Limits...
Knowledge retrieval from PubMed abstracts and electronic medical records with the Multiple Sclerosis Ontology.

Malhotra A, Gündel M, Rajput AM, Mevissen HT, Saiz A, Pastor X, Lozano-Rubi R, Martinez-Lapiscina EH, Martinez-Lapsicina EH, Zubizarreta I, Mueller B, Kotelnikova E, Toldo L, Hofmann-Apitius M, Villoslada P - PLoS ONE (2015)

Bottom Line: The MS Ontology retrieved 80% of the genes associated with MS from scientific abstracts and identified additional pathways targeted by approved disease-modifying drugs (e.g. apoptosis pathways associated with mitoxantrone, rituximab and fingolimod).The analysis of the EMR from patients with MS identified current usage of disease modifying drugs and symptomatic therapy as well as comorbidities, which are in agreement with recent reports.The MS Ontology provides a semantic framework that is able to automatically extract information from both scientific literature and EMR from patients with MS, revealing new pathogenesis insights as well as new clinical information.

View Article: PubMed Central - PubMed

Affiliation: Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing, 53754, Sankt Augustin, Germany.

ABSTRACT

Background: In order to retrieve useful information from scientific literature and electronic medical records (EMR) we developed an ontology specific for Multiple Sclerosis (MS).

Methods: The MS Ontology was created using scientific literature and expert review under the Protégé OWL environment. We developed a dictionary with semantic synonyms and translations to different languages for mining EMR. The MS Ontology was integrated with other ontologies and dictionaries (diseases/comorbidities, gene/protein, pathways, drug) into the text-mining tool SCAIView. We analyzed the EMRs from 624 patients with MS using the MS ontology dictionary in order to identify drug usage and comorbidities in MS. Testing competency questions and functional evaluation using F statistics further validated the usefulness of MS ontology.

Results: Validation of the lexicalized ontology by means of named entity recognition-based methods showed an adequate performance (F score = 0.73). The MS Ontology retrieved 80% of the genes associated with MS from scientific abstracts and identified additional pathways targeted by approved disease-modifying drugs (e.g. apoptosis pathways associated with mitoxantrone, rituximab and fingolimod). The analysis of the EMR from patients with MS identified current usage of disease modifying drugs and symptomatic therapy as well as comorbidities, which are in agreement with recent reports.

Conclusion: The MS Ontology provides a semantic framework that is able to automatically extract information from both scientific literature and EMR from patients with MS, revealing new pathogenesis insights as well as new clinical information.

Show MeSH

Related in: MedlinePlus

Concepts identified using the MS Ontology in the competency questions.Figure shows the concepts (in grey boxes) retrieved in the competency questions (search strategy) annotated by the MS Ontology and linked to other MS Ontology concepts, indicating the PMID of the abstract from PubMed and the type of interaction described in such abstract. A) references linking brain atrophy and CNS repair with remyelination in MS; B) references linking Myelin Oligodendrocyte Glycoprotein (MOG) to antibody-mediated demyelination; and C) references linking fingolimod tested as a drug for treatment of relapsing-remitting MS in phase 3 clinical trials
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4321837&req=5

pone.0116718.g002: Concepts identified using the MS Ontology in the competency questions.Figure shows the concepts (in grey boxes) retrieved in the competency questions (search strategy) annotated by the MS Ontology and linked to other MS Ontology concepts, indicating the PMID of the abstract from PubMed and the type of interaction described in such abstract. A) references linking brain atrophy and CNS repair with remyelination in MS; B) references linking Myelin Oligodendrocyte Glycoprotein (MOG) to antibody-mediated demyelination; and C) references linking fingolimod tested as a drug for treatment of relapsing-remitting MS in phase 3 clinical trials

Mentions: To evaluate the queries, we compared documents returned by the MS Ontology with documents returned by “advance search” in PubMed (we used manual search in PubMed using keywords and revised by an expert as a gold standard). We found that the MS Ontology obtained a lower ratio of false positive and false negative results than manual searching (Table 1). Nevertheless, the information retrieved from PubMed with the MS Ontology provided a structure on the basis of the relationship between terms, allowing the hierarchy and logic of the evidence found in scientific abstracts to be followed (Fig. 2). These results indicate that MS Ontology-based information retrieval improved the chances of gaining more accurate (decreasing false positive and negative results) and structured information compared to PubMed advance searches.


