Sungrim (Riea) Moon, Ph.D.
Data and Technology Advancement National Service Scholar (DATA Scholar)
Informatics
Division of Preclinical Innovation
Contact Info
Biography
Sungrim (Riea) Moon, Ph.D., is a Data and Technology Advancement National Service Scholar (DATA Scholar) in NIH’s Office of Data Science Strategy and is part of the Informatics Core within NCATS’ Division of Preclinical Innovation. She has a decade of experience using natural language processing (NLP), machine learning (ML), deep learning and data mining for health care and biomedical data.
Before joining NCATS, Moon was an assistant professor of biomedical informatics and a senior translational informatics analyst at Mayo Clinic. Moon has shown her dedication and biomedical research contributions through more than 50 peer-reviewed publications and many conference presentations.
Moon earned her doctorate in health informatics from the University of Minnesota Twin Cities in 2012. She researched automated disambiguation of acronyms and abbreviations in clinical texts. She also worked to develop sense inventories for those terms. As a postdoctoral research fellow at The University of Texas Health Science Center at Houston, Moon worked on NLP projects with The University of Texas MD Anderson Cancer Center and the Department of Veterans Affairs. At Mayo Clinic, her research included problem contextualization; data processing and analysis; and model design, development, evaluation and visualization. She worked with clinical investigators and information technology teams using electronic health records.
Research Topics
Moon’s primary research centers on developing biomedical informatics applications for translational research in rare diseases. She works to harmonize diverse biomedical and clinical data types, mainly through information retrieval and extraction from free texts using NLP and ML techniques tailored for rare diseases.
Selected Publications
-
Extractive Clinical Question-Answering With Multianswer and Multifocus Questions: Data Set Development and Evaluation Study
-
Bridging the Granularity Gap in Family History Information Extracted from Clinical Narratives
-
Identifying Information Gaps in Electronic Health Records by Using Natural Language Processing: Gynecologic Surgery History Identification
-
Automated Disambiguation of Acronyms and Abbreviations in Clinical Texts: Window and Training Size Considerations
-
A Sense Inventory for Clinical Abbreviations and Acronyms Created Using Clinical Notes and Medical Dictionary Resources