databases and to automatically annotate nested and intercepted concepts. BeCAS, the Biomedical Concept Annotation System, is an API for biomedical concept identification and a web-based tool that addresses these limitations. MEDLINE abstracts or free text can be annotated directly in the web interface, where identified concepts are enriched with links to reference databases. Using its customizable widget, it can also be used to augment external web pages with concept highlighting features. Furthermore, all text-processing and annotation features are made available through an HTTP REST API, allowing integration in any text-processing pipeline. BeCAS is freely available for non-commercial use at http://bioinformatics.ua.pt/becas. tiago.nunes@ua.pt or jlo@ua.pt.

Mo1342 A Concept Recognition Tool to Identify the Surgical Complications of Crohn's Disease in Electronic Health Records

Background: Previous studies have shown that diagnosis of Crohn's disease (CD) in childhood is associated with a different phenotype when compared to adults (higher risk for ileocolonic disease and fibrostenotic behavior), and may be associated with a more aggressive form of disease requiring more surgery. Those diagnosed at an older age have been reported to have an increased rate of isolated colonic disease and a milder course of disease requiring less surgery. Methods: A comprehensive medical chart review was done for 571 CD patients that were followed in a tertiary referral IBD clinic. Among the parameters that were recorded for each patient at specific time intervals were parameters of disease phenotype according to the Montreal Classification (A1 diagnosed ,16, n=88, A2 diagnosed 16-40, n=287, A3 diagnosed .40, n=77) as well as having surgery. Results: The study included 452 patients that had complete data in the charts. At 6 years from diagnosis and at last follow-up (median11 years), A3 had a higher rate of isolated colonic disease than A1 but not in comparison to A2. Perianal involvement was significantly less common in A3 than A1 or A2. Complicated disease behavior (B2/B3) was similar for all three groups at both time frames. Nonetheless, at 6 years and last follow-up, IBD-related abdominal surgery rates were significantly lower for A1 vs. A2 and vs A3. Conclusions: While there are some disease location differences that emerge with increasing age of presentation (more isolated colonic disease and less perineal disease) disease behavior over time is similar regardless of age at diagnosis and surgeries were least likely in those diagnosed prior to age 16. Our study did not corroborate a more aggressive course for CD that presents in the pediatric age group. Outcomes at 6 years from diagnosis

Pooling annotated corpora for clinical concept extraction

BackgroundThe availability of annotated corpora has facilitated the application of machine learning algorithms to concept extraction from clinical notes. However, high expenditure and labor are required for creating the annotations. A potential alternative is to reuse existing corpora from other institutions by pooling with local corpora, for training machine taggers. In this paper we have investigated the latter approach by pooling corpora from 2010 i2b2/VA NLP challenge and Mayo Clinic Rochester, to evaluate taggers for recognition of medical problems. The corpora were annotated for medical problems, but with different guidelines. The taggers were constructed using an existing tagging system MedTagger that consisted of dictionary lookup, part of speech (POS) tagging and machine learning for named entity prediction and concept extraction. We hope that our current work will be a useful case study for facilitating reuse of annotated corpora across institutions.ResultsWe found that pooling was effective when the size of the local corpus was small and after some of the guideline differences were reconciled. The benefits of pooling, however, diminished as more locally annotated documents were included in the training data. We examined the annotation guidelines to identify factors that determine the effect of pooling.ConclusionsThe effectiveness of pooling corpora, is dependent on several factors, which include compatibility of annotation guidelines, distribution of report types and size of local and foreign corpora. Simple methods to rectify some of the guideline differences can facilitate pooling. Our findings need to be confirmed with further studies on different corpora. To facilitate the pooling and reuse of annotated corpora, we suggest that – i) the NLP community should develop a standard annotation guideline that addresses the potential areas of guideline differences that are partly identified in this paper; ii) corpora should be annotated with a two-pass method that focuses first on concept recognition, followed by normalization to existing ontologies; and iii) metadata such as type of the report should be created during the annotation process.

