RATIONALE AND OBJECTIVES. Case-based reasoning, an artificial intellig
ence technique for learning and reasoning from experience, has shown g
reat potential for use in decision support systems. The authors develo
ped and tested a prototype case-based decision support system to explo
re the applicability of this technique to the selection of diagnostic
imaging procedures. METHODS. A case-based system, ProtoISIS, was devel
oped based on the Protos learning apprentice. ProtoISIS learned the do
main of ultrasonography and body computed tomography by reviewing 200
consecutive cases of actual requests for imaging procedures. ProtoISIS
was tested by using it to classify four sets of 25 cases of actual im
aging procedure requests. RESULTS. ProtoISIS correctly classified 72%
of the imaging-procedure requests. Its performance improved as it gain
ed experience: in the last two test series, it correctly classified 84
% of the cases presented. CONCLUSIONS. Case-based reasoning can be app
lied successfully to the selection of diagnostic imaging procedures an
d holds potential for use in clinical decision support aids. Further w
ork is necessary to realize a clinically useful system.