The association between use of ambient voice technology documentation during primary care patient encounters, documentation burden, and provider burnout

Abstract Background The burden of documentation in the electronic medical record has been cited as a major factor in provider burnout. The aim of this study was to evaluate the association between ambient voice technology, coupled with natural language processing and artificial intelligence (DAX™), on primary care provider documentation burden and burnout. Methods An observational study of 110 primary care providers within a community teaching health system. The primary objectives were to determine the association between DAX™ usage and provider burnout scores on the Oldenburg Burnout Inventory (OLBI) as well as the effect on documentation time per patient encounter (minutes). Results The completion rate for the survey was 75% (83/110) and high DAX™ use (60% of encounters) was seen in 28% of providers (23/83). High DAX™ use was associated with significantly less burnout on the OLBI disengagement sub-score (MD Mean Difference −2.1; 95% confidence interval CI −3.8 to −0.4) but not the OLBI disengagement sub-score (−1.0; 95% CI −2.9 to 1.0) or total score (MD −3.0; 95% CI −6.4 to 0.3). Nineteen providers with high implementation of DAX™ had pre and postimplementation data on documentation time per encounter. After DAX™ implementation average documentation time in notes per encounter was significantly reduced by 28.8% (1.8 min; 95% CI 1.4–2.2). Conclusions The use of ambient voice technology during patient encounters was associated with significantly reduced documentation burden and primary care provider disengagement but not total provider burnout scores.