Insights from classifying visual concepts with multiple kernel learning.

Combining information from various image features has become a standard technique in concept recognition tasks. However, the optimal way of fusing the resulting kernel functions is usually unknown in practical applications. Multiple kernel learning (MKL) techniques allow to determine an optimal linear combination of such similarity matrices. Classical approaches to MKL promote sparse mixtures. Unfortunately, 1-norm regularized MKL variants are often observed to be outperformed by an unweighted sum kernel. The main contributions of this paper are the following: we apply a recently developed non-sparse MKL variant to state-of-the-art concept recognition tasks from the application domain of computer vision. We provide insights on benefits and limits of non-sparse MKL and compare it against its direct competitors, the sum-kernel SVM and sparse MKL. We report empirical results for the PASCAL VOC 2009 Classification and ImageCLEF2010 Photo Annotation challenge data sets. Data sets (kernel matrices) as well as further information are available at http://doc.ml.tu-berlin.de/image_mkl/(Accessed 2012 Jun 25).

A COMPARISON OF SEMANTIC SIMILARITY MODELS IN EVALUATING CONCEPT SIMILARITY

Abstract. The semantic similarities are important in concept definition, recognition, categorization, interpretation, and integration. Many semantic similarity models have been established to evaluate semantic similarities of objects or/and concepts. To find out the suitability and performance of different models in evaluating concept similarities, we make a comparison of four main types of models in this paper: the geometric model, the feature model, the network model, and the transformational model. Fundamental principles and main characteristics of these models are introduced and compared firstly. Land use and land cover concepts of NLCD92 are employed as examples in the case study. The results demonstrate that correlations between these models are very high for a possible reason that all these models are designed to simulate the similarity judgement of human mind.

Research of Feature Recognition Method Based on STEP-NC

To achieve the numerical control (NC) system based on the standard for the exchange of product model data-numerical control (STEP-NC), the feature concept and feature recognition method of STEP-NC is proposed. The meaning of feature in STEP-NC, while the three classification methods of STEP-NC feature were also presented. The expression methods of STEP-NC feature were analyzed in details. Furthermore, the feature recognition methods based on above the analyse were described. Finally, we simulate several machining features on STEP-NC milling simulation system. The simulation results demonstrate that the feature recognition method is correct and feasible.

Towards a universal detector by mining concepts with small semantic gaps

Can we have a universal detector that could visually recognize unseen objects with no training exemplars available? Such a detector is so desirable, as there are hundreds of thousands of object concepts in human vocabulary but few labeled image examples available. In this study, we attempt to build such a universal detector to predict concepts in the absence of training data. First, by considering both semantic relatedness and visual variance, we mine a set of realistic small-semantic-gap (SSG) concepts from a large-scale image corpus, i.e., ImageNet, which comprises 4961 concepts and nearly 4 million images. The discovered SSG concepts can be depicted well by visual models and their detectors can deliver reasonably satisfactory recognition accuracies. From these distinctive visual models, we then leverage the semantic ontology knowledge and co-occurrence statistics of concepts to extend visual recognition to unseen concepts. The rational is that object concepts generally co-occur in a real-life image. Their visual co-occurrence and semantic ontology provide the possibility for concept recognition to transcend the visual learning of image exemplars, and therefore, enable the detector to predict unseen realistic concepts without training samples. To the best of our knowledge, this work presents the first research attempting to substantiate the semantic gap measuring of a large amount of concepts and leverage visually learnable concepts to predicate those with no training images available. Testings on NUS-WIDE dataset demonstrate that the selected concepts with small semantic gaps can be well modeled and the prediction of unseen concepts delivers promising results with comparable accuracy to preliminary training-based methods.

