Abstract
The ministry of Health, Labor and Welfare of Japan introduced a Long –Term Care Insurance
system of April 1st 2000, then started a revised system in April 1st 2003. The eligibility assessment
executes classification of patients by tree-based algorithm which enables to classify patients into seven
classes depending on the amount of care needed by the eligibility assessment of the Long Term Care
Insurance. The problem of finding the necessary conditions for classifying patients into each class is the
reverse problem of classification. This article proposes an algorithm for the reverse problem of
classification. The computational experiment reveals the effectiveness of the proposed algorithm.
Sensitivity analysis is also described.
