Role of a Digital Clinical Decision-Support System in General Practitioners' Management of COPD in Norway.

Background: The study investigated if a web-based clinical decision-support system (CDSS) tool would improve general practitioners' (GPs) accuracy of diagnosis and classification of patients with chronic obstructive pulmonary disease (COPD), and whether nonpharmacological and pharmacological treatment would be better aligned with the COPD guidelines. Methods: GPs were randomized to either a single use of the CDSS or continuing standard of care. The clinical recommendations of the CDSS were based on the GOLD guidelines and provided suggestions for treatment and management of COPD. Data were collected digitally from GPs and patients in both groups using a tablet computer. A follow-up questionnaire was sent to the GPs 1 year after the conclusion of the study. Results: A total of 25 GPs (31% women, mean age 41 years) participated, 12 randomized to using the CDSS tool and 13 followed standard of care when assessing their next five to ten COPD patients. In sum, 149 patients with presumed COPD were included (88 CDSS group, 61 standard-of-care group). In the CDSS group, no COPD misdiagnoses occurred, 98% received vaccine recommendations, and all smokers (n=39) received smoking-cessation advice. The standard-of-care group had 23% misdiagnosis (P<0.001), only 67% received vaccine recommendations (P<0.001), and 87% smoking-cessation advice (P=0.022. All told, 31% of patients did not receive medication as recommended according to guidelines, with no significant differences between the groups. GPs rated the CDSS as very useful. Mean usage time was 3 minutes, 26 seconds. A majority (13 of 19, 68%) of the GPs continued using the CDSS after the conclusion of the study. CAT score identified twice as many patients as having more symptoms than the mMRC, indicating the added value of the multi-item questionnaire. Conclusion: Use of the CDSS was associated with preventing misdiagnosis of COPD and improved adherence to recommended nonpharmacological measures, but a single use did not improve pharmacological treatment considerations.