Abstract
We applied text mining to a database of discharge letters of patients with acute myocardial infarction for a quality of care-related task: the automatic validation of acute myocardial infarction diagnoses. The system should evaluate if the information contained in the discharge letters was consistent, by medical standards, with the letters’ coded diagnoses of acute myocardial infarction. The system was composed of a text mining tool (GATE) and a set of linguistic resources which were specifically developed from a training set of letters. It was validated on a test set of letters manually annotated by cardiologists and results were satisfactory. Further analyses can be made on the efficiency of the development of the system and on its ongoing effectiveness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
The project was financed by Regione Lombardia. The TM section was realized by Azienda Ospedaliera di Melegnano, Politecnico di Milano, and CEFRIEL (CEFRIEL is a not-for-profit organization. Its shareholders are universities, public authorities, and 15 leading multinational companies in ICT and media sectors. CEFRIEL’s primary objective is to strengthen existing ties between academic and business worlds in the innovative ICT sector, by carrying out research and development in application fields that today are crucial for enterprises and public authorities).
- 2.
Uboldo Hospital and Vizzoli Predabissi Hospital. Both of them are situated in Lombardy (Italy) and are part of Azienda Ospedaliera di Melegnano. To respect patients’ privacy, all DLs were anonymized at the time of extraction.
- 3.
GATE is a project of the University of Sheffield and it is freely available as an open source software architecture at http://gate.ac.uk.
- 4.
The DLs were written in Italian, but we will translate quotations from them into English for better clarity.
- 5.
Precision, recall, and F-measure scores were specifically calculated for each diagnostic element. We present the aggregated scores for brevity.
References
Feldman, R., Sanger, J.: The Text Mining Handbook. Advanced Approaches in Analyzing Unstructured Data. Cambridge University Press, New York, NY (2007)
Warrer, P., Hansen, E.H., Juhl-Jensen, L., Aagaard, L.: Using text-mining techniques in electronic patient records to identify ADRs from medicine use. Br. J. Clin. Pharmacol. 73(5), 674–684 (2012). doi:10.1111/j.1365-2125.2011.04153.x
Penz, J.F., Wilcox, A.B.., Hurdle, J.F.: Automated identification of adverse events related to central venous catheters. J. Biomed. Inform. 40(2), 174–182 (2007). doi:10.1016/j.jbi.2006.06.003
Lakhani, P., Kim, W., Langlotz, C.P.: Automated detection of critical results in radiology reports. J. Digit. Imaging 25(1), 30–36 (2012). doi:10.1007/s10278-011-9426-6
He, Q., Veldkamp, B.P., de Vries, T.: Screening for posttraumatic stress disorder using verbal features in self narratives: A text mining approach. Psychiatry Res. (2012). doi:10.1016/j.psychres.2012.01.032
Cunningham, H. et al.: Text Processing with GATE (Version 6). University of Sheffield, Department of Computer Science (2011)
Ananiadou, S., McNaught, J.: Text Mining for Biology and Biomedicine. Artech House, Boston/London (2006)
Acknowledgments
The project was realized by the authors and the following people: Pietro Barbieri, M.D. (Azienda Ospedaliera di Melegnano), developed the overall design and acted as a domain expert (cardiology); Barbara Severgnini, M.D. (Azienda Ospedaliera di Melegnano), also acted as a domain expert (cardiology); Mauro Maistrello, M.D. (Azienda Ospedaliera di Melegnano), extracted the DLs from the hospitals’ databases and anonymized them; and professor Anna Maria Paganoni (Politecnico di Milano, Maths Department “Francesco Brioschi”) and engineer Lorenzo Vayno (Politecnico di Milano) experimented with ML methods.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Italia
About this chapter
Cite this chapter
Ballerio, S., Cerizza, D. (2013). Using Text Mining to Validate Diagnoses of Acute Myocardial Infarction. In: Grieco, N., Marzegalli, M., Paganoni, A. (eds) New Diagnostic, Therapeutic and Organizational Strategies for Acute Coronary Syndromes Patients. Contributions to Statistics. Springer, Milano. https://doi.org/10.1007/978-88-470-5379-3_5
Download citation
DOI: https://doi.org/10.1007/978-88-470-5379-3_5
Published:
Publisher Name: Springer, Milano
Print ISBN: 978-88-470-5378-6
Online ISBN: 978-88-470-5379-3
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)