Automating classification of free‐text electronic health records for epidemiological studies

Increasingly, patient information is stored in electronic medical records, which could be reused for research. Often these records comprise unstructured narrative data, which are cumbersome to analyze. The authors investigated whether text mining can make these data suitable for epidemiological studies and compared a concept recognition approach and a range of machine learning techniques that require a manually annotated training set. The authors show how this training set can be created with minimal effort by using a broad database query. The approaches were tested on two data sets: a publicly available set of English radiology reports for which International Classification of Diseases, Ninth Revision, Clinical Modification code needed to be assigned and a set of Dutch GP records that needed to be classified as either liver disorder cases or noncases. Performance was tested against a manually created gold standard. The best overall performance was achieved by a combination of a manually created filter for removing negations and speculations and rule learning algorithms such as RIPPER, with high scores on both the radiology reports (positive predictive value = 0.88, sensitivity = 0.85, specificity = 1.00) and the GP records (positive predictive value = 0.89, sensitivity =0.91, specificity =0.76). Although a training set still needs to be created manually, text mining can help reduce the amount of manual work needed to incorporate narrative data in an epidemiological study and will make the data extraction more reproducible. An advantage of machine learning is that it is able to pick up specific language use, such as abbreviations and synonyms used by physicians.

Using an ensemble system to improve concept extraction from clinical records

Recognition of medical concepts is a basic step in information extraction from clinical records. We wished to improve on the performance of a variety of concept recognition systems by combining their individual results.We selected two dictionary-based systems and five statistical-based systems that were trained to annotate medical problems, tests, and treatments in clinical records. Manually annotated clinical records for training and testing were made available through the 2010 i2b2/VA (Informatics for Integrating Biology and the Bedside) challenge. Results of individual systems were combined by a simple voting scheme. The statistical systems were trained on a set of 349 records. Performance (precision, recall, F-score) was assessed on a test set of 477 records, using varying voting thresholds.The combined annotation system achieved a best F-score of 82.2% (recall 81.2%, precision 83.3%) on the test set, a score that ranks third among 22 participants in the i2b2/VA concept annotation task. The ensemble system had better precision and recall than any of the individual systems, yielding an F-score that is 4.6% point higher than the best single system. Changing the voting threshold offered a simple way to obtain a system with high precision (and moderate recall) or one with high recall (and moderate precision).The ensemble-based approach is straightforward and allows the balancing of precision versus recall of the combined system. The ensemble system is freely available and can easily be extended, integrated in other systems, and retrained.

Synthesis of Pillar[5]arene Dimers and Their Cooperative Binding toward Some Neutral Guests

Three pillar[5]arene dimers, bridged by a flexible aliphatic chain (H1) or a relatively rigid phenylene unit (H2 and H3), were synthesized, with the possible synthetic strategies being discussed. The dimers could significantly enhance the binding affinities toward neutral model substrates in comparison with monomeric 1,4-dimethoxypillar[5]arene (H4) through the cooperative binding of two pillar[5]arene moieties. The molecular binding ability and selectivity are discussed from the viewpoints of the size/shape-fit concept and multiple recognition mechanism.

Stringent response of Escherichia coli: revisiting the bibliome using literature mining

BackgroundUnderstanding the mechanisms responsible for cellular responses depends on the systematic collection and analysis of information on the main biological concepts involved. Indeed, the identification of biologically relevant concepts in free text, namely genes, tRNAs, mRNAs, gene products and small molecules, is crucial to capture the structure and functioning of different responses.ResultsIn this work, we review literature reports on the study of the stringent response in Escherichia coli. Rather than undertaking the development of a highly specialised literature mining approach, we investigate the suitability of concept recognition and statistical analysis of concept occurrence as means to highlight the concepts that are most likely to be biologically engaged during this response. The co-occurrence analysis of core concepts in this stringent response, i.e. the (p)ppGpp nucleotides with gene products was also inspected and suggest that besides the enzymes RelA and SpoT that control the basal levels of (p)ppGpp nucleotides, many other proteins have a key role in this response. Functional enrichment analysis revealed that basic cellular processes such as metabolism, transcriptional and translational regulation are central, but other stress-associated responses might be elicited during the stringent response. In addition, the identification of less annotated concepts revealed that some (p)ppGpp-induced functional activities are still overlooked in most reviews.ConclusionsIn this paper we applied a literature mining approach that offers a more comprehensive analysis of the stringent response in E. coli. The compilation of relevant biological entities to this stress response and the assessment of their functional roles provided a more systematic understanding of this cellular response. Overlooked regulatory entities, such as transcriptional regulators, were found to play a role in this stress response. Moreover, the involvement of other stress-associated concepts demonstrates the complexity of this cellular response.

