Healthc Inform Res.  2010 Jun;16(2):67-76. 10.4258/hir.2010.16.2.67.

Classification and Sequential Pattern Analysis for Improving Managerial Efficiency and Providing Better Medical Service in Public Healthcare Centers

• Choi K
• Chung S
• Rhee H
• Suh Y

• KMID: 2166569
• DOI: http://doi.org/10.4258/hir.2010.16.2.67

Abstract

OBJECTIVES
This study sought to find answers to the following questions: 1) Can we predict whether a patient will revisit a healthcare center? 2) Can we anticipate diseases of patients who revisit the center?
METHODS
For the first question, we applied 5 classification algorithms (decision tree, artificial neural network, logistic regression, Bayesian networks, and Naive Bayes) and the stacking-bagging method for building classification models. To solve the second question, we performed sequential pattern analysis.
RESULTS
We determined: 1) In general, the most influential variables which impact whether a patient of a public healthcare center will revisit it or not are personal burden, insurance bill, period of prescription, age, systolic pressure, name of disease, and postal code. 2) The best plain classification model is dependent on the dataset. 3) Based on average of classification accuracy, the proposed stacking-bagging method outperformed all traditional classification models and our sequential pattern analysis revealed 16 sequential patterns.
CONCLUSIONS
Classification models and sequential patterns can help public healthcare centers plan and implement healthcare service programs and businesses that are more appropriate to local residents, encouraging them to revisit public health centers.

Keyword

Public Healthcare Center; Data Mining; Classification Analysis; Sequential Pattern Analysis; Ensemble Method

MeSH Terms

Blood Pressure
Commerce
Data Mining
Delivery of Health Care
Humans
Insurance
Logistic Models
Prescriptions
Public Health

Figure

• 

  Figure 1 Average of classification accuracy of each data mining techniques. DT: decision tree, LR: logistic regression, ANN: artificial neural network, BN: Bayesian networks, NB: Naïve Bayes.

• 

  Figure 2 Classification accuracy of plain best, bagging of each best plain technique, stacking, and stacking-bagging method in each dataset. PB: plain best, B-DT: bagging of decision tree, B-LR: bagging of logistic regression, B-ANN: bagging of artificial neural network, B-BN: bagging of Bayesian network, B-NB: bagging of Naïve Bayes, SB: stacking-bagging. 3M: 3 months dataset, 6M: 6 months dataset, 12M: 12 months dataset.

Reference

1. Raphael D, Bryant T. The state's role in promoting population health: public health concerns in Canada, USA, UK, and Sweden. Health Policy. 2006. 78:39–55.

2. Kim HY. A positive study on satisfaction in public medical service according to types of community people. J Korean Assoc Gov. 2007. 14:325–347.

3. Yoon KJ. Using DEA to measure the efficiency of local health centers. J Korean Assoc Policy Stud. 1996. 5:80–109.

4. Yoo KR. Measuring the productivity of public health centers: the case of the Jeollabuk provice in Korea. Korean Rev Public Adm. 2003. 37:261–280.

5. Nam CH. Policy development on health administration system in the era of local autonomous government. J Korean Soc Health Educ Promot. 1996. 16:101–126.

6. Chae YM, Kim HS, Tark KC, Park HJ, Ho SH. Analysis of healthcare quality indicator using data mining and decision support system. Expert Syst Appl. 2003. 24:167–172.

7. Han HK, Kim HS, Sohn SY. Sequential association rules for forecasting failure patterns of aircrafts in Korean airforce. Expert Syst Appl. 2009. 36:1129–1133.

8. Hung SY, Yen DC, Wang HY. Applying data mining to telecome churn management. Expert Syst Appl. 2006. 31:515–524.

9. Wu LG, Lee JX, Huang HD, Liu BJ, Horng JT. An expert system to predict protein thermostability using decision tree. Expert Syst Appl. 2009. 36:9007–9014.

10. Yeh IC, Lien CH. The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Syst Appl. 2009. 36:2473–2480.

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

12. Silva A, Cortez P, Santos MF, Gomes L, Neves J. Mortality assessment in intensive care units via adverse events using artificial neural networks. Artif Intell Med. 2006. 36:223–234.

13. Choi JP, Han TH, Park RW. A hybrid Bayesian network model for predicting breast cancer prognosis. J Korean Soc Med Inform. 2009. 15:49–57.

