Data reduction for continuum of care: an exploratory study using the predicate-argument structure to pre-process radiology sentences for measurement of semantic similarity

Authors:
Eric Newsom;Josette F. Jones
Affiliations:
Indiana University Health, Indianapolis, IN;Indiana University-Purdue University Indianapolis, Indianapolis, IN
Venue:
UAHCI'13 Proceedings of the 7th international conference on Universal Access in Human-Computer Interaction: applications and services for quality of life - Volume Part III
Year:
2013

Citing 11
Cited 0

Towards the development of a conceptual distance metric for the UMLS

Journal of Biomedical Informatics
Using predicate-argument structures for information extraction

ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Semantic retrieval for the accurate identification of relational concepts in massive textbases

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Mining a lexicon of technical terms and lay equivalents

BioNLP '07 Proceedings of the Workshop on BioNLP 2007: Biological, Translational, and Clinical Language Processing
Corpus-based and knowledge-based measures of text semantic similarity

AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Methodological Review: What can natural language processing do for clinical decision support?

Journal of Biomedical Informatics
A semi-automatic method for annotating a biomedical proposition bank

LAC '06 Proceedings of the Workshop on Frontiers in Linguistically Annotated Corpora 2006
Arguments of nominals in semantic interpretation of biomedical text

BioNLP '10 Proceedings of the 2010 Workshop on Biomedical Natural Language Processing
Knowledge Discovery and Data Mining of Free Text Radiology Reports

HISB '11 Proceedings of the 2011 IEEE First International Conference on Healthcare Informatics, Imaging and Systems Biology
Ontology-Driven construction of domain corpus with frame semantics annotations

CICLing'12 Proceedings of the 13th international conference on Computational Linguistics and Intelligent Text Processing - Volume Part I
Evolutionary algorithm based on different semantic similarity functions for synonym recognition in the biomedical domain

Knowledge-Based Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

In the clinical setting, continuum of care depends on integrated information services to assure a smooth progression for patient centered care, and these integrated information services must understand past events and personal circumstances to make care relevant. Clinicians face a problem that the amount of information produced in disparate electronic clinical notes is increasing to levels incapable of being processed by humans. Clinicians need a function in information services that can reduce the free text data to a message useful at time of care. Information extraction (IE) is a sub-field of natural language processing with the goal of data reduction of unstructured free text. Pertinent to IE is an annotated corpus that frames how IE methods should create a logical expression necessary for processing meaning of text. This study explores and reports on the requirements to using the predicate-argument statement (PAS) as the framework. A convenient sample from a prior study with ten synsets of 100 unique sentences from radiology reports deemed by domain experts to mean the same thing will be the text from which PAS structures are formed. Through content analysis of pattern recognition, findings show PAS is a feasible framework to structure sentences for semantic similarity measurement.