Nursing staffing is of major interest in hospital management, however, no practical method has been developed. The present study proposed a mathematical model based on the patient classification system for nursing staffing optimization. A few characteristic parameters possibly determined experimentally and/or empirically were introduced followed by systematic calculation of the required number of nurses. An essential concept of the model is the unit work load defined as the amount of nursing work performed on single patient per unit time, where the work load is defined as the number of nursing staffs multiplied by the working hours. The unit work load was considered to vary with the patient classification level as well as the working time during a day, both of which were represented by corresponding parameter values. The number of patients for each class and the number of working hours were multiplied to the unit work load, and added up to obtain the total required work load. As the next step, the averaged number of hours that a nurse could provide per day was formulated considering the degree of nursing practice experience into 3 levels. Finally, the appropriate number of nursing staffs was calculated as the total work load divided by the average working hours per nurse. The present technique has a great advantage that the number of nursing staffs to fulfill the required work load is systematically calculated once the characteristic parameters are appropriately determined, leading to instant and fast evaluation. A practical PC program was also developed to apply the present model to nursing practice.