Extracting Disease-Symptom Relationships by Learning Syntactic Patterns from Dependency Graphs

Mohsen Hassan (1) , Olfa Makkaoui (1) , Adrien Coulet (1) , Yannick Toussaint (1)

1 ORPAILLEUR - Knowledge representation, reasonning

Disease-symptom relationships are of primary importance for biomedical informat-ics, but databases that catalog them are incomplete in comparison with the state of the art available in the scientific literature. We propose in this paper a novel method for automatically extracting disease-symptom relationships from text, called SPARE (standing for Syntactic PAttern for Relationship Extraction). This method is composed of 3 successive steps: first, we learn patterns from the dependency graphs; second, we select best patterns based on their respective quality and specificity (their ability to identify only disease-symptom relationships); finally, the patterns are used on new texts for extracting disease-symptom relationships. We experimented SPARE on a corpus of 121,796 abstracts of PubMed related to 457 rare diseases. The quality of the extraction has been evaluated depending on the pattern quality and specificity. The best F-measure obtained is 55.65% (for speci f icity ≥ 0.5 and quality ≥ 0.5). To provide an insight on the novelty of disease-symptom relationship extracted, we compare our results to the content of phenotype databases (OrphaData and OMIM). Our results show the feasibility of automatically extracting disease-symptom relationships, including true relationships that were not already referenced in phenotype databases and may involve complex symptom descriptions.

Mots clés: Text mining; phenotype; symptom; disease; dependency graph; syntactic pattern

Domaines: Traitement du texte et du document; Bio-informatique [q-bio.QM]; Base de données [cs.DB]

Mohsen Hassan, Olfa Makkaoui, Adrien Coulet, Yannick Toussaint. Extracting Disease-Symptom Relationships by Learning Syntactic Patterns from Dependency Graphs. BioNLP 15, Association for Computational Linguistics, Jul 2015, Beijing, China. pp.184. ⟨hal-01184655⟩