Search

The BioCreative V chemical-disease relation (CDR) track was proposed to accelerate the progress of text mining in facilitating integrative understanding of chemicals, diseases and their relations. In this article, we describe an extension of our system (namely UET-CAM) that participated in the BioCreative V CDR. The original UET-CAM system's performance was ranked fourth among 18 participating systems by the BioCreative CDR track committee. In the Disease Named Entity Recognition and Normalization (DNER) phase, our system employed joint inference (decoding) with a perceptron-based named entity recognizer (NER) and a back-off model with Semantic Supervised Indexing and Skip-gram for named entity normalization. In the chemical-induced disease (CID) relation extraction phase, we proposed a pipeline that includes a coreference resolution module and a Support Vector Machine relation extraction model. The former module utilized a multi-pass sieve to extend entity recall. In this article, the UET-CAM system was improved by adding a 'silver' CID corpus to train the prediction model. This silver standard corpus of more than 50 thousand sentences was automatically built based on the Comparative Toxicogenomics Database (CTD) database. We evaluated our method on the CDR test set. Results showed that our system could reach the state of the art performance with F1 of 82.44 for the DNER task and 58.90 for the CID task. Analysis demonstrated substantial benefits of both the multi-pass sieve coreference resolution method (F1 + 4.13%) and the silver CID corpus (F1 +7.3%).Database URL: SilverCID-The silver-standard corpus for CID relation extraction is freely online available at: https://zenodo.org/record/34530 (doi:10.5281/zenodo.34530)., (© The Author(s) 2016. Published by Oxford University Press.)

Analysis of scientific and clinical phenotypes reported in the experimental literature has been curated manually to build high-quality databases such as the Online Mendelian Inheritance in Man (OMIM). However, the identification and harmonization of phenotype descriptions struggles with the diversity of human expressivity. We introduce a novel automated extraction approach called PhenoMiner that exploits full parsing and conceptual analysis. Apriori association mining is then used to identify relationships to human diseases. We applied PhenoMiner to the BMC open access collection and identified 13,636 phenotype candidates. We identified 28,155 phenotype-disorder hypotheses covering 4898 phenotypes and 1659 Mendelian disorders. Analysis showed: (i) the semantic distribution of the extracted terms against linked ontologies; (ii) a comparison of term overlap with the Human Phenotype Ontology (HP); (iii) moderate support for phenotype-disorder pairs in both OMIM and the literature; (iv) strong associations of phenotype-disorder pairs to known disease-genes pairs using PhenoDigm. The full list of PhenoMiner phenotypes (S1), phenotype-disorder associations (S2), association-filtered linked data (S3) and user database documentation (S5) is available as supplementary data and can be downloaded at http://github.com/nhcollier/PhenoMiner under a Creative Commons Attribution 4.0 license. Database URL: phenominer.mml.cam.ac.uk., (© The Author(s) 2015. Published by Oxford University Press.)

Concept recognition tools rely on the availability of textual corpora to assess their performance and enable the identification of areas for improvement. Typically, corpora are developed for specific purposes, such as gene name recognition. Gene and protein name identification are longstanding goals of biomedical text mining, and therefore a number of different corpora exist. However, phenotypes only recently became an entity of interest for specialized concept recognition systems, and hardly any annotated text is available for performance testing and training. Here, we present a unique corpus, capturing text spans from 228 abstracts manually annotated with Human Phenotype Ontology (HPO) concepts and harmonized by three curators, which can be used as a reference standard for free text annotation of human phenotypes. Furthermore, we developed a test suite for standardized concept recognition error analysis, incorporating 32 different types of test cases corresponding to 2164 HPO concepts. Finally, three established phenotype concept recognizers (NCBO Annotator, OBO Annotator and Bio-LarK CR) were comprehensively evaluated, and results are reported against both the text corpus and the test suites. The gold standard and test suites corpora are available from http://bio-lark.org/hpo_res.html. Database URL: http://bio-lark.org/hpo_res.html., (© The Author(s) 2015. Published by Oxford University Press.)