HIGH-PRECISION BIOLOGICAL EVENT EXTRACTION: EFFECTS OF SYSTEM AND OF DATA.

We approached the problems of event detection, argument identification, and negation and speculation detection in the BioNLP'09 information extraction challenge through concept recognition and analysis. Our methodology involved using the OpenDMAP semantic parser with manually written rules. The original OpenDMAP system was updated for this challenge with a broad ontology defined for the events of interest, new linguistic patterns for those events, and specialized coordination handling. We achieved state-of-the-art precision for two of the three tasks, scoring the highest of 24 teams at precision of 71.81 on Task 1 and the highest of 6 teams at precision of 70.97 on Task 2. We provide a detailed analysis of the training data and show that a number of trigger words were ambiguous as to event type, even when their arguments are constrained by semantic class. The data is also shown to have a number of missing annotations. Analysis of a sampling of the comparatively small number of false positives returned by our system shows that major causes of this type of error were failing to recognize second themes in two-theme events, failing to recognize events when they were the arguments to other events, failure to recognize nontheme arguments, and sentence segmentation errors. We show that specifically handling coordination had a small but important impact on the overall performance of the system. The OpenDMAP system and the rule set are available at http://bionlp.sourceforge.net.

A context-blocks model for identifying clinical relationships in patient records

BackgroundPatient records contain valuable information regarding explanation of diagnosis, progression of disease, prescription and/or effectiveness of treatment, and more. Automatic recognition of clinically important concepts and the identification of relationships between those concepts in patient records are preliminary steps for many important applications in medical informatics, ranging from quality of care to hypothesis generation.MethodsIn this work we describe an approach that facilitates the automatic recognition of eight relationships defined between medical problems, treatments and tests. Unlike the traditional bag-of-words representation, in this work, we represent a relationship with a scheme of five distinct context-blocks determined by the position of concepts in the text. As a preliminary step to relationship recognition, and in order to provide an end-to-end system, we also addressed the automatic extraction of medical problems, treatments and tests. Our approach combined the outcome of a statistical model for concept recognition and simple natural language processing features in a conditional random fields model. A set of 826 patient records from the 4th i2b2 challenge was used for training and evaluating the system.ResultsResults show that our concept recognition system achieved an F-measure of 0.870 for exact span concept detection. Moreover the context-block representation of relationships was more successful (F-Measure = 0.775) at identifying relationships than bag-of-words (F-Measure = 0.402). Most importantly, the performance of the end-to-end system of relationship extraction using automatically extracted concepts (F-Measure = 0.704) was comparable to that obtained using manually annotated concepts (F-Measure = 0.711), and their difference was not statistically significant.ConclusionsWe extracted important clinical relationships from text in an automated manner, starting with concept recognition, and ending with relationship identification. The advantage of the context-blocks representation scheme was the correct management of word position information, which may be critical in identifying certain relationships. Our results may serve as benchmark for comparison to other systems developed on i2b2 challenge data. Finally, our system may serve as a preliminary step for other discovery tasks in medical informatics.

