NLP development and evaluation requires tools to compare annotations, analyze differences, and compute accuracy metrics. None of the few existing tools allows consuming the output of any NLP system, comparing it with reference annotations in...
Our interactive panel at the AMIA annual symposium encountered great success and active participation by the audience. The audience experience with automatic text de-identification we limited, based on their feed-back: Presenters included...
Kim, Y., Heider, P., & Meystre, S. M. (2018). Ensemble-based Methods to Improve De-identification of Electronic Health Record Narratives. AMIA Annu Symp Proc. 663–672.
The 2018 n2c2 shared tasks focused on Cohort Selection for Clinical Trials (track 1) and on Adverse Drug Events and Medication Extraction (track 2). We participated in both tracks, with 28-45 other international teams. For track 2, we obtained...
Successful panel at the EFMI Special Topic Conference (Zagreb, Croatia) featuring: Stephane Meystre on “Automatic Trial Eligibility Surveillance to Support Patient Screening Decisions” Jihad Obeid on “Automated Detection of Altered Mental...
Garvin, J. H., Kim, Y., Gobbel, G. T., Matheny, M. E., Redd, A., Bray, B. E., et al. (2018). Automating Quality Measures for Heart Failure Using Natural Language Processing: A Descriptive Study in the Department of Veterans Affairs. JMIR...
Kim, Y., Riloff, E., & Meystre, S. M. (2017). Exploiting Unlabeled Texts with Clustering-based Instance Selection for Medical Relation Classification (pp. 1060–1069). Presented at the AMIA Annu Symp Proc, Washington, DC.
The “Unstructured Clinical Data Reuse for Precision Medicine” Workshop organized at the Medinfo 2017 conference in Hangzhou, China, was a great success. Taking place on August 24, 2017, it included presentations by Christoph...
Meystre, S. M., & Doing-Harris, K. (2017). Semi-automated Ontology Development and Management System Applied to Medically Unexplained Syndromes in the U.S. Veterans Population. Artificial Intelligence in Medicine (Vol. 10259, pp. 345–350)...
Stéphane Meystre organized a tutorial with Meliha Yetisgen, Scott DuVall, and Hua Xu at the AIME (Artificial Intelligence in Medicine) conference, in Vienna. This tutorial focused on “NLP for Clinical Information Extraction” and...
Meystre S, Gouripeddi R, Tieder J, Simmons J, Srivastava R, Shah S. Enhancing Comparative Effectiveness Research With Automated Pediatric Pneumonia Detection in a Multi-Institutional Clinical Repository: A PHIS+ Pilot Study. J Med Internet...
Meystre SM, Lovis C, Bürkle T, Tognola G, Budrionis A, Lehmann CU. Clinical Data Reuse or Secondary Use: Current Status and Potential Future Progress. Yearb Med Inform. 2017 May 8;26(1).
Kim, Y., Garvin, J. H., Goldstein, M. K., Hwang, T. S., Redd, A., Bolton, D., et al. (2017). Extraction of Left Ventricular Ejection Fraction Information from Various Types of Clinical Reports. Journal of Biomedical Informatics...
Stephane Meystre moved from the University of Utah to the Medical University of South Carolina (MUSC) and Health Sciences South Carolina in August 2016. He was awarded a SmartState Endowed Chair in Translational Biomedical Informatics...
In the context of the POET project led by John Hurdle, we are developing and evaluating methods to detect abbreviations and acronyms in clinical text, disambiguate them, and replace them with their long form. Publications: Kim, Y., Hurdle, J....
The structure of clinical documents, and more specifically their sections, have a strong importance when assessing the context of clinical information extracted from clinical documents. For example, a diagnosis of asthma extracted from a...
In the context of a Teaching Enhancement Initiative co-led by Catherine Staes and Stephane Meystre, a “sandbox” with informatics tools and resources for students and faculty to safely play with has been developed at the University...
Our work with the i2b2 hive started with a collaboration with the Informatics for Integrating Biology and the Bedside (i2b2) NIH-funded National Center for Biomedical Computing based at Partners Healthcare (Boston, MA) to evaluate the...
Meystre S, Shen S, Hofmann D, Gundlapali A (2014). Can Physicians Recognize Their Own Patients in De-identified Notes? Stud Health Technol Inform, 205, 778-82.