Developing a manually annotated clinical document corpus to identify phenotypic information for inflammatory bowel disease

South, Brett R.; Shen, Shuying; Jones, Makoto; Garvin, Jennifer H.; Samore, Matthew H.; Chapman, Wendy W.; Gundlapalli, Adi V.

doi:10.1186/1471-2105-10-s9-s12

Cited by 38 publications

(29 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Other existing biomedical datasets annotate only diseases; they include the NCBI disease corpus [4] which consists of 793 PubMed abstracts with 6,892 disease mentions and 790 unique disease concepts mapped to the Medical Subject Headings (MeSH), 11 and the Arizona Disease Corpus (AZDC) [9] which contains 2,784 sentences from MEDLINE abstracts annotated with disease mentions and mapped to the Unified Medical Language System (UMLS) 12 . Symptom recognition [10] is a relatively new task, often included in more general categories such as clinical concepts [19], medical problems [18] or phenotypic information [16]. Even on these categories, few studies take advantage of considering the linguistic context in which symptoms appear, and they are more focused on the linguistic analysis.…”

Section: Related Workmentioning

confidence: 99%

Weakly-Supervised Symptom Recognition for Rare Diseases in Biomedical Text

Holat¹,

Tomeh²,

Charnois³

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In this paper, we tackle the issue of symptom recognition for rare diseases in biomedical texts. Symptoms typically have more complex and ambiguous structure than other biomedical named entities. Furthermore, existing resources are scarce and incomplete. Therefore, we propose a weakly-supervised framework based on a combination of two approaches: sequential pattern mining under constraints and sequence labeling. We use unannotated biomedical paper abstracts with dictionaries of rare diseases and symptoms to create our training data. Our experiments show that both approaches outperform simple projection of the dictionaries on text, and their combination is beneficial. We also introduce a novel pattern mining constraint based on semantic similarity between words inside patterns.

show abstract

Section: Related Workmentioning

confidence: 99%

Weakly-Supervised Symptom Recognition for Rare Diseases in Biomedical Text

Holat¹,

Tomeh²,

Charnois³

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…H & P NOTEs had a similar number of average sections, and an equally large standard deviation of 13.88. The document types with the lowest average number of sections (2) were NO SHOW NOTE (stdev = 2.81), GROUP COUNSELING NOTE (stdev = 1.38), IMMUNIZATION NOTE (stdev = 1.26), and SCANNED NOTE (stdev = 0.66).…”

Section: Document Structure Analysis (Section)mentioning

confidence: 99%

“…A number of studies have applied Natural Language Processing (NLP) techniques to VistA free text data [1][2][3][4][5][6][7], with promising results. These studies have, however, only explored a very small fraction of the vast amount of VistA notes in terms of domain and facility coverage.…”

Section: Introductionmentioning

confidence: 99%

Characterizing Clinical Text and Sublanguage: A Case Study of the VA Clinical Notes

Zeng¹

2013

J Health Med Inform

View full text Add to dashboard Cite

Objective: To characterize text and sublanguage in medical records to better address challenges within Natural Language Processing (NLP) tasks such as information extraction, word sense disambiguation, information retrieval, and text summarization. The text and sublanguage analysis is needed to scale up the NLP development for large and diverse free-text clinical data sets. Design: This is a quantitative descriptive study which analyzes the text and sublanguage characteristics of a very large Veteran Affairs (VA) clinical note corpus (569 million notes) to guide the customization of natural language processing (NLP) of VA notes. Methods: We randomly sampled 100,000 notes from the top 100 most frequently appearing document types. We examined surface features and used those features to identify sublanguage groups using unsupervised clustering. Results: Using the text features, we are able to characterize each of the 100 document types and identify 16 distinct sublanguage groups. The identified sublanguages reflect different clinical domains and types of encounters within the sample corpus. We also found much variance within each of the document types. Such characteristics will facilitate the tuning and crafting of NLP tools. Conclusion: Using a diverse and large sample of clinical text, we were able to show that there are a relatively large number of sublanguages and variance both within and between document types. These findings will guide NLP development to create more customizable and generalizable solutions across medical domains and sublanguages.

show abstract

“…In the medical domain, Knowtator (Ogren 2006) has been most often used (Ogren et al 2008;South et al 2009;Roberts et al 2009). There exist several available open-source tools for manually annotating text corpora.…”

Section: Annotation Toolsmentioning

confidence: 99%

Pediatric Biomedical Informatics

Hutton¹

2012

Translational Bioinformatics

View full text Add to dashboard Cite

Aims and ScopeThe Book Series in Translational Bioinformatics is a powerful and integrative resource for understanding and translating discoveries and advances of genomic, transcriptomic, proteomic and bioinformatic technologies into the study of human diseases. The Series represents leading global opinions on the translation of bioinformatics sciences into both the clinical setting and descriptions to medical informatics. It presents the critical evidence to further understand the molecular mechanisms underlying organ or cell dysfunctions in human diseases, the results of genomic, transcriptomic, proteomic and bioinformatic studies from human tissues dedicated to the discovery and validation of diagnostic and prognostic disease biomarkers, essential information on the identification and validation of novel drug targets and the application of tissue genomics, transcriptomics, proteomics and bioinformatics in drug efficacy and toxicity in clinical research.The Book Series in Translational Bioinformatics focuses on outstanding articles/chapters presenting significant recent works in genomic, transcriptomic, proteomic and bioinformatic profiles related to human organ or cell dysfunctions and clinical findings. The Series includes bioinformatics-driven molecular and cellular disease mechanisms, the understanding of human diseases and the improvement of patient prognoses. Additionally, it provides practical and useful study insights into and protocols of design and methodology. Series DescriptionTranslational bioinformatics is defined as the development of storage-related, analytic, and interpretive methods to optimize the transformation of increasingly voluminous biomedical data, and genomic data in particular, into proactive, predictive, preventive, and participatory health. Translational bioinformatics includes research on the development of novel techniques for the integration of biological and clinical data and the evolution of clinical informatics methodology to encompass biological observations. The end product of translational bioinformatics is the newly found knowledge from these integrative efforts that can be disseminated to a variety of stakeholders including biomedical scientists, clinicians, and patients. Issues related to database management, administration, or policy will be coordinated through the clinical research informatics domain. Analytic, storage-related, and interpretive methods should be used to improve predictions, early diagnostics, severity monitoring, therapeutic effects, and the prognosis of human diseases.

show abstract

Developing a manually annotated clinical document corpus to identify phenotypic information for inflammatory bowel disease

Cited by 38 publications

References 10 publications

Weakly-Supervised Symptom Recognition for Rare Diseases in Biomedical Text

Weakly-Supervised Symptom Recognition for Rare Diseases in Biomedical Text

Characterizing Clinical Text and Sublanguage: A Case Study of the VA Clinical Notes

Pediatric Biomedical Informatics

Contact Info

Product

Resources

About