报告题目: Mining Non-lattice Subgraphs for Biomedical Ontology Quality Assurance

报告人：崔丽聪  Assistant Professor

Department of Computer Science at the University of Kentucky

报告时间：2017-6-20,16:30-18:00

报告地点：长安校区图书馆一层小会议室

  Title: Mining Non-lattice Subgraphs for Biomedical Ontology Quality Assurance

 Abstract:

Biomedical ontologies and terminologies play a vital role in healthcare information management, data integration, and decision support.  Quality issues in biomedical ontologies, if not addressed, can affect the quality of all downstream information systems relying on them as a knowledge source. Thus Ontology quality assurance (OQA) is an indispensable part of the ontology engineering cycle. However, it is labor-intensive and time-consuming to discover errors or inconsistencies by manual review of large biomedical ontologies. Effective, automated approaches for improving the quality of biomedical ontologies are needed to overcome the limitations of manual work. In this talk, I will present a non-lattice-based approach to detecting and mining potential errors in SNOMED CT, the most comprehensive clinical health care terminology worldwide. I will introduce a scalable MapReduce pipeline for exhaustively extracting non-lattice pairs from SNOMED CT, and an effective method for mining lexical patterns in non-lattice subgraphs to detect errors in SNOMED CT and suggest remediations. Since virtually all biomedical ontologies are organized into subsumption hierarchies and have concept names, our non-lattice–based approach can be generalized and applied to other biomedical ontologies for quality assurance purposes.

Short Bio:

Licong Cui is an Assistant Professor in the Department of Computer Science at the University of Kentucky (http://www.cs.uky.edu/~licong/). She received her Ph.D. in Computer Science from Case Western Reserve University. She received her MS degree in Pure Mathematics and BS degree in Information and Computing Science from Shaanxi Normal University, Xi'an, China. Dr. Cui’s research interests include knowledge representation and reasoning, knowledge discovery, ontology quality assurance, information retrieval, information extraction, text mining, data integration and management, and big data analytics. She has combined her computer science theory knowledge with software design and development skills to make key contributions to several NIH and NSF-funded research projects. Her work has led to peer-reviewed articles published by leading biomedical informatics journals and conferences such as Journal of Medical Internet Research (JMIR), Journal of American Medical Informatics Association (JAMIA), Journal of Biomedical Informatics (JBI), ACM Transactions on Knowledge Discovery from Data (TKDD), IEEE International Conference on Big Data, IEEE International Conference on Healthcare Informatics (ICHI), and American Medical Informatics Association (AMIA) Annual Symposium.