This study aimed to characterize the use of medical service and medical costs of each cluster categorized by its discharge disposition pattern.

Data extracted from Electronic Data Interchange database of Korea Workers' Compensation and Welfare Service was analyzed. Among those who suffered from industrial accidents from Jan 1, 2006 to Dec 31, 2006, 422 were stroke patients. We categorized the subjects into 2 groups using k-means cluster analysis according to the discharge disposition pattern. Demographic characteristics, days of treatment, medical cost, initially admitted medical institution and disease type were analyzed in each group.

There was no difference between the 2 groups in age, sex, type of stroke (ischemic or hemorrhagic stroke) and initially admitted medical institution. However medical cost and days of treatment were significantly different between 2 groups.

K-means cluster analysis according to transferring pattern revealed a distinct group with longer hospitalization and more medical cost in injured workers. Further study is necessary to find out the characteristics of this group.