Effect of a practice-based strategy on test ordering performance of primary care physicians: a randomized trial

Abstract

Context: Numbers of diagnostic tests ordered by primary care physicians are growing and many of these tests seem to be unnecessary according to established, evidence-based guidelines. An innovative strategy that focused on clinical problems and associated tests was developed.

Objective: To determine the effects of a multifaceted strategy aimed at improving the performance of primary care physicians' test ordering.

Design: Multicenter, randomized controlled trial with a balanced, incomplete block design and randomization at group level. Thirteen groups of primary care physicians underwent the strategy for 3 clinical problems (arm A; cardiovascular topics, upper and lower abdominal complaints), while 13 other groups underwent the strategy for 3 other clinical problems (arm B; chronic obstructive pulmonary disease and asthma, general complaints, degenerative joint complaints). Each arm acted as a control for the other.

Setting: Primary care physician groups in 5 regions in the Netherlands with diagnostic centers recruited from May to September 1998.

Study participants: Twenty-six primary care physician groups, including 174 primary care physicians.

Intervention: During the 6 months of intervention, physicians discussed 3 consecutive, personal feedback reports in 3 small group meetings, related them to 3 evidence-based clinical guidelines, and made plans for change.

Main outcome measure: According to existing national, evidence-based guidelines, a decrease in the total numbers of tests ordered per clinical problem, and of some defined inappropriate tests, is considered a quality improvement.

Results: For clinical problems allocated to arm A, the mean total number of requested tests per 6 months per physician was reduced from baseline to follow-up by 12% among physicians in the arm A intervention, but was unchanged in the arm B control, with a mean reduction of 67 more tests per physician per 6 months in arm A than in arm B (P =.01). For clinical problems allocated to arm B, the mean total number of requested tests per 6 months per physician was reduced from baseline to follow-up by 8% among physicians in the arm B intervention, and by 3% in the arm A control, with a mean reduction of 28 more tests per physician per 6 months in arm B than in arm A (P =.22). Physicians in arm A had a significant reduction in mean total number of inappropriate tests ordered for problems allocated to arm A, whereas the reduction in inappropriate test ordered physicians in arm B for problems allocated to arm B was not statistically significant.

Conclusion: In this study, a practice-based, multifaceted strategy using guidelines, feedback, and social interaction resulted in modest improvements in test ordering by primary care physicians.