Research Topics
| Ozlem UzunerSummaryAffiliation: University at Albany Country: USA Publications
|
Detail Information
Publications
Evaluating the state-of-the-art in automatic de-identificationOzlem Uzuner
University at Albany, SUNY, Draper 114A, 135 Western Ave, Albany, NY 12222, USA
J Am Med Inform Assoc 14:550-63. 2007..However, identifying ambiguous PHI proved challenging. The performance of systems on the test data set is encouraging. Future evaluations of these systems will involve larger data sets from more heterogeneous sources...- Evaluating the state of the art in coreference resolution for electronic medical recordsOzlem Uzuner
Department of Information Studies, University at Albany, SUNY, Albany, New York 12222, USA
J Am Med Inform Assoc 19:786-91. 2012..These corpora contained various record types (ie, discharge summaries, pathology reports) from multiple institutions... - 2010 i2b2/VA challenge on concepts, assertions, and relations in clinical textOzlem Uzuner
Department of Information Studies, University at Albany, State University of New York, Albany, New York 12222, USA
J Am Med Inform Assoc 18:552-6. 2011..Ensembles of classifiers, information from unlabeled data, and external knowledge sources can help when the training data are inadequate... - Community annotation experiment for ground truth generation for the i2b2 medication challengeOzlem Uzuner
Department of Information Studies, University at Albany, State University of New York, Albany, NY, USA
J Am Med Inform Assoc 17:519-23. 2010.... - Extracting medication information from clinical textOzlem Uzuner
Department of Information Studies, University at Albany, State University of New York, Albany, NY, USA
J Am Med Inform Assoc 17:514-8. 2010..However, they are limited in recognizing duration and reason fields and would benefit from future research... - Semantic relations for problem-oriented medical recordsOzlem Uzuner
University at Albany, State University of New York, 135 Western Ave, Draper 114A, Albany, NY 12222, USA
Artif Intell Med 50:63-73. 2010..We describe semantic relation (SR) classification on medical discharge summaries. We focus on relations targeted to the creation of problem-oriented records. Thus, we define relations that involve the medical problems of patients... - Recognizing obesity and comorbidities in sparse dataOzlem Uzuner
University at Albany, SUNY, Albany, NY, USA
J Am Med Inform Assoc 16:561-70. 2009..Information on disease-related concepts, such as symptoms and medications, and general medical knowledge help systems infer intuitive judgments on the diseases... - Machine learning and rule-based approaches to assertion classificationOzlem Uzuner
Information Studies, State Unviersity of New York, Albany, NY, USA
J Am Med Inform Assoc 16:109-15. 2009.... - A de-identifier for medical discharge summariesOzlem Uzuner
University at Albany, State University of New York, Draper 114, Albany, NY 12222, USA
Artif Intell Med 42:13-35. 2008.... - Identifying patient smoking status from medical discharge recordsOzlem Uzuner
University at Albany, SUNY, Draper 114A, 135 Western Avenue, Albany, NY 12222, USA
J Am Med Inform Assoc 15:14-24. 2008..g., "smok", "tobac", "cigar", Social History, etc.). Many of the effective smoking status identifiers benefit from these features... - Specializing for predicting obesity and its co-morbiditiesIra Goldstein
College of Computing and Information, State University of New York, University at Albany, Draper 114B, 1400 Washington Avenue, Albany, NY 12222, USA
J Biomed Inform 42:873-86. 2009..We evaluate specializing on each of the 16 diseases and show that it improves significantly over voting and stacking when used for multi-class classification on our data...