Radiology order entry with decision support: initial clinical experience.

PURPOSE To determine whether an appropriately designed computerized order entry system for radiology can be clinically accepted and influence ordering practices. MATERIALS AND METHODS An intranet-based outpatient ordering and scheduling system was designed and implemented beginning in 2001. Indications used to request imaging have been standardized and keystrokes minimized by using menus. The system offers online scheduling and provides patient reminders, preparation instructions, and driving directions. Since November 2004, examination requests have been given utility scores on the basis of the indications provided. Comparative scores for other types of imaging examinations are displayed alongside the scores for the examinations requested. Physicians' performance is tracked, and senior clinicians counsel physicians with many low-scoring examinations. Data collected from the order entry system were used to evaluate rates of use, examinations with low "utility scores," and changes in the scores over the first year of use. RESULTS The use of the order entry system has increased steadily, currently constituting 75% of all potential outpatient studies. Since the addition of decision support in November 2004, almost 72,000 examinations have been scored. The highest number of low utility examinations were imaging of the spine, either computed tomography or magnetic resonance imaging. The percentage of low utility examinations declined from 6% to 2% overall. The amount of the decline was greatest for primary care physicians and for those who interacted with the computer themselves rather than through office staff members. CONCLUSIONS Computerized order entry with decision support can be widely accepted by clinicians and can have an impact on ordering practices.