Skip to main page content
Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Nov 12;10(Suppl 1):22.
doi: 10.1186/s13326-019-0212-6.

Exploring Semantic Deep Learning for Building Reliable and Reusable One Health Knowledge From PubMed Systematic Reviews and Veterinary Clinical Notes

Affiliations
Free PMC article

Exploring Semantic Deep Learning for Building Reliable and Reusable One Health Knowledge From PubMed Systematic Reviews and Veterinary Clinical Notes

Mercedes Arguello-Casteleiro et al. J Biomed Semantics. .
Free PMC article

Abstract

Background: Deep Learning opens up opportunities for routinely scanning large bodies of biomedical literature and clinical narratives to represent the meaning of biomedical and clinical terms. However, the validation and integration of this knowledge on a scale requires cross checking with ground truths (i.e. evidence-based resources) that are unavailable in an actionable or computable form. In this paper we explore how to turn information about diagnoses, prognoses, therapies and other clinical concepts into computable knowledge using free-text data about human and animal health. We used a Semantic Deep Learning approach that combines the Semantic Web technologies and Deep Learning to acquire and validate knowledge about 11 well-known medical conditions mined from two sets of unstructured free-text data: 300 K PubMed Systematic Review articles (the PMSB dataset) and 2.5 M veterinary clinical notes (the VetCN dataset). For each target condition we obtained 20 related clinical concepts using two deep learning methods applied separately on the two datasets, resulting in 880 term pairs (target term, candidate term). Each concept, represented by an n-gram, is mapped to UMLS using MetaMap; we also developed a bespoke method for mapping short forms (e.g. abbreviations and acronyms). Existing ontologies were used to formally represent associations. We also create ontological modules and illustrate how the extracted knowledge can be queried. The evaluation was performed using the content within BMJ Best Practice.

Results: MetaMap achieves an F measure of 88% (precision 85%, recall 91%) when applied directly to the total of 613 unique candidate terms for the 880 term pairs. When the processing of short forms is included, MetaMap achieves an F measure of 94% (precision 92%, recall 96%). Validation of the term pairs with BMJ Best Practice yields precision between 98 and 99%.

Conclusions: The Semantic Deep Learning approach can transform neural embeddings built from unstructured free-text data into reliable and reusable One Health knowledge using ontologies and content from BMJ Best Practice.

Keywords: CBOW; Deep learning; Module extraction; One health; Ontology; PubMed; SNOMED CT; Semantic deep learning; Skip-gram; Veterinary clinical narratives.

Conflict of interest statement

The authors declare that they have no competing interests.

Figures

Fig. 1
Fig. 1
Flowchart of the short form detector introduced – a diagrammatic representation outlining how the short form detector assigns the labels {SF-U, SF-NU, SF}. If no label is assigned, this means that the n-gram has no clinically meaningful short form(s)
Fig. 2
Fig. 2
Overview of the extended version of the lemon core ontology (called here the lemonEXT) used for this study
Fig. 3
Fig. 3
Overview of the modified version of the OBAN core ontology (called here the OBANmod) used for this study
Fig. 4
Fig. 4
Exemplifying the population of both the lemonEXT and OBANmod core ontologies – the figure illustrates how the 3-tuple (C0017601|Glaucoma, C0020581|Hyphema, “Relatedness by Inexact match (background knowledge)”) is represented as a modified version of the OBAN association. This 3-tuple has two bibo:excerpts: 1) the term “trabeculotomy” from BMJ Best Practice for open-angle glaucoma; and 2) few lines of text from the PubMed article with identifier PMID = 29,035,912. The top of the figure shows the lexical entry from the lemonEXT ontology corresponding to the focus concept C0020581|Hyphema

Similar articles

See all similar articles

References

    1. WHO: One Health. September 2017. http://www.who.int/features/qa/one-health/en/.
    1. Kahn LH. Perspective: the one-health way. Nature. 2017;543(7647):S47. - PMC - PubMed
    1. Stroud, C., Dmitriev, I., Kashentseva, E., Bryan, J.N., Curiel, D.T., Rindt, H., Reinero, C., Henry, C.J., Bergman, P.J., Mason, N.J. and Gnanandarajah, J.S., 2016, August. A One Health overview, facilitating advances in comparative medicine and translational research. In Clinical and translational medicine (Vol. 5, No. 1, p. 26). Springer Berlin Heidelberg. - PMC - PubMed
    1. Semantic Deep Learning. http://semdeep.iiia.csic.es.
    1. Semantic Deep Learning. http://www.semantic-web-journal.net/blog/call-papers-special-issue-semantic-deep-learning. Accessed 25th April 2019.

Publication types

LinkOut - more resources

Feedback