Skip to main content

Olivier Bodenreider, MD, PhD


Research Interests

For the past 20 years, the goal of the Medical Ontology Research project has been to develop methods whereby ontologies could be acquired from existing resources, as well as validated against other knowledge sources. Our research is organized into two major areas.
  • Health information standards as an object of research – The goal of this research is to assess whether specific standards (e.g., the SNOMED CT terminology) are fit for purpose. Specific aspects of this research include quality assurance and interoperability assessment of biomedical terminologies.
  • Application of health information standards – Here, the goal is to investigate standards “in action”, e.g., in support of tasks, such as natural language processing, annotation, data integration and mapping across terminologies.


Abeysinghe R, Zheng F, Bernstam EV, Shi J, Bodenreider O, Cui L. A deep learning approach to identify missing is-a relations in SNOMED CT. J Am Med Inform Assoc. 2023 Feb 16;30(3):475-484. doi: 10.1093/jamia/ocac248. PubMed PMID: 36539234; PubMed Central PMCID: PMC9933066.

Nguyen V, Bodenreider O. Adding an Attention Layer Improves the Performance of a Neural Network Architecture for Synonymy Prediction in the UMLS Metathesaurus. Stud Health Technol Inform. 2022 Jun 6;290:116-119. doi: 10.3233/SHTI220043. PubMed PMID: 35672982; PubMed Central PMCID: PMC9484765.

Xu J, Fung KW, Bodenreider O. Sequential Mapping - A Novel Approach to Map from ICD-10-CM to ICD-11. Stud Health Technol Inform. 2022 Jun 6;290:96-100. doi: 10.3233/SHTI220039. PubMed PMID: 35672978; PubMed Central PMCID: PMC9491349.

Bajaj G, Nguyen V, Wijesiriwardene T, Yip HY, Javangula V, Parthasarathy S, Sheth A, Bodenreider O. Evaluating Biomedical Word Embeddings for Vocabulary Alignment at Scale in the UMLS Metathesaurus Using Siamese Networks. Proc Conf Assoc Comput Linguist Meet. 2022 May;2022:82-87. doi: 10.18653/v1/2022.insights-1.11. PubMed PMID: 36093038; PubMed Central PMCID: PMC9455661.