Özlem Uzuner, Ph.D.

Özlem Uzuner, PhD

Visiting Associate Professor of Biomedical Informatics, Harvard Medical School

Ozlem Uzuner is an Associate Professor of Information Sciences and Technology at George Mason University. She is the lead investigator of the National NLP Clinical Challenges (n2c2) which she has been organizing since 2006, first under Informatics for Integrating Biology and the Bedside (i2b2), then under CEGS N-GRID, and now under the Department of Biomedical Informatics (DBMI) of Harvard Medical School jointly with George Mason University. She is a natural language processing (NLP) expert and specializes in methods that process clinical narratives for effective and efficient information access that can support clinical applications. As a part of her NLP efforts, she de-identifies clinical records; as a part of the outreach and education efforts of DBMI and George Mason, enables use of de-identified narrative clinical data for research and course work.

Segment convolutional neural networks (Seg-CNNs) for classifying relations in clinical notes.
Authors: Luo Y, Cheng Y, Uzuner Ö, Szolovits P, Starren J.
J Am Med Inform Assoc
View full abstract on Pubmed
De-identification of psychiatric intake records: Overview of 2016 CEGS N-GRID shared tasks Track 1.
Authors: Stubbs A, Filannino M, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed
Symptom severity prediction from neuropsychiatric clinical records: Overview of 2016 CEGS N-GRID shared tasks Track 2.
Authors: Filannino M, Stubbs A, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed
A natural language processing challenge for clinical records: Research Domains Criteria (RDoC) for psychiatry.
Authors: Uzuner Ö, Stubbs A, Filannino M.
J Biomed Inform
View full abstract on Pubmed
Prescription extraction using CRFs and word embeddings.
Authors: Tao C, Filannino M, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed
Automatic prediction of coronary artery disease from clinical narratives.
Authors: Buchan K, Filannino M, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed
Bridging semantics and syntax with graph algorithms-state-of-the-art of extracting biomedical relations.
Authors: Luo Y, Uzuner Ö, Szolovits P.
Brief Bioinform
View full abstract on Pubmed
Bridging semantics and syntax with graph algorithms-state-of-the-art of extracting biomedical relations.
Authors: Luo Y, Uzuner Ö, Szolovits P.
Brief Bioinform
View full abstract on Pubmed
A systematic comparison of feature space effects on disease classifier performance for phenotype identification of five diseases.
Authors: Kotfila C, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed
Automated systems for the de-identification of longitudinal clinical narratives: Overview of 2014 i2b2/UTHealth shared task Track 1.
Authors: Stubbs A, Kotfila C, Uzuner Ö.
J Biomed Inform
View full abstract on Pubmed