Satya Sahoo, Joseph Plasek, Hua Xu, Ozlem Uzuner, Trevor Cohen, Meliha Yetisgen, Hongfang Liu, Stéphane Meystre , Yanshan Wang J Am Med Inform Assoc, published online Apr 24, 2024, https://doi.org/10.1093/jamia/ocae074 Available at...
Prof. Meystre presented a keynote on “Opening the Treasure Trove Chest: AI to Enable Clinical Data Reuse for Research and Care Support” at the Clinical AI: from research and development to the bedside track during the AMLD’24...
Stéphane M Meystre, Paul M Heider, Youngjun Kim, Matthew Davis, Jihad Obeid, James Madory, Alexander V Alekseyenko J Am Med Inform Assoc. Volume 29, Issue 1, January 2022, Pages...
Youngjun Kim, Paul M Heider, Isabel Rh Lally, and Stéphane M Meystre JMIR Med Inform. 2021 Apr 22;9(4):e22797. Available at: https://pubmed.ncbi.nlm.nih.gov/33885370/ and at: https://medinform.jmir.org/2021/4/e22797/
PCORI awarded our MUSC team partnering with Vanderbilt University funding to develop, test and share a new software application for COVID-19 related information extraction based on the same new Natural Language Processing (NLP) methods to...
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...
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...
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...
This project focuses on providing VA clinical research with methods and instruments for syndrome surveillance, on improving detection and mitigation of health problems in deployed veterans, and more specifically on the detection of medically...
Textractor is based on the Apache Unstructured Information Management Architecture (UMIA) framework, and uses methods that are a hybrid between machine learning and pattern matching. Our earlier versions of information extraction applications...
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...