Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

Data Mining for Knowledge Management in a Health Insurance Domain

  • Chae, Young-Moon (Graduate School of Health Policy and Administration Yonsei University) ;
  • Ho, Seung-Hee (Graduate School of Health Policy and Administration Yonsei University) ;
  • Cho, Kyoung-Won (Graduate School of Health Policy and Administration Yonsei University) ;
  • Lee, Dong-Ha (Graduate School of Health Policy and Administration Yonsei University) ;
  • Ji, Sun-Ha (Graduate School of Health Policy and Administration Yonsei University)
  • Published : 2000.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

This study examined the characteristicso f the knowledge discovery and data mining algorithms to demonstrate how they can be used to predict health outcomes and provide policy information for hypertension management using the Korea Medical Insurance Corporation database. Specifically this study validated the predictive power of data mining algorithms by comparing the performance of logistic regression and two decision tree algorithms CHAID (Chi-squared Automatic Interaction Detection) and C5.0 (a variant of C4.5) since logistic regression has assumed a major position in the healthcare field as a method for predicting or classifying health outcomes based on the specific characteristics of each individual case. This comparison was performed using the test set of 4,588 beneficiaries and the training set of 13,689 beneficiaries that were used to develop the models. On the contrary to the previous study CHAID algorithm performed better than logistic regression in predicting hypertension but C5.0 had the lowest predictive power. In addition CHAID algorithm and association rule also provided the segment characteristics for the risk factors that may be used in developing hypertension management programs. This showed that data mining approach can be a useful analytic tool for predicting and classifying health outcomes data.

Keywords

References

  1. Management information systems, fifth edition Laudon KC;Laudon JP
  2. Health Promotion Law Misistry of Health and Welfare
  3. Advances in Knowledge Discovery and Data Mining From data mining to knowledge discovery; an over-view. Fayyad U.;Piatesky-Shapiro G;Smyth P.;Fayyad U;Piatetsky-Shapiro G,;Smyth eds.
  4. Arch Pathol Lab Med v.122 Pathology information systems: data mining leads to knowledge discovery McDonald JM;Brossette S;Moser SA
  5. Proceedings of Annual Confernece of AMIA Medical data mining: Knowledge discovery in c clinical data warehouse Prather JC;Lobach DF;Goodwin LK;Hales JW;Hage ML;Hammond WE
  6. Computers and Biomedical Research v.30 Automated detection of hereditary syndromes using data mining Evans S;Lemon S;Deters CA;Fusaro RM;Lynch HT
  7. Computers and Biomedical Research v.26 A comparison of logistic regression to decision-tree induction in a medical domain Long WJ;Griffith JL;Selker HP;DAgostino RB
  8. C4.5: Programs for machine learning Quinlan JR
  9. J of Applied Statistics v.18 A method of choosing multiway partitions for classification and decision trees Biggs DB;de Ville B;Suen E.
  10. International Conference on the Management of Data. In Proceeding of the ACMSIGMOD Mining association rules between sets of items in large databases Arawal R;Imielinski T;Swami A.
  11. Rulequest. C5.0 better than C4.5
  12. Informatica v.21 Medical decision support system for the management of hypertension Chae YM;Lee SH;Ho SH;Bae MY;Ohrr HC