After the introduction of National Medical Insurance in 1989, the medical demand has rapidly increased. The impact of increased medical demand was followed by an increase in the number of claims in need of review. We studied a new, fair method for reducing the number of claims reviewed. We analysed 90,583 outpatient claims submitted between September and October; claims were made for services given August of 1994. We finally suggested a screening system for claims review using a statistical method of discriminant analysis of the medical costs. The results were as follows. 1. In the cut-off group, age, days of medication, number of hospital or clinic visits, and total charge were significantly high. The cut-off rates according to the hospital-type and existence of accompanied disease were significantly different 2. According to ICD, the cut-off rate was highest in peripheral enthesopathies and allied syndromes(20.76%), lowest in acute sinusitis(0.93%). The mean charges were significantly different according to ICD and existence of cut-off. 3. We build discriminant functions by ICD with such discriminant variables as patient age, sex, existence of accompanied disease, number of hospital or clinic visits, and 9 detailed hospital or clinic charges included in claim. 4. We applied the discriminant function for screening those claims that were expected to be cut-off. The sensitivities comprised from 40% to 70%, and specificities from 70% to 95% by ICD. Acute rhinitis had highest sensitivity(100.00%) and other local infections of skin and subcutaneous tissue had highest specificity(98.45%). The expected number of cut-off was 17,762(19.61%). The total sensitivity was 49.62%, the total specificity was 82.57% and the error rate was 19.66%. We lacked economic analysis such as cost-benefit analysis. But, if the new method of screening claims using discriminant analysis were applied, the number of claims in need of review will reduce considerably.