Extracting and normalizing temporal expressions in clinical data requests from researchers

Authors:
Tianyong Hao;Alex Rusanov;Chunhua Weng
Affiliations:
Department of Biomedical Informatics, Columbia University;Department of Anesthesiology, Columbia University;Department of Biomedical Informatics, Columbia University
Venue:
ICSH'13 Proceedings of the 2013 international conference on Smart Health
Year:
2013

Citing 7
Cited 1

NLTK: the natural language toolkit

COLING-ACL '06 Proceedings of the COLING/ACL on Interactive presentation sessions
Assessing clinical trial eligibility with logic expression queries

Data & Knowledge Engineering
SemEval-2010 task 13: evaluating events, time expressions, and temporal relations (TempEval-2)

DEW '09 Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions
SemEval-2010 task 13: TempEval-2

SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
HeidelTime: High quality rule-based extraction and normalization of temporal expressions

SemEval '10 Proceedings of the 5th International Workshop on Semantic Evaluation
A corpus of clinical narratives annotated with temporal information

Proceedings of the 2nd ACM SIGHIT International Health Informatics Symposium
A robust shallow temporal reasoning system

NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Demonstration Session

Defining and measuring completeness of electronic health records for secondary use

Journal of Biomedical Informatics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Automatic translation of clinical researcher data requests to executable database queries is instrumental to an effective interface between clinical researchers and "Big Clinical Data". A necessary step towards this goal is to parse ample temporal expressions in free-text researcher requests. This paper reports a novel algorithm called TEXer. It uses heuristic rule and pattern learning for extracting and normalizing temporal expressions in researcher requests. Based on 400 real clinical queries with human annotations, we compared our method with four baseline methods. TEXer achieved a precision of 0.945 and a recall of 0.858, outperforming all the baseline methods. We conclude that TEXer is an effective method for temporal expression extraction from free-text clinical data requests.