A deep learning approach to identify missing is-a relations in SNOMED CT. (20th December 2022)

• Record Type: Journal Article
• Authors: Abeysinghe, Rashmie; Zheng, Fengbo; Bernstam, Elmer V; Shi, Jay; Bodenreider, Olivier; Cui, Licong
• Is Part Of: Journal of the American Medical Informatics Association. Volume 30:Number 3(2023)
• Page Start: 475
• Page End: 484
• Publication Date: 2022-12-20
• Subjects: ontology quality assurance -- SNOMED CT -- deep learning -- missing is-a relations; Medical informatics -- Periodicals; Information Services -- Periodicals; Medical Informatics -- Periodicals; Médecine -- Informatique -- Périodiques; Informatica; Geneeskunde; Informatique médicale; Computer network resources; Electronic journals; 610.285
• DOI: 10.1093/jamia/ocac248
• Languages: English
• ISSNs: 1067-5027

Abstract

Abstract: Objective: SNOMED CT is the largest clinical terminology worldwide. Quality assurance of SNOMED CT is of utmost importance to ensure that it provides accurate domain knowledge to various SNOMED CT-based applications. In this work, we introduce a deep learning-based approach to uncover missing is-a relations in SNOMED CT. Materials and Methods: Our focus is to identify missing is-a relations between concept-pairs exhibiting a containment pattern (ie, the set of words of one concept being a proper subset of that of the other concept). We use hierarchically related containment concept-pairs as positive instances and hierarchically unrelated containment concept-pairs as negative instances to train a model predicting whether an is-a relation exists between 2 concepts with containment pattern. The model is a binary classifier leveraging concept name features, hierarchical features, enriched lexical attribute features, and logical definition features. We introduce a cross-validation inspired approach to identify missing is-a relations among all hierarchically unrelated containment concept-pairs. Results: We trained and applied our model on the Clinical finding subhierarchy of SNOMED CT (September 2019 US edition). Our model (based on the validation sets) achieved a precision of 0.8164, recall of 0.8397, and F1 score of 0.8279. Applying the model to predict actual missing is-a relations, we obtained a total of 1661 potential candidates. Domain experts performed evaluation on randomly selected 230 samples and verified that 192 (83.48%) are valid. Conclusions: The results showed that our deep learning approach is effective in uncovering missing is-a relations between containment concept-pairs in SNOMED CT.