On the Use of Decision Trees Based on Diagnosis and Drug Codes for Analyzing Chronic Patients
Diabetes mellitus (DM) and essential hypertension (EH) are chronic diseases more prevalent every year, both independently and jointly. To gain insights about the particularities of these chronic conditions, we study the use of decision trees as a tool for selecting discriminative features and making predictive analyses of the health status of this kind of chronic patients. We considered gender, age, ICD9 codes for diagnosis and ATC codes for drugs associated with the diabetic and/or hypertensive population linked to the University Hospital of Fuenlabrada (Madrid, Spain) during 2012. Results show a relationship among DM/EH and diseases/drugs related to the respiratory system, mental disorders, or the musculoskeletal system. We conclude that drugs are quite informative, collecting information about the disease when the diagnosis code is not registered. Regarding predictive analyses, when discriminating patients with EH-DM and just one of these chronic conditions, better accuracy is obtained for EH (85.4%) versus DM (80.1%).
KeywordsChronic health status Diabetes Hypertension Feature selection Decision trees Diagnoses Drugs
This work has been partly supported by Research Projects TEC2016-75361-R, TIN2014-62143-EXP, and TIN2015-70799-R from the Spanish Government, and Research Project DTS17/00158 from Carlos III Institute.
- 1.WHO: OMS (2017). http://www.who.int/topics/chronic_diseases/es/
- 3.Soni, A., Mitchell, E.: Expenditures for commonly treated conditions among adults age 18 and older in the US civilian noninstitutionalized population, 2013 (2001)Google Scholar
- 5.International Diabetes Federation: IDF Diabetes Atlas, 5th edn. International Diabetes Federation, Brussels (2011)Google Scholar
- 11.Davis, N.A., LaCour, M.: Foundations of Health Information Management. Elsevier Health Sciences, Amsterdam (2016)Google Scholar
- 12.Averill, R.F., et al.: Development and evaluation of clinical risk groups (CRGs). 3M Health Information Systems (1999)Google Scholar
- 14.Fernández-Sánchez, J., et al.: Clinical risk groups analysis for chronic hypertensive patients in terms of ICD9-cm diagnosis codes. In: Proceedings of the 4th International Conference on Physiological Computing Systems - Vol. 1. INSTICC, SciTePress, pp. 13–22 (2017)Google Scholar
- 15.Centers for Disease Control and Prevention: International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) (2011)Google Scholar
- 16.WHO: collaborating centre for drug statistics methodology. In: Guidelines for ATC Classification and DDD Assignment (2016)Google Scholar
- 19.Quinlan, J.: C4.5. Programs for Machine Learning. Morgan Kaufmann, Burlington (2014)Google Scholar
- 20.Wallace, B.C., et al.: Class imbalance, redux. In: Proceedings of the International Conference on Data Mining, Vancouver, Canada, pp. 754–763, 11–14 December 2011Google Scholar