- Home
- ACMI Fellows
- Dina Demner-Fushman, MD, PhD, FACMI
Dina Demner-Fushman, MD, PhD, FACMI
Year Elected: 2011
Institution When Elected: National Library of Medicine
Currently: National Library of Medicine
Dr. Demner-Fushman received a doctoral degree in Medicine and Dentistry and PhD degree in Immunology from universities in the Soviet Union, and practiced as an orthodontist in Kazan in the USSR and in Frankfurt, Germany. She emigrated to the US and continued her education, receiving a bachelors degree in computer science from Hunter College in New York, and Masters and PhD degrees in computer science from the University of Maryland. She undertook a postdoctoral fellowship in medical informatics at the Lister Hill Center, and in 2007 became a staff scientist at the National Library of Medicine.
At NLM Dr. Demner-Fushman has been a major contributor in the application of natural language processing and information management for enhancing clinical infrastructure and health care delivery. She developed an innovative method combining UMLS ontological knowledge with clinical knowledge from the literature. This approach, which was originally devised for clinical question answering, is being applied to automatic extraction of information needs from NIH Clinical Center records. She has been recognized as a leading biomedical NLP researcher as evidenced by her role since 2007 in organizing the BioNLP workshops of the Association for Computational Linguistics, which have attracted a growing number of mainstream computational linguists and computer scientists.
At the time of her election, Dr. Demner-Fushman had contributed as an author to 87 peer reviewed publications, and creation of a number of novel applications, including InfoBot, a Repository for Informed Decision Making (or RIDeM), methods for automatic annotational and retrieval of images extracted from publications known as iMEDLINE, and HLDISCOVERY, which is a de-identified database system for clinically derived data. She has also been instrumental in adapting related information extraction techniques for NLM’s successful participation in several biomedical natural language processing competitions. Her election to fellowship recognizes these technical and organizational contributions.