14. Diri B, Albayrak S. Visualization and analysis of classifiers performance in multi-class medical data. Expert Syst Appl. 2008. 34:628–634.

15. Phillips-Wren G, Sharkey P, Dy SM. Mining lung cancer patient data to assess healthcare resource utilization. Expert Syst Appl. 2008. 35:1611–1619.

16. Chang CL, Chen CH. Applying decision tree and neural network to increase quality of dermatologic diagnosis. Expert Syst Appl. 2009. 36:4035–4041.

17. Lee WI, Shin BY. Application of neural networks to recognize profitable customers for dental services marketing: a case of dental clinics in Taiwan. Expert Syst Appl. 2009. 36:199–208.

18. Polat K, Kara SI, Guven A, Gunes S. Usage of class dependency based feature selection and fuzzy weighted pre-processing methods on classification of macular disease. Expert Syst Appl. 2009. 36:2584–2591.

19. Ture M, Tokatli F, Omurlu IK. The comparisons of prognostic indexes using data mining techniques and Cox regression analysis in the breast cancer data. Expert Syst Appl. 2009. 36:8247–8254.

20. Chang P, Huang FP, Lai ML. The feasibility of using classification and identification techniques to auto-assess the quality of health information on the web. J Korean Soc Med Inform. 2009. 15:247–254.

21. Kang JO, Chung SH, Suh YM. Prediction of hospital charges for the cancer patients with data mining techniques. J Korean Soc Med Inform. 2009. 15:13–23.

22. Exarchos TP, Papaloukas C, Lampros C, Fotiadis DI. Mining sequential patterns for protein fold recognition. J Biomed Inform. 2008. 41:165–179.

23. Chiang JH, Liu HS, Chao SY, Chen CY. Discovering gene-gene relations from sequential sentence patterns in biomedical literature. Expert Syst Appl. 2007. 33:1036–1041.

24. Ryan GW. What do sequential behavioral patterns suggest about the medical decision-making process: modeling home case management of acute illnesses in a rural Cameroonian village. Soc Sci Med. 1998. 46:209–225.

25. Lasker GE. Application of sequential pattern-recognition technique to medical diagnostics. Int J Biomed Comput. 1970. 1:173–186.

26. Lin F, Chou S, Pan S, Chen Y. Mining time dependency patterns in clinical pathways. Int J Med Inform. 2001. 62:11–25.

27. Concaro S, Sacchi L, Bellazzi R. Temporal data mining methods for the analysis of the AHRQ archives. Proc Am Med Inform Assoc 2007 Annu Symp. 2007. Chicago (IL): American Medical Information Association.

28. Cooper GS, Virnig B, Klabunde CN, Schussler N, Freeman J, Warren JL. Use of SEER-Medicare data for measuring cancer surgery. Med Care. 2002. 40:8 Suppl. IV-43–IV-48.

29. Earle CC, Nattinger AB, Potosky AL, Lang K, Mallick R, Berger M, Warren JL. Identifying cancer relapse using SEER-Medicare data. Med Care. 2002. 40:8 Suppl. IV-75–IV-81.

30. Oh HS. Health behavior and utilization of the public health center in rural adults. J Honam Univ Acad. 2008. 29:361–376.

31. Yoo HR. Implementing a smoking cessation clinic at a public health center in Korea: evaluating the outcomes and the smokers' perceptions. J Korean Acad Public Health Nurs. 2008. 22:62–73.

32. Yoon HS, Lee HY, Lee SK. Factors associated with the use of health promotion program: Seoul community health center. Health Soc Welf Rev. 2008. 28:157–184.

33. Cao JM, Kanafani A. Real-time decision support for integration of airline flight cancellations and delays part II: algorithm and computational experiments. Transp Plan Technol. 1997. 20:201–217.

34. Devaraj S, Kohli R. Information technology payoff in the health-care industry: a longitudinal study. J Manag Inf Syst. 2000. 16:41–67.

35. Dietterich TG. An experimental comparison of three methods for constructing ensembles of decision trees: bagging, boosting, and randomization. Mach Learn. 2000. 40:139–157.

36. Opitz D, Maclin R. Popular ensemble methods: an empirical study. J Artif Intell Res. 1999. 11:169–198.

37. Zhu D. A hybrid approach for efficient ensembles. Decis Support Syst. 2010. 48:480–487.