Computer-based clinical decision support systems (CDSSs) have been championed for their potential to improve health-care quality. However, there has been no systematic study of the types of CDSSs that have been developed. In previous work, we developed the CDSS Taxonomy for comprehensively describing the technical, workflow, and contextual characteristics of CDSSs. We now use the CDSS Taxonomy to describe outpatient CDSSs evaluated in randomized controlled trials published between 1998 and 2002. 31 studies comprising 42 CDSS systems were included in our analysis. The majority of systems used rule-based reasoning engines to "push" explicit, individualized recommendations concerning non-urgent decisions to clinicians or patients, but not both. 71% of the systems required someone to manually enter data into the system or to process the system output for use by the target decision maker. The average kappa for coding agreement was > 0.6. Our findings demonstrate that outpatient CDSSs vary greatly in design and function. Many impose a data entry or output-processing burden on clinic staff. More complete reporting of CDSS characteristics is needed in the literature.