Quantifying the impact of concept recognition on biomedical information retrieval

In ad hoc querying of document collections, current approaches to ranking primarily rely on identifying the documents that contain the query terms. Methods such as query expansion, based on thesaural information or automatic feedback, are used to add further terms, and can yield significant though usually small gains in effectiveness. Another approach to adding terms, which we investigate in this paper, is to use natural language technology to annotate – and thus disambiguate – key terms by the concept they represent. Using biomedical research documents, we quantify the potential benefits of tagging users’ targeted concepts in queries and documents in domain-specific information retrieval. Our experiments, based on the TREC Genomics track data, both on passage and full-text retrieval, found no evidence that automatic concept recognition in general is of significant value for this task. Moreover, the issues raised by these results suggest that it is difficult for such disambiguation to be effective.

Dragon exploratory system on Hepatitis C Virus (DESHCV)

Even though Hepatitis C Virus (HCV) cDNA was characterized about 20 years ago, there is insufficient understanding of the molecular etiology underlying HCV infections. Current global rates of infection and its increasingly chronic character are causes of concern for health policy experts. Vast amount of data accumulated from biochemical, genomic, proteomic, and other biological analyses allows for novel insights into the HCV viral structure, life cycle and functions of its proteins. Biomedical text-mining is a useful approach for analyzing the increasing corpus of published scientific literature on HCV. We report here the first comprehensive HCV customized biomedical text-mining based online web resource, dragon exploratory system on Hepatitis C Virus (DESHCV), a biomedical text-mining and relationship exploring knowledgebase was developed by exploring literature on HCV. The pre-compiled dictionaries existing in the dragon exploratory system (DES) were enriched with biomedical concepts pertaining to HCV proteins, their name variants and symbols to make it suitable for targeted information exploration and knowledge extraction as focused on HCV. A list of 32,895 abstracts retrieved via PubMed database using specific keywords searches related to HCV were processed based on concept recognition of terms from several dictionaries. The web query interface enables retrieval of information using specified concepts, keywords and phrases, generating text-derived association networks and hypotheses, which could be tested to identify potentially novel relationship between different concepts. Such an approach could also augment efforts in the search for diagnostic or even therapeutic targets. DESHCV thus represents online literature-based discovery resource freely accessible for academic and non-profit users via http://apps.sanbi.ac.za/DESHCV/ and its mirror site http://cbrc.kaust.edu.sa/deshcv/.

Molecular Recognition of Bridged Bis(β-cyclodextrin) Linked by the 4,4′-Diaminodiphenyl Sulfone Tether with Non-aromatic Oligopeptides

The molecular recognition behavior of 4,4′-diaminodiphenyl sulfone bis(β-cyclodextrin) 1 with representative non-aromatic oligopeptides (Leu-Gly, Gly-Leu, Glu-Glu, Met-Met, Gly-Gly, Gly-Gly-Gly and Gly-Pro) was investigated by circular dichroism, fluorescence, 1H and 2D NMR spectroscopy at 25 °C in phosphate buffer solutions (pH=7.20). From the circular dichroism and 2D NMR results, it is inferred that the phenyl moiety in the linker of bis(β-cyclodextrin) is partly self-included in the cyclodextrin cavity, and it is entirely expelled out of the cyclodextrin cavity upon complexation with oligopeptides. Owing to the cooperative sandwich binding mode, bis(β-cyclodextrin) not only affords the highest binding constant of 29200 L⋅mol−1 for the tripeptide Gly-Gly-Gly, but it also can recognize the size and hydrophobicity of oligopeptides. The bis(β-cyclodextrin) gives an exciting residue selectivity of up to 78.9 for the Gly-Gly-Gly/Glu-Glu pair, and a higher length selectivity of up to 28.1 for the Gly-Gly-Gly/Gly-Gly pair. These phenomena are discussed from the viewpoint of the size-fit concept and multipoint recognition between host and guest.

