Application of Support Vector Machine for Prediction of Medication Adherence in Heart Failure Patients
2
조회
0
다운로드
9
인용
0
참고문헌
키워드
초록
Objectives: Heart failure (HF) is a progressive syndrome that marks the end-stage of heart diseases, and it has a high mortality rate and significant cost burden. In particular, non-adherence of medication in HF patients may result in serious consequences such as hospital readmission and death. This study aims to identify predictors of medication adherence in HF patients. In this work, we applied a Support Vector Machine (SVM), a machine-learning method useful for data classification. Methods: Data about medication adherence were collected from patients at a university hospital through self-reported questionnaire. The data included 11 variables of 76 patients with HF. Mathematical simulations were conducted in order to develop a SVM model for the identification of variables that would best predict medication adherence. To evaluate the robustness of the estimates made with the SVM models, leave-one-out cross-validation (LOOCV) was conducted on the data set. Results: The two models that best classified medication adherence in the HF patients were: one with five predictors (gender,daily frequency of medication, medication knowledge, New York Heart Association [NYHA] functional class, spouse)and the other with seven predictors (age, education, monthly income, ejection fraction, mini-mental status exam–Korean [MMSE-K], medication knowledge, NYHA functional class). The highest detection accuracy was 77.63%. Conclusions: SVM modeling is a promising classification approach for predicting medication adherence in HF patients. This predictive model helps stratify the patients so that evidence-based decisions can be made and patients managed appropriately. Further, this approach should be further explored in other complex diseases using other common variables.
Abstract
Objectives: Heart failure (HF) is a progressive syndrome that marks the end-stage of heart diseases, and it has a high mortality rate and significant cost burden. In particular, non-adherence of medication in HF patients may result in serious consequences such as hospital readmission and death. This study aims to identify predictors of medication adherence in HF patients. In this work, we applied a Support Vector Machine (SVM), a machine-learning method useful for data classification. Methods: Data about medication adherence were collected from patients at a university hospital through self-reported questionnaire. The data included 11 variables of 76 patients with HF. Mathematical simulations were conducted in order to develop a SVM model for the identification of variables that would best predict medication adherence. To evaluate the robustness of the estimates made with the SVM models, leave-one-out cross-validation (LOOCV) was conducted on the data set. Results: The two models that best classified medication adherence in the HF patients were: one with five predictors (gender,daily frequency of medication, medication knowledge, New York Heart Association [NYHA] functional class, spouse)and the other with seven predictors (age, education, monthly income, ejection fraction, mini-mental status exam–Korean [MMSE-K], medication knowledge, NYHA functional class). The highest detection accuracy was 77.63%. Conclusions: SVM modeling is a promising classification approach for predicting medication adherence in HF patients. This predictive model helps stratify the patients so that evidence-based decisions can be made and patients managed appropriately. Further, this approach should be further explored in other complex diseases using other common variables.
참고문헌 (27)
- Cortes C, "Support-vector networks", Machine Learning, 20, pp.273~297 (1995)
- Verplancke T, "Support vector machine versus logistic regression modeling for prediction of hospital mortality in critically ill patients with haematological malignancies", BMC Med Inform Decis Mak, 8(56) (2008)
- Yu W, "Application of support vector machine modeling for prediction of common diseases: the case of diabetes and prediabetes", BMC Med Inform Decis Mak, 10, pp.16~ (2010)
- Maglogiannis I, "Support vectors machine-based identification of heart valve diseases using heart sounds", Comput Methods Programs Biomed, 95, pp.47~61 (2009)
- Thurston RC, "Improving the performance of physiologic hot flash measures with support vector machines", Psychophysiology, 46, pp.285~292 (2009)
- Chu A, "A decision support system to facilitate management of patients with acute gastrointestinal bleeding", Artif Intell Med, 42, pp.247~259 (2008)
- Rice SB, "Mining protein function from text using term-based support vector machines", BMC Bioinformatics, 6(Suppl 1), pp.S22~ (2005)
- Hauptman PJ, "Medication adherence in heart failure", Heart Fail Rev, 13, pp.99~106 (2008)
- Komajda M, "Adherence to guidelines is a predictor of outcome in chronic heart failure: the MAHLER survey", Eur Heart J, 26, pp.1653~1659 (2005)
- Toh CT, "Barriers to medication adherence in chronic heart failure patients during home visits", J Pharm Prac Res, 40, pp.27~30 (2010)
- Riegel B, "State of the science: promoting self-care in persons with heart failure: a scientific statement from the American Heart Association", Circulation, 120, pp.1141~1163 (2009)
- van der Wal MH, "Compliance in heart failure patients: the importance of knowledge and beliefs", Eur Heart J, 27, pp.434~440 (2006)
- Hope CJ, "Association of medication adherence, knowledge, and skills with emergency department visits by adults 50 years or older with congestive heart failure", Am J Health Syst Pharm, 61, pp.2043~2049 (2004)
- Rud S, "A support vector machine (SVM) classification approach to heart murmur detection", Lect Notes Comp Sci, 6004, pp.52~59 (2010)
- Balasubramanian VN, "Support vector machine based conformal predictors for risk of complications following a coronary drug eluting stent procedure", Proceedings of Computer in cardiology 2009, pp.5~8 (2009)
- 최근호, "Classification and Sequential Pattern Analysis for Improving Managerial Efficiency and Providing Better Medical Service in Public Healthcare Centers", Healthcare Informatics Research, 16(2), pp.67~76 (2010), 대한의료정보학회
- 최종필, "A Hybrid Bayesian Network Model for Predicting Breast Cancer Prognosis", Healthcare Informatics Research, 15(1), pp.49~57 (2009), 대한의료정보학회
- Kim BM, "Prognosis prediction for class III malocclusion treatment by feature wrapping method", Angle Orthod, 79, pp.683~691 (2009)
- Guyon I, "Gene selection for cancer classification using support vector machines", Mach Learn, 46, pp.389~422 (2002)
- "LIBSVM: a library for support vector machines"[URL]
- "On the value of leave-one-out cross validation bounds"[URL]
- Swets JA, "Measuring the accuracy of diagnostic systems", Science, 240, pp.1285~1293 (1988)
- Kim HS, "Aaptive nonlinear discriminant analysis by regularized minimum squared errors", IEEE Trans Knowl Data Eng, 18, pp.603~612 (2006)
- Vlasnik JJ, "Medication adherence: factors influencing compliance with prescribed medication plans", Case Manager, 16, pp.47~51 (2005)
- Morrow DG, "Improving medication knowledge among older adults with heart failure: a patient-centered approach to instruction design", Gerontologist, 45, pp.545~552 (2005)
- Berkson J, "Limitations of the application of fourfold table analysis to hospital data", Biometrics, 2, pp.47~53 (1946)
- Cho BH, "Application of irregular and unbalanced data to predict diabetic nephropathy using visualization and feature selection methods", Artif Intell Med, 42, pp.37~53 (2008)