A Lexical-based Formal Concept Analysis Method to Identify Missing Concepts in the NCI Thesaurus

Logical definition-based identification of potential missing concepts in SNOMED CT

BACKGROUND

Biomedical ontologies are representations of biomedical knowledge that provide terms with precisely defined meanings. They play a vital role in facilitating biomedical research in a cross-disciplinary manner. Quality issues of biomedical ontologies will hinder their effective usage. One such quality issue is missing concepts. In this study, we introduce a logical definition-based approach to identify potential missing concepts in SNOMED CT. A unique contribution of our approach is that it is capable of obtaining both logical definitions and fully specified names for potential missing concepts.

METHOD

The logical definitions of unrelated pairs of fully defined concepts in non-lattice subgraphs that indicate quality issues are intersected to generate the logical definitions of potential missing concepts. A text summarization model (called PEGASUS) is fine-tuned to predict the fully specified names of the potential missing concepts from their generated logical definitions. Furthermore, the identified potential missing concepts are validated using external resources including the Unified Medical Language System (UMLS), biomedical literature in PubMed, and a newer version of SNOMED CT.

RESULTS

From the March 2021 US Edition of SNOMED CT, we obtained a total of 30,313 unique logical definitions for potential missing concepts through the intersecting process. We fine-tuned a PEGASUS summarization model with 289,169 training instances and tested it on 36,146 instances. The model achieved 72.83 of ROUGE-1, 51.06 of ROUGE-2, and 71.76 of ROUGE-L on the test dataset. The model correctly predicted 11,549 out of 36,146 fully specified names in the test dataset. Applying the fine-tuned model on the 30,313 unique logical definitions, 23,031 total potential missing concepts were identified. Out of these, a total of 2,312 (10.04%) were automatically validated by either of the three resources.

CONCLUSIONS

The results showed that our logical definition-based approach for identification of potential missing concepts in SNOMED CT is encouraging. Nevertheless, there is still room for improving the performance of naming concepts based on logical definitions.

A substring replacement approach for identifying missing IS-A relations in SNOMED CT

Biomedical ontologies provide formalized information and knowledge in the biomedical domain. Over the years, biomedical ontologies have played an important role in facilitating biomedical research and applications. Common quality issues of biomedical ontologies include inconsistent naming of concepts, redundant concepts, redundant relations, incomplete/incorrect concept definitions, and incomplete/incorrect class hierarchies. In this work, we focus on addressing the incompleteness of the class hierarchy in SNOMED CT. We develop a substring replacement approach, leveraging concepts' lexical features and existing IS-A relations to identify potential missing IS-A relations in SNOMED CT. To evaluate the effectiveness of our approach, we performed both automated and manual validation. For the automated evaluation, we leverage relations from external terminologies in the Unified Medical Language System (UMLS) to validate the identified missing IS-A relations. For the manual validation, a randomly selected 100 samples from the results are reviewed by a domain expert. Applying our approach to the March 2022 release of SNOMED CT US Edition, we identified 3,228 potential missing IS-A relations, among which 63 were validated through the UMLS. The evaluation by the domain expert revealed that 89 out of 100 (a precision of 89%) missing IS-A relations are valid cases, showing the effectiveness of this substring replacement approach to facilitate the quality assurance of IS-A relations in SNOMED CT.

Leveraging non-lattice subgraphs for suggestion of new concepts for SNOMED CT

Missing hierarchical is-a relations and missing concepts are common quality issues in biomedical ontologies. Non-lattice subgraphs have been extensively studied for automatically identifying missing is-a relations in biomedical ontologies like SNOMED CT. However, little is known about non-lattice subgraphs' capability to uncover new or missing concepts in biomedical ontologies. In this work, we investigate a lexical-based intersection approach based on non-lattice subgraphs to identify potential missing concepts in SNOMED CT. We first construct lexical features of concepts using their fully specified names. Then we generate hierarchically unrelated concept pairs in non-lattice subgraphs as the candidates to derive new concepts. For each candidate pair of concepts, we conduct an order-preserving intersection based on the two concepts' lexical features, with the intersection result serving as the potential new concept name suggested. We further perform automatic validation through terminologies in the Unified Medical Language System (UMLS) and literature in PubMed. Applying this approach to the March 2021 release of SNOMED CT US Edition, we obtained 7,702 potential missing concepts, among which 1,288 were validated through UMLS and 1,309 were validated through PubMed. The results showed that non-lattice subgraphs have the potential to facilitate suggestion of new concepts for SNOMED CT.

Identification of missing concepts in biomedical terminologies using sequence-based formal concept analysis

Background

As biomedical knowledge is rapidly evolving, concept enrichment of biomedical terminologies is an active research area involving automatic identification of missing or new concepts. Previously, we prototyped a lexical-based formal concept analysis (FCA) approach in which concepts were derived by intersecting bags of words, to identify potentially missing concepts in the National Cancer Institute (NCI) Thesaurus. However, this prototype did not handle concept naming and positioning. In this paper, we introduce a sequenced-based FCA approach to identify potentially missing concepts, supporting concept naming and positioning.

Methods

We consider the concept name sequences as FCA attributes to construct the formal context. The concept-forming process is performed by computing the longest common substrings of concept name sequences. After new concepts are formalized, we further predict their potential positions in the original hierarchy by identifying their supertypes and subtypes from original concepts. Automated validation via external terminologies in the Unified Medical Language System (UMLS) and biomedical literature in PubMed is performed to evaluate the effectiveness of our approach.

Results

We applied our sequenced-based FCA approach to all the sub-hierarchies under Disease or Disorder in the NCI Thesaurus (19.08d version) and five sub-hierarchies under Clinical Finding and Procedure in the SNOMED CT (US Edition, March 2020 release). In total, 1397 potentially missing concepts were identified in the NCI Thesaurus and 7223 in the SNOMED CT. For NCI Thesaurus, 85 potentially missing concepts were found in external terminologies and 315 of the remaining 1312 appeared in biomedical literature. For SNOMED CT, 576 were found in external terminologies and 1159 out of the remaining 6647 were found in biomedical literature.

Conclusion

Our sequence-based FCA approach has shown the promise for identifying potentially missing concepts in biomedical terminologies.