It includes a step of extracting a feature vector Fnew from face data of a patient as an evaluation subject, a step of selecting a plurality of case patients having feature vectors Fpre(i), extracted from the face data of a plurality of previous patients, that have a short distance from the feature vector Fnew, or a step of selecting a similar case class having a cluster center Gpre(l) that has a short distance from the feature vector Fnew, a step of obtaining pre-orthodontic facial shape models Hpre(i) and a post-orthodontic facial shape models Hpost(i) in which the faces of the selected previous case patients before and after a treatment have been normalized, a step of obtaining a facial shape model Hnew in which the face of the patient as an evaluation subject has been normalized, and a step of obtaining a three-dimensional predicted facial shape model Hprd as predicted after orthodontic treatment, by modifying the facial shape model Hnew of the patient as an evaluation subject, using a vector average difference AVEpost−AVEpre between the pre-treatment and post-treatment facial shape models of case patients having a facial shape similar to that of the patient as an evaluation subject.
