Healthc Inform Res.  2013 Mar;19(1):33-41. 10.4258/hir.2013.19.1.33.

Predictors of Medication Adherence in Elderly Patients with Chronic Diseases Using Support Vector Machine Models

• Lee SK
• Kang BY
• Kim HG
• Son YJ

• KMID: 2166660
• DOI: http://doi.org/10.4258/hir.2013.19.1.33

Abstract

OBJECTIVES
The aim of this study was to establish a prediction model of medication adherence in elderly patients with chronic diseases and to identify variables showing the highest classification accuracy of medication adherence in elderly patients with chronic diseases using support vector machine (SVM) and conventional statistical methods, such as logistic regression (LR).
METHODS
We included 293 chronic disease patients older than 65 years treated at one tertiary hospital. For the medication adherence, Morisky's self-report was used. Data were collected through face-to-face interviews. The mean age of the patients was 73.8 years. The classification process was performed with LR (SPSS ver. 20.0) and SVM (MATLAB ver. 7.12) method.
RESULTS
Taking into account 16 variables as predictors, the result of applying LR and SVM classification accuracy was 71.1% and 97.3%, respectively. We listed the top nine variables selected by SVM, and the accuracy using a single variable, self-efficacy, was 72.4%. The results suggest that self-efficacy is a key factor to medication adherence among a Korean elderly population both in LR and SVM.
CONCLUSIONS
Medication non-adherence was strongly associated with self-efficacy. Also, modifiable factors such as depression, health literacy, and medication knowledge associated with medication non-adherence were identified. Since SVM builds an optimal classifier to minimize empirical classification errors in discriminating between patient samples, it could achieve a higher accuracy with the smaller number of variables than the number of variables used in LR. Further applications of our approach in areas of complex diseases, treatment will provide uncharted potentials to researchers in the domains.

Keyword

Medication Adherence; Aged; Chronic Disease; Regression Analysis; Support Vector Machines

MeSH Terms

Aged
Chronic Disease
Depression
Health Literacy
Humans
Logistic Models
Medication Adherence
Regression Analysis
Support Vector Machine
Tertiary Care Centers

Figure

• 

  Figure 1 The Principal Component Analysis plot of 293 samples (stars represent good adherence and circles represent poor adherence).

• 

  Figure 2 Classification accuracy for the 293 patients achieved with support vector machine (SVM) according to the number of input variables.

• 

  Figure 3 Area under the receiver operating characteristic curve (AUC) of the logistic regression (LR) and support vector machine (SVM) models.

Reference

1. 2011 Statistics on older people [Internet]. c2011. cited at 2013 Mar 18. Daejeon: Statistics Korea;Available from: http://kostat.go.kr/portal/korea/kor_nw/2/1/index.board?bmode=read&aSeq=250718.

2. Kim SO, Park JY, Choi YS, Lee HY, Kim JH. Control scheme of drug cost according to a sort of medical service using. Seoul: National Health Insurance.

3. Hughes CM. Medication non-adherence in the elderly: how big is the problem? Drugs Aging. 2004. 21(12):793–811.

4. Donnan PT, MacDonald TM, Morris AD. Adherence to prescribed oral hypoglycaemic medication in a population of patients with type 2 diabetes: a retrospective cohort study. Diabet Med. 2002. 19(4):279–284.

5. Mann DM, Allegrante JP, Natarajan S, Halm EA, Charlson M. Predictors of adherence to statins for primary prevention. Cardiovasc Drugs Ther. 2007. 21(4):311–316.

6. Rieckmann N, Kronish IM, Haas D, Gerin W, Chaplin WF, Burg MM, et al. Persistent depressive symptoms lower aspirin adherence after acute coronary syndromes. Am Heart J. 2006. 152(5):922–927.

7. Dreiseitl S, Ohno-Machado L. Logistic regression and artificial neural network classification models: a methodology review. J Biomed Inform. 2002. 35(5-6):352–359.

8. Verplancke T, Van Looy S, Benoit D, Vansteelandt S, Depuydt P, De Turck F, et al. Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies. BMC Med Inform Decis Mak. 2008. 8:56.

9. Lin Y, Lee Y, Wahba G. Support vector machines for classification in nonstandard situations. Mach Learn. 2002. 46(1-3):191–202.

10. Lee SM, Park RW. Basic concepts and principles of data mining in clinical practice. J Korean Soc Med Inform. 2009. 15(2):175–189.

11. Sheikh JI, Hesavage JA. Geriatric Depression Scale (GDS): recent evidence and development of a shorter version. Clin Gerontol. 1986. 5(1-2):165–173.

12. Burge S, White D, Bajorek E, Bazaldua O, Trevino J, Albright T, et al. Correlates of medication knowledge and adherence: findings from the residency research network of South Texas. Fam Med. 2005. 37(10):712–718.

13. Chew LD, Bradley KA, Boyko EJ. Brief questions to identify patients with inadequate health literacy. Fam Med. 2004. 36(8):588–594.

14. Risser J, Jacobson TA, Kripalani S. Development and psychometric evaluation of the Self-efficacy for Appropriate Medication Use Scale (SEAMS) in low-literacy patients with chronic disease. J Nurs Meas. 2007. 15(3):203–219.

15. Morisky DE, Green LW, Levine DM. Concurrent and predictive validity of a self-reported measure of medication adherence. Med Care. 1986. 24(1):67–74.

16. Krapek K, King K, Warren SS, George KG, Caputo DA, Mihelich K, et al. Medication adherence and associated hemoglobin A1c in type 2 diabetes. Ann Pharmacother. 2004. 38(9):1357–1362.

17. Gellad WF, Grenard JL, Marcum ZA. A systematic review of barriers to medication adherence in the elderly: looking beyond cost and regimen complexity. Am J Geriatr Pharmacother. 2011. 9(1):11–23.

18. Jolliffe IT. Principal component analysis. 2002. 2nd ed. New York (NY): Springer.

19. Sahiner B, Chan HP, Petrick N, Wagner RF, Hadjiiski L. Feature selection and classifier performance in computer-aided diagnosis: the effect of finite sample size. Med Phys. 2000. 27(7):1509–1522.

20. Swets JA. Measuring the accuracy of diagnostic systems. Science. 1988. 240(4857):1285–1293.

21. Shalansky SJ, Levy AR. Effect of number of medications on cardiovascular therapy adherence. Ann Pharmacother. 2002. 36(10):1532–1539.

22. Miller NH. Compliance with treatment regimens in chronic asymptomatic diseases. Am J Med. 1997. 102(2A):43–49.

23. Nielsen-Bohlman L, Panzer AM, Kindig DA. Health literacy: a prescription to end confusion. 2004. Washington (DC): National Academies Press.

24. Gazmararian JA, Williams MV, Peel J, Baker DW. Health literacy and knowledge of chronic disease. Patient Educ Couns. 2003. 51(3):267–275.

25. Ziegelstein RC, Fauerbach JA, Stevens SS, Romanelli J, Richter DP, Bush DE. Patients with depression are less likely to follow recommendations to reduce cardiac risk during recovery from a myocardial infarction. Arch Intern Med. 2000. 160(12):1818–1823.

26. Son YJ, Kim HG, Kim EH, Choi S, Lee SK. Application of support vector machine for prediction of medication adherence in heart failure patients. Healthc Inform Res. 2010. 16(4):253–259.