Electronic health records and scientific articles possess differing linguistic characteristics that may impact the performance of natural language processing tools developed for one or the other. In this paper, we investigate the performance of four extant concept recognition tools: the clinical Text Analysis and Knowledge Extraction System (cTAKES), the National Center for Biomedical Ontology (NCBO) Annotator, the Biomedical Concept Annotation System (BeCAS) and MetaMap. Each of the four concept recognition systems is applied to four different corpora: the i2b2 corpus of clinical documents, a PubMed corpus of Medline abstracts, a clinical trails corpus and the ShARe/CLEF corpus. In addition, we assess the individual system performances with respect to one gold standard annotation set, available for the ShARe/CLEF corpus. Furthermore, we built a silver standard annotation set from the individual systems' output and assess the quality as well as the contribution of individual systems to the quality of the silver standard. Our results demonstrate that mainly the NCBO annotator and cTAKES contribute to the silver standard corpora (F1-measures in the range of 21% to 74%) and their quality (best F1-measure of 33%), independent from the type of text investigated. While BeCAS and MetaMap can contribute to the precision of silver standard annotations (precision of up to 42%), the F1-measure drops when combined with NCBO Annotator and cTAKES due to a low recall. In conclusion, the performances of individual systems need to be improved independently from the text types, and the leveraging strategies to best take advantage of individual systems' annotations need to be revised. The textual content of the PubMed corpus, accession numbers for the clinical trials corpus, and assigned annotations of the four concept recognition systems as well as the generated silver standard annotation sets are available from http://purl.org/phenotype/resources. The textual content of the ShARe/CLEF (https://sites.google.com/site/shareclefehealth/data) and i2b2 (https://i2b2.org/NLP/DataSets/) corpora needs to be requested with the individual corpus providers.

The identification of phenotype descriptions in the scientific literature, case reports and patient records is a rewarding task for bio-medical text mining. Any progress will support knowledge discovery and linkage to other resources. However because of their wide variation a number of challenges still remain in terms of their identification and semantic normalisation before they can be fully exploited for research purposes. This paper presents novel techniques for identifying potential complex phenotype mentions by exploiting a hybrid model based on machine learning, rules and dictionary matching. A systematic study is made of how to combine sequence labels from these modules as well as the merits of various ontological resources. We evaluated our approach on a subset of Medline abstracts cited by the Online Mendelian Inheritance of Man database related to auto-immune diseases. Using partial matching the best micro-averaged F-score for phenotypes and five other entity classes was 79.9%. A best performance of 75.3% was achieved for phenotype candidates using all semantics resources. We observed the advantage of using SVM-based learn-to-rank for sequence label combination over maximum entropy and a priority list approach. The results indicate that the identification of simple entity types such as chemicals and genes are robustly supported by single semantic resources, whereas phenotypes require combinations. Altogether we conclude that our approach coped well with the compositional structure of phenotypes in the auto-immune domain.

Real world pandemics such as SARS 2002 as well as popular fiction like the movie Contagion graphically depict the health threat of a global pandemic and the key role of epidemic intelligence (EI). While EI relies heavily on established indicator sources a new class of methods based on event alerting from unstructured digital Internet media is rapidly becoming acknowledged within the public health community. At the heart of automated information gathering systems is a technology called text mining. My contribution here is to provide an overview of the role that text mining technology plays in detecting epidemics and to synthesise my existing research on the BioCaster project.

Purpose: The emergence and re-emergence of disease outbreaks of international concern in the last several years has raised the importance of health surveillance systems that exploit the open media for their timely and precise detection of events. However, one of the key barriers faced by current event-based health surveillance systems is in identifying fine-grained terms for an outbreak's geographical location. In this article, we present a method to tackle this problem by associating each reported event with the most specific spatial information available in a news report. This would be useful not only for health surveillance systems, but also for other event-centered processing systems., Methods: To develop an automated spatial attribute annotation system, we first created a gold standard corpus for training a machine learning model. Since the qualitative analysis on data suggested that the event class might have an impact on the spatial attribute annotation, we also developed an event classification system to incorporate event class information into the spatial attribute annotation model. To automatically recognize the spatial attribute of events, several approaches, ranging from a simple heuristic technique to a more sophisticated approach based on a state-of-the-art Conditional Random Fields (CRFs) model were explored. Different feature sets were incorporated into the model and compared., Results: The evaluations were conducted on 100 outbreak news articles. Spatial attribute recognition performance was evaluated based on three metrics; precision, recall and the harmonic mean of precision and recall (F-score). Among three strategies proposed in this article, the CRF model appeared to be the most promising for spatial attribute recognition with a best performance of 85.5% F-score (86.3% precision and 84.7% recall)., Conclusion: We presented a methodology for associating each event in media outbreak reports with their spatial attribute at the finest level of granularity. Our goal has been to provide a means for enhancing the spatial understanding of outbreak-related events. Evaluation studies showed promising results for automatic spatial attribute annotation. In the future, we plan to explore more features, such as semantic correlation between words, that maybe useful for the spatial attribute annotation task., ((c) 2010 Elsevier Ireland Ltd. All rights reserved.)