Analysis of Healthcare Quality Indicators using Data Mining and Development of a Decision Support System

Kim, Hye Sook; Chae, Young-Moon; Tark, Kwan-Chul; Park, Hyun-Ju; Ho, Seung-Hee

Journal of Korean Society Quality Assurance Health Care 2001;8(2): 186.
Published online December 30, 2001.

데이터마이닝을 이용한 의료의 질 측정지표 분석 및 의사결정지원시스템 개발

김혜숙¹, 채영문¹, 탁관철², 박현주², 호승희¹

¹연세대학교 보건대학원
²신촌 세브란스병원 적정진료관리실

Analysis of Healthcare Quality Indicators using Data Mining and Development of a Decision Support System

Hye Sook Kim¹, Young-Moon Chae¹, Kwan-Chul Tark², Hyun-Ju Park², Seung-Hee Ho¹

¹Grduate School of Health Science ans Management Yonsei University
²Quality Improvement Department, Yonsei University Severance Hospital

Abstract

Background
This study presented an analysis of healthcare quality indicators using data mining and a development of decision support system for quality improvement. Method : Specifically, important factors influencing the key quality indicators were identified using a decision tree method for data mining based on 8,405 patients who discharged from a medical center during the period between December 1, 2000 and January 31, 2001. In addition, a decision support system was developed to analyze and monitor trends of these quality indicators using a Visual Basic 6.0. Guidelines and tutorial for quality improvement activities were also included in the system.
Result
Among 12 selected quality indicators, decision tree analysis was performed for 3 indicators ; unscheduled readmission due to the same or related condition, unscheduled return to intensive care unit, and inpatient mortality which have a volume bigger than 100 cases during the period. The optimum range of target group in healthcare quality indicators were identified from the gain chart. Important influencing factors for these 3 indicators were: diagnosis, attribute of the disease, and age of the patient in unscheduled returns to ICU group ; and length of stay, diagnosis, and belonging department in inpatient mortality group.
Conclusion
We developed a decision support system through analysis of healthcare quality indicators and data mining technique which can be effectively implemented for utilization review and quality management in a healthcare organization. In the future, further number of quality indicators should be developed to effectively support a hospital-wide Continuous Quality Improvement activity. Through these endevours, a decision support system can be developed and the newly developed decision support system should be well integrated with the hospital Order Communication System to support concurrent review, utilization review, quality and risk management.

Key words Data mining;Quality indicator;Decision support system;Continuous quality improvement;Quality management;