Extracting Diagnosis Patterns in Electronic Medical Records using Association Rule Mining

Abstract

Data mining technologies have been used extensively in the commercial retail sectors to extract data from their "big data" warehouses. In healthcare, data mining has been used as well in various aspects which we explore. The voluminous amounts of data generated by medical systems form a good basis for discovery of interesting patterns that may aid decision making and saving of lives not to mention reduction of costs in research work and possibly reduced morbidity prevalence. It is from this that we set out to implement a concept using association rule mining technology to find out any possible diagnostic associations that may have arisen in patients' medical records spanning across multiple contacts of care. The dataset was obtained from Practice Fusion's open research data that contained over 98,000 patient clinic visits from all American states. Using an implementation of the classical apriori algorithm, we were able to mine for patterns arising from medical diagnosis data. The diagnosis data was based on ICD-9 coding and this helped limit the set of possible diagnostic groups for the analysis. We then subjected the results to domain expert opinion. The panel of experts validated some of the most common associations that had a minimum confidence level of between 56-76% with a concurrence rate of 90% whereas others elicited debate amongst the medical practitioners. The results of our research showed that association rule mining can not only be used to confirm what is already known from health data in form of comorbidity patterns, but also generate some very interesting disease diagnosis associations that can provide a good starting point and room for further exploration through studies by medical researchers to explain the patterns that are seemingly unknown or peculiar in the concerned populations.

References

• "Standards and Guidelines for Electronic Medical Record Systems in Kenya," Ministries of Health, Government of Kenya, Health Information Policy, 2009.
• R. Agrawal and R. Srikant, "Fast Algorithms For Mining Association Rules In Datamining," in 20th International Conference on Very Large Data Bases, Santiago, Chile, 1994, pp. 487–499.
• "WHO | International Classification of Diseases (ICD)," WHO. [Online]. Available: http://www. who. int/classifications/icd/en/. [Accessed: 03-Feb-2014].
• "WHO | World Health Organization," WHO, 2014. [Online]. Available: http://www. who. int/classifications/icd/revision/en/. [Accessed: 05-Feb-2014].
• "ICD-10 Conversion and Mapping - AAPC," 2014. [Online]. Available: http://www. aapc. com/icd-10/conversion-mapping. aspx. [Accessed: 06-Feb-2014].
• M. J. A. Berry and G. Linoff, Data mining techniques for marketing, sales, and customer relationship management, 2nd ed. Indianapolis: Wiley, 2004.
• C. J. Matheus, P. K. Chan, and G. Piatetsky-Shapiro, "Systems for Knowledge Discovery in Databases," IEEE Trans Knowl Data Eng, vol. 5, no. 6, pp. 903–913, Dec. 1993.
• B. Bhargavi, B. Venkanna, and V. H. Prasad, "Mining Frequent Items Using Directed Graphs," Int. J. Sci. Res. Comput. Sci. , vol. 1, no. 2, pp. 21–24, Sep. 2013.
• A. Rajak and M. K. Gupta, "Association rule mining-applications in various areas," in Proceedings of International Conference on Data Management, Ghaziabad, India, 2008, pp. 3–7.
• G. Serban, C. Istvan-Gergely, and C. Alina, "A Programming Interface For Medical diagnosis Prediction," Stud. Univ. Babes - Bolyai Inform. , vol. LI, pp. 21–30, 2006.
• H. C. Koh and G. Tan, "Data mining applications in healthcare," J. Healthc. Inf. Manag. , vol. 19, no. 2, p. 65, 2011.
• Y. -M. Tai and H. -W. Chiu, "Comorbidity study of ADHD: applying association rule mining (ARM) to National Health Insurance Database of Taiwan," Int. J. Med. Inf. , vol. 78, no. 12, pp. e75–83, Dec. 2009.
• H. S. Kim, A. M. Shin, M. K. Kim, and Y. N. Kim, "Comorbidity Study on Type 2 Diabetes Mellitus Using Data Mining," Korean J. Intern. Med. , vol. 27, no. 2, pp. 197–202, Jun. 2012.
• M. A. Rashid, M. T. Hoque, and A. Sattar, "Association Rules Mining Based Clinical Observations," ArXiv Prepr. ArXiv14012571, 2014.
• "Analyze This! | Research Division," Research- Practice Fusion, 06-Jun-2012. [Online]. Available: http://www. practicefusion. com/research/analyze-this/. [Accessed: 06-Feb-2014].
• "Big Data Gets Put to Work for Public Health," Practice Fusion, 15-Mar-2012. [Online]. Available: http://www. practicefusion. com/pages/pr/big-data-public-health. html. [Accessed: 06-Feb-2014].
• CMS, "ICD-9 Code Lookup," Centers for Medicare & Medicaid Services, 2014. [Online]. Available: http://www. cms. gov/medicare-coverage-database/staticpages/icd-9-code-lookup. aspx. [Accessed: 06-Aug-2014].
• J. F. Roddick, P. Fule, and W. J. Graco, "Exploratory medical knowledge discovery: Experiences and issues," ACM SIGKDD Explor. Newsl. , vol. 5, no. 1, pp. 94–99, 2003.
• K. S. Vimaleswaran, A. Cavadino, D. J. Berry, R. Jorde, A. K. Dieffenbach, C. Lu, A. C. Alves, H. J. L. Heerspink, E. Tikkanen, J. Eriksson, A. Wong, M. Mangino, K. A. Jablonski, I. M. Nolte, D. K. Houston, T. S. Ahluwalia, P. J. van der Most, D. Pasko, L. Zgaga, E. Thiering, V. Vitart, R. M. Fraser, J. E. Huffman, R. A. de Boer, B. Schöttker, K. -U. Saum, M. I. McCarthy, J. Dupuis, K. -H. Herzig, S. Sebert, A. Pouta, J. Laitinen, M. E. Kleber, G. Navis, M. Lorentzon, K. Jameson, N. Arden, J. A. Cooper, J. Acharya, R. Hardy, O. Raitakari, S. Ripatti, L. K. Billings, J. Lahti, C. Osmond, B. W. Penninx, L. Rejnmark, K. K. Lohman, L. Paternoster, R. P. Stolk, D. G. Hernandez, L. Byberg, E. Hagström, H. Melhus, E. Ingelsson, D. Mellström, Ö. Ljunggren, I. Tzoulaki, S. McLachlan, E. Theodoratou, C. M. T. Tiesler, A. Jula, P. Navarro, A. F. Wright, O. Polasek, J. F. Wilson, I. Rudan, V. Salomaa, J. Heinrich, H. Campbell, J. F. Price, M. Karlsson, L. Lind, K. Michaëlsson, S. Bandinelli, T. M. Frayling, C. A. Hartman, T. I. A. Sørensen, S. B. Kritchevsky, B. L. Langdahl, J. G. Eriksson, J. C. Florez, T. D. Spector, T. Lehtimäki, D. Kuh, S. E. Humphries, C. Cooper, C. Ohlsson, W. März, M. H. de Borst, M. Kumari, M. Kivimaki, T. J. Wang, C. Power, H. Brenner, G. Grimnes, P. van der Harst, H. Snieder, A. D. Hingorani, S. Pilz, J. C. Whittaker, M. -R. Järvelin, and E. Hyppönen, "Association of vitamin D status with arterial blood pressure and hypertension risk: a mendelian randomisation study," Lancet Diabetes Endocrinol. , Jun. 2014.

Index Terms

Keywords