Synthesis of Novel Bis(β‐cyclodextrin)s Linked with Glycol and Their Inclusion Complexation with Organic Dyes

AbstractThree novel bis(β‐cyclodextrin (CD))s with flexible glycol linkers, i.e., ethylene glycol‐bridged bis(6‐hydroxy‐6‐deoxy‐β‐CD) (2), diethylene glycol‐bridged bis(6‐hydroxy‐6‐deoxy‐β‐CD) (3), and triethylene glycol‐bridged bis(6‐hydroxy‐6‐deoxy‐β‐CD) (4) have been synthesized by the reaction of mono[6‐O‐(p‐toluenesulfonyl)]‐β‐CD with corresponding materials. The inclusion complexation behaviors of these compounds 2–4 with organic dyes; that is, acridine red (=N‐[(3Z)‐6‐(methylamino)‐3H‐xanthen‐3‐ylidene]methanaminium chloride; AR), neutral red (=N8,N8,3‐trimethylphenazine‐2,8‐diamine hydrochloride; NR), ammonium 8‐anilinonaphthalene‐1‐sulfonate (ANS), sodium 6‐(p‐toluidinyl)‐naphthalene‐2‐sulfonate (TNS), rhodamine B (RhB) and brilliant green (=N‐(4‐{[4‐(diethylamino)cyclohexa‐2,5‐dien‐1‐yl](phenyl)methyl}cyclohex‐2‐en‐1‐ylidene)‐N‐ethyl‐ethanaminium hydrogen sulfate; BG), have been investigated at 25° in phosphate buffer (pH 7.20) by ultraviolet, fluorescence, and 2D‐NMR spectroscopy. The results indicate that the two linked CD units may cooperatively bind a guest, and the molecular binding ability toward dye guests, especially bent ANS, T‐shaped RhB, and triangular BG, can be extended. This cooperative binding mode is confirmed by Job's experiments and 2D‐NMR investigations. Furthermore, the complex stability depends greatly on the linker length of these glycol‐bridged bis(β‐CD)s and the size and shape of guest. The higher binding ability and selectivity of dye molecules by bis(β‐CD)s 2–4 are discussed from the viewpoint of size/shape‐fit concept and multiple recognition mechanism.

Extraction of genotype-phenotype-drug relationships from text: from entity recognition to bioinformatics application.

Advances in concept recognition and natural language parsing have led to the development of various tools that enable the identification of biomedical entities and relationships between them in text. The aim of the Genotype-Phenotype-Drug Relationship Extraction from Text workshop (or GPD-Rx workshop) is to examine the current state of art and discuss the next steps for making the extraction of relationships between biomedical entities integral to the curation and knowledge management workflow in Pharmacogenomics. The workshop will focus particularly on the extraction of Genotype-Phenotype, Genotype-Drug, and Phenotype-Drug relationships that are of interest to Pharmacogenomics. Extracting and structuring such text-mined relationships is a key to support the evaluation and the validation of multiple hypotheses that emerge from high throughput translational studies spanning multiple measurement modalities. In order to advance this agenda, it is essential that existing relationship extraction methods be compared to one another and that a community wide benchmark corpus emerges; against which future methods can be compared. The workshop aims to bring together researchers working on the automatic or semi-automatic extraction of relationships between biomedical entities from research literature in order to identify the key groups interested in creating such a benchmark.

프로야구 관람자의 관람동기가 정신집중, 시간적 개념인지결여, 경기만족에 미치는 영향

프로야구 관람자의 관람동기가 정신집중, 시간적 개념인지결여, 경기만족에 미치는 영향

Ontology-based video retrieval

The paper presents an ontological approach for enabling semantic-aware video retrieval framework facilitating the user access to desired contents. Through the ontologies, the system will express key entities and relationships describing videos in a formal machine-processable representation. An ontology-based knowledge representation could be used for content analysis and concept recognition, for reasoning processes and for enabling user-friendly and intelligent multimedia content retrieval.