Automatic identification of critical follow-up recommendation sentences in radiology reports
- PMID: 22195225
- PMCID: PMC3243284
Automatic identification of critical follow-up recommendation sentences in radiology reports
Abstract
Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. When recommendations are not systematically identified and promptly communicated to referrers, poor patient outcomes can result. Using information technology can improve communication and improve patient safety. In this paper, we describe a text processing approach that uses natural language processing (NLP) and supervised text classification methods to automatically identify critical recommendation sentences in radiology reports. To increase the classification performance we enhanced the simple unigram token representation approach with lexical, semantic, knowledge-base, and structural features. We tested different combinations of those features with the Maximum Entropy (MaxEnt) classification algorithm. Classifiers were trained and tested with a gold standard corpus annotated by a domain expert. We applied 5-fold cross validation and our best performing classifier achieved 95.60% precision, 79.82% recall, 87.0% F-score, and 99.59% classification accuracy in identifying the critical recommendation sentences in radiology reports.
References
-
- Hussain S. Communicating Critical Results in Radiology. J Am Coll Radiol. 2010;7(2):148–51. - PubMed
-
- American College of Radiology (ACR) ACR practice guideline for communication of diagnostic imaging findings. Accessed: July 1st, 2011. Available at: http://www.acr.org/SecondaryMainMenuCategories/quality_safety/guidelines....
-
- The Royal College of Radiologists Standards for Communication of critical, urgent and unexpected significant radiological findings. Accessed: July 1st, 2011. Available at: www.rcr.ac.uk/docs/radiology/pdf/Stand_urgent_reports.pdf.
-
- Towbin AJ, Hall S, Moskovitz J, Johnson ND, Donnelly LF. Creating a comprehensive customer service program to help convey critical and acute results of radiology studies. AJR Am J Roentgenol. 2011;196(1):W48–51. - PubMed
-
- Lucey LL, Kushner DC. The ACR Guideline on Communication: To Be or Not to Be, That Is the Question. L Am Coll Radiol. 2010;7(2):109–114. - PubMed
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources