ABSTRACT
OBJECTIVE: To establish an expert system that automatically generates optimal GDC selection program for the embolization of intracranial aneurysm. METHODS: Twenty highly cost-effective cases of intracranial aneurysm embolized with GDC dense packing were collected. Each of them contains information including aneurysm's volume measured by three-dimension digital subtraction angiography (3D DSA), aneurysm's location, maximum transverse diameter, maximum length diameter, and GDC selection program. An expert system made up of a case base, a mathematical model simulating experts' experience (established with the help of data mining techniques combining multi-layer perceptron network with polyhedrons in high dimensional space), and data envelopment analysis (DEA), was implemented. RESULTS: When the user inputted four required parameters (volume, location, maximum transverse diameter, and maximum length diameter) into the expert system and clicked the "program design" button, candidate GDC selection program(s) would be presented in the result box. CONCLUSION: Case base, data mining techniques, and DEA can be used to establish the expert system that automatically generates optimal GDC selection program for the embolization of intracranial aneurysm. Its clinical value needs to be further evaluated.
