News: Human scribes still document better than digital scribes, study says

Speech-to-text transcription solutions have been touted as a way to reduce physician documentation burdens, but a study published in the Journal of Informatics in Health and Biomedicine suggests that such systems are not a complete replacement for human scribes.

The study initially aimed to develop an understanding of the work performed by medical scribes “in order to inform the design of such [speech-based] technologies” capable of automatically generating clinical documentation based on patient-provider conversation. The results found a significant variation in scribe expectations and responsibilities across healthcare organizations.

While digital scribes would be unable to do so, human scribes often adapt their work based on the provider’s style and preferences. The study notes that human scribes’ jobs extend “far beyond capturing conversation in the exam room; they also actively interact with patients and the care team and integrate data from other sources such as prior charts and lab test results.”

A one-size-fits-all solution will be “unlikely to work because of the significant variation in scribe work,” the study notes. It also suggests that technology designers need to be aware of the limited role that their solution can fulfill. While electronic scribes can capture information, they are not capable of critical thinking the way a human scribe would be. Plus, human scribes often interact person-to-person with other teams and pull data from other reports and tests.

“To product comprehensive clinical documentation, such technologies will likely have to incorporate information beyond the exam room conversation,” the study says.

The study also notes that issues of patient consent and privacy have yet to be adequately addressed, “which could become paramount barriers to implementing such technologies in realistic clinical settings.”

Because medical scribes perform such complex work, researchers say that further study is needed to better understand their roles in a clinical setting before being able to create adequate speech-based clinical documentation technologies.

Editor’s note: The study abstract can be found here. To read a CDI Journal article about leveraging artificial intelligence solutions for CDI work, click here.