Detecting concept relations in clinical text: Insights from a state-of-the-art model

Autor: Berry de Bruijn, Xiaodan Zhu, Svetlana Kiritchenko, Colin Cherry, Joel Martin
Rok vydání: 2013
Předmět:
Text mining
Databases
Factual
Computer science
Electronic health record
Health Informatics
02 engineering and technology
data extraction
computer.software_genre
State of the art
03 medical and health sciences
0302 clinical medicine
Artificial Intelligence
Factor (programming language)
0202 electrical engineering
electronic engineering
information engineering
Knowledge sources
Real-world scenario
Data Mining
Electronic Health Records
Humans
030212 general & internal medicine
Medical problems
computer.programming_language
Natural Language Processing
accuracy
business.industry
Medical concepts
Natural language processing systems
Variety (cybernetics)
Feature design
Semantics
Computer Science Applications
kernel method
020201 artificial intelligence & image processing
Artificial intelligence
State (computer science)
Semantic relations
business
Construct (philosophy)
computer
Natural language processing
Algorithms
Zdroj: Journal of Biomedical Informatics. 46(2):275-285
ISSN: 1532-0464
DOI: 10.1016/j.jbi.2012.11.006
Popis: This paper addresses an information-extraction problem that aims to identify semantic relations among medical concepts (problems, tests, and treatments) in clinical text. The objectives of the paper are twofold. First, we extend an earlier one-page description (appearing as a part of [5]) of a top-ranked model in the 2010 I2B2 NLP Challenge to a necessary level of details, with the belief that feature design is the most crucial factor to the success of our system and hence deserves a more detailed discussion. We present a precise quantification of the contributions of a wide variety of knowledge sources. In addition, we show the end-to-end results obtained on the noisy output of a top-ranked concept detector, which could help construct a more complete view of the state of the art in the real-world scenario. As the second major objective, we reformulate our models into a composite-kernel framework and present the best result, according to our knowledge, on the same dataset.
Databáze: OpenAIRE
Externí odkaz: