Abstract
The main goal of this research is to identify and extract risk factors for Diabetes Mellitus. The data source for our experiments are 8 mln outpatient records from the Bulgarian Diabetes Registry submitted to the Bulgarian Health Insurance Fund by general practitioners and all kinds of professionals during 2014. In this paper we report our work on automatic identification of the patients’ smoking status. The experiments are performed on free text sections of a randomly extracted subset of the registry outpatient records. Although no rich semantic resources for Bulgarian exist, we were able to enrich our model with semantic features based on categorical vocabularies. In addition to the automatically labeled records we use the records form the Diabetes register that contain diagnoses related to tobacco usage. Finally, a combined result from structured information (ICD-10 codes) and extracted data about the smoking status is associated with each patient. The reported accuracy of the best model is comparable to the highest results reported at the i2b2 Challenge 2006. These method is ready to be validated on big data after minor improvements.
References
Aramaki, E., Imai, T., Miyo, K., Ohe, K.: Patient status classification by using rule based sentence extraction and BM25 kNN-based classifier. In: i2b2 Workshop on Challenges in Natural Language Processing for Clinical Data (2006)
Boytcheva, S., Angelova, G., Angelov, Z., Tcharaktchiev, D.: Text mining and big data analytics for retrospective analysis of clinical texts from outpatient care. Cybern. Inf. Technol. 15(4), 58–77 (2015)
Boytcheva, S., Angelova, G., Angelov, Z., Tcharaktchiev, D.: Mining clinical events to reveal patterns and sequences. In: Margenov, S., Angelova, G., Agre, G. (eds.) Innovative Approaches and Solutions in Advanced Intelligent Systems. Studies in Computational Intelligence, vol. 648, pp. 95–111. Springer, Heidelberg (2016)
Clark, C., Good, K., Jezierny, L., Macpherson, M., Wilson, B., Chajewska, U.: Identifying smokers with a medical extraction system. J. Am. Med. Inform. Assoc. 15, 36–39 (2008)
Cohen, A.M.: Five-way smoking status classification using text hot-spot identification and error-correcting output codes. J. Am. Med. Inform. Assoc. 15, 32–35 (2008)
Cohen, K.B., Demner-Fushman, D.: Biomedical Natural Language Processing, vol. 11. John Benjamins Publishing Company, Amsterdam (2014)
Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.: The WEKA data mining software: an update. SIGKDD Explor. Newsl. 11(1), 10–18 (2009)
International Classification of Diseases and Related Health Problems 10th Revision. http://apps.who.int/classifications/icd10/browse/2015/en
Jonnagaddala, J., Dai, H.-J., Ray, P., Liaw, S.-T.: A preliminary study on automatic identification of patient smoking status in unstructured electronic health records. In: ACL-IJCNLP 2015, pp. 147–151 (2015)
Laurence, A.: AntWordProfiler (Version 1.4.0w) (Computer software). Waseda University, Tokyo, Japan (2014). http://www.laurenceanthony.net/
Nakov, P.: BulStem : Design and evaluation of inflectional stemmer for Bulgarian. In: Proceedings of Workshop on Balkan Language Resources and Tools (1st Balkan Conference in Informatics) (2003)
Nikolova, I., Tcharaktchiev, D., Boytcheva, S., Angelov, Z., Angelova, G.: Applying language technologies on healthcare patient records for better treatment of Bulgarian diabetic patients. In: Agre, G., Hitzler, P., Krisnadhi, A.A., Kuznetsov, S.O. (eds.) AIMSA 2014. LNCS, vol. 8722, pp. 92–103. Springer, Heidelberg (2014)
Osenova, P., Simov, K.: Using the linguistic knowledge in BulTreeBank for the selection of the correct parses. In: Proceedings of The Ninth International Workshop on Treebanks and Linguistic Theories, Tartu, Estonia, pp. 163–174 (2010)
Rice, D., Kocurek, B., Snead, C.A.: Chronic disease management for diabetes: Baylor Health Care System’s coordinated efforts and the opening of the Diabetes Health and Wellness Institute. Proc. (Bayl. Univ. Med. Cent.) 23, 230–234 (2010)
Stubbs, A., Uzuner, Ö.: Annotating risk factors for heart disease in clinical narratives for diabetic patients. J. Biomed. Inform. 58, S78–S91 (2015)
Uzuner, Ö., Goldstein, I., Luo, Y., Kohane, I.: Identifying patient smoking status from medical discharge records. J. Am. Med. Inform. Assoc.: JAMIA 15(1), 14–24 (2008)
Wiley, L.K., Shah, A., Xu, H., Bush, W.S.: ICD-9 tobacco use codes are effective identifiers of smoking status. J. Am. Med. Inform. Assoc. 20(4), 652–658 (2013)
Acknowledgements
This study is partially financed by the grant DFNP-100/04.05.2016 “Automatic analysis of clinical text in Bulgarian for discovery of correlations in the Diabetes Registry” with the Bulgarian Academy of Sciences.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Nikolova, I., Boytcheva, S., Angelova, G., Angelov, Z. (2016). Combining Structured and Free Textual Data of Diabetic Patients’ Smoking Status. In: Dichev, C., Agre, G. (eds) Artificial Intelligence: Methodology, Systems, and Applications. AIMSA 2016. Lecture Notes in Computer Science(), vol 9883. Springer, Cham. https://doi.org/10.1007/978-3-319-44748-3_6
Download citation
DOI: https://doi.org/10.1007/978-3-319-44748-3_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-44747-6
Online ISBN: 978-3-319-44748-3
eBook Packages: Computer ScienceComputer Science (R0)