Knowledge retrieval from PubMed abstracts and electronic medical records with the Multiple Sclerosis Ontology.

Malhotra A, Gündel M, Rajput AM, Mevissen HT, Saiz A, Pastor X, Lozano-Rubi R, Martinez-Lapiscina EH, Martinez-Lapsicina EH, Zubizarreta I, Mueller B, Kotelnikova E, Toldo L, Hofmann-Apitius M, Villoslada P - PLoS ONE (2015)

Concepts identified using the MS Ontology in the competency questions.Figure shows the concepts (in grey boxes) retrieved in the competency questions (search strategy) annotated by the MS Ontology and linked to other MS Ontology concepts, indicating the PMID of the abstract from PubMed and the type of interaction described in such abstract. A) references linking brain atrophy and CNS repair with remyelination in MS; B) references linking Myelin Oligodendrocyte Glycoprotein (MOG) to antibody-mediated demyelination; and C) references linking fingolimod tested as a drug for treatment of relapsing-remitting MS in phase 3 clinical trials
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4321837&req=5

pone.0116718.g002: Concepts identified using the MS Ontology in the competency questions.Figure shows the concepts (in grey boxes) retrieved in the competency questions (search strategy) annotated by the MS Ontology and linked to other MS Ontology concepts, indicating the PMID of the abstract from PubMed and the type of interaction described in such abstract. A) references linking brain atrophy and CNS repair with remyelination in MS; B) references linking Myelin Oligodendrocyte Glycoprotein (MOG) to antibody-mediated demyelination; and C) references linking fingolimod tested as a drug for treatment of relapsing-remitting MS in phase 3 clinical trials
Mentions: To evaluate the queries, we compared documents returned by the MS Ontology with documents returned by “advance search” in PubMed (we used manual search in PubMed using keywords and revised by an expert as a gold standard). We found that the MS Ontology obtained a lower ratio of false positive and false negative results than manual searching (Table 1). Nevertheless, the information retrieved from PubMed with the MS Ontology provided a structure on the basis of the relationship between terms, allowing the hierarchy and logic of the evidence found in scientific abstracts to be followed (Fig. 2). These results indicate that MS Ontology-based information retrieval improved the chances of gaining more accurate (decreasing false positive and negative results) and structured information compared to PubMed advance searches.

Bottom Line: The MS Ontology retrieved 80% of the genes associated with MS from scientific abstracts and identified additional pathways targeted by approved disease-modifying drugs (e.g. apoptosis pathways associated with mitoxantrone, rituximab and fingolimod).The analysis of the EMR from patients with MS identified current usage of disease modifying drugs and symptomatic therapy as well as comorbidities, which are in agreement with recent reports.The MS Ontology provides a semantic framework that is able to automatically extract information from both scientific literature and EMR from patients with MS, revealing new pathogenesis insights as well as new clinical information.

View Article: PubMed Central - PubMed

Affiliation: Department of Bioinformatics, Fraunhofer Institute for Algorithms and Scientific Computing, 53754, Sankt Augustin, Germany.

ABSTRACT

Background: In order to retrieve useful information from scientific literature and electronic medical records (EMR) we developed an ontology specific for Multiple Sclerosis (MS).

Methods: The MS Ontology was created using scientific literature and expert review under the Protégé OWL environment. We developed a dictionary with semantic synonyms and translations to different languages for mining EMR. The MS Ontology was integrated with other ontologies and dictionaries (diseases/comorbidities, gene/protein, pathways, drug) into the text-mining tool SCAIView. We analyzed the EMRs from 624 patients with MS using the MS ontology dictionary in order to identify drug usage and comorbidities in MS. Testing competency questions and functional evaluation using F statistics further validated the usefulness of MS ontology.

Results: Validation of the lexicalized ontology by means of named entity recognition-based methods showed an adequate performance (F score = 0.73). The MS Ontology retrieved 80% of the genes associated with MS from scientific abstracts and identified additional pathways targeted by approved disease-modifying drugs (e.g. apoptosis pathways associated with mitoxantrone, rituximab and fingolimod). The analysis of the EMR from patients with MS identified current usage of disease modifying drugs and symptomatic therapy as well as comorbidities, which are in agreement with recent reports.

Conclusion: The MS Ontology provides a semantic framework that is able to automatically extract information from both scientific literature and EMR from patients with MS, revealing new pathogenesis insights as well as new clinical information.

Show MeSH
Related in: MedlinePlus