Computer-aided diagnosis of odontogenic lesions.

4 cysts and 8 tumors of odontogenic origin have been described for the computer in terms of the prevalence of the associated clinical and radiological findings. Symptom prevalence as given in the literature and modified by our own experience was stated quantitatively as incidence ratios so that Bayes' formula could be used to calculate the probability of each disorder for each set of patient data. The model was applied to 48 cases whose lesions were identified by histopathology following surgery. In all cases, the actual lesion was listed in the computer-produced differential diagnosis, in 94% of the cases the lesion headed the list, and in 75% a probability of 0.85 or greater was achieved. The model can thus be applied to patients awaiting surgery to obtain a reliable differential diagnosis for guiding the medical staff in the proper management of the patient.