Computer systems can help radiologists decide which tests to perform a
nd which diagnoses to consider. Repositories of clinical data and gene
ral medical knowledge can provide information on demand for decisionma
king tasks; many of these information resources are available remotely
via the Internet. Decision support systems can incorporate the techni
ques of artificial intelligence to apply their general knowledge to th
e features of a particular patient. Successful use of these technologi
es requires careful attention to design, implementation, and rigorous
evaluation. Computer-based decision aids can improve the cost effectiv
eness and diagnostic accuracy of radiologic practice and are poised to
play an important role in the future of radiology.