Context:

In high-acuity nursing environments (e.g., ICU, medical-surgical), the accurate recording of inpatient data is not only an essential component of quality healthcare, but also a physical communication tool among members of a patient’s care team. In hospitals across the U.S., despite the prevalence of charting — i.e., entering short-form patient data into EHRs (electronic health records) — there is ample evidence that nurses rely on other artifacts, typically paper, to collect and recall patient data for charting purposes.

While physicians have successfully adopted speech recognition technology to record patient data through narrative-like dictation (considered “documentation”), the process remains manual for nurses.

Business Goal:

Explore the feasibility of leveraging the client’s technology (DMO, DAX) for inpatient charting.

Research Goals:

• Understand nursing workflows for patient data collection

• Capture and explore their specific goals & motivations

• Identify obstacles that prevent the realization of these goals & motivations

• Propose and lightly validate concepts to help them overcome these obstacles

Methods:

• To assess the current technological and attitudinal landscape, the study protocol began with a literature review of 25 journal articles about nursing workflows and the uses of voice technology in nursing.

• For alignment purposes, 3 client stakeholder interviews helped formulate a 6 research questions, which helped give rise to a moderation guide.

• Recruitment followed suit, relying upon a convenience sample that passed a screener: 10 semi-structured cognitive interviews.

• Using Dovetail, data were coded in several phases using a shared code book. After surfacing early patterns in an initial grounded theory phase, we proceeded to successive rounds of thematic analysis by assigning structural and process codes to all interviews, to which I added elements of interpretative phenomenological analysis with an idiographic focus.

• In-depth analysis was ultimately accomplished by having team members code interviews they neither moderated nor took notes for (for debiasing purposes). The process that yielded more than 100 discrete codes, 800 coding instances, and culminated in 40 core findings.

Findings, Insights, Themes:

With one exception, attitudes ranged from ambivalence, to reticence, to hostility. Accordingly, the primary conclusion is that this was a solution in search of a problem. Reasons and insights fell along several lines:

• Unlike physicians who keep narrative-like records, nurses typically capture short, discrete bursts of information, which are additionally used as memory assists. This population didn’t view speech recognition tech as conducive to charting and note-taking.

• For privacy reasons, participants couldn’t conceive of taking voice notes in front of loved ones, who are oftentimes in the room.

• They negatively viewed the idea that (conscious) patients should be audibly exposed to jargon being spoken into an EHR.

• While working in EHRs may still leave something to be desired — they have their own workflow issues — the prevailing attitude was: “Better the devil you know.” And while paper notes have minor shortcomings, such notes remain workable solutions. Moreover, paper notes are effortlessly passed between nurses during shift changes and don’t suffer from glitches or WiFi issues. Most fundamentally, these notes are deeply ingrained behavioral habits not be easily abandoned, and voice tech was largely considered yet another digital tool to interfere with nurse-patient interaction.

• Interestingly, a minor finding worth reporting was a lack of concern surrounding the quality of speech recognition.

Impact, Business Outcomes:

Nuance abandoned this line of inquiry after triangulating these results with existing research, which held similar findings. With independent studies validating each other, the inquiry’s removal from the roadmap ultimately saved the client further financial and staffing resources by avoiding investment in an area that, at present, demonstrates signs of being largely unreceptive to this technology.

Next Steps, Opportunities, Recommendations:

Despite the above results, speech recognition technology is more than just voice dictation. Final recommendations regarding its use in this context:

• Investigate the potential intersection of speech recognition technology with communication devices already used in these settings, if not for charting, then at least for note taking.

• Investigate potential correlations surfaced through the participant spectrum map (Diagram 2). Nurses who work at hospitals that require structured, templated note-taking also reported that charting has a “very high impact” on work-life balance (due to EHR workflow issues).

• Identify clinics that do not allow paper into the patient’s room due to COVID-19. If this practice is enforced in more inpatient settings than what our convenience sample found, it could be an opportunity at least for voice-enabled note taking.

• Continue exploring ways to replace paper as a stopgap solution for quickly adding highly structured information to an EHR system. Utilize a participatory design method like a charrette with nurse participants, which would serve well.

• Continue this line of inquiry with the next generation of nurses, as there are some signals that that youngest practitioners were at least more receptive to this tech.

Limitations:

• Observation and interviews in situ would have been ideal. This likely would’ve been possible in a pre-COVID world. Regrettably, it wasn’t an option at the time of this study.

• Recruitment fell a bit short of the minimum 12 participants desired. (Why 12? See here and here if you’re really, really interested.)

  • Patient technicians, who also play a role in high-acuity patient care, would have been welcome. But recruitment limitations unfortunately did not allow for this.

• Coding and analysis took longer than expected, which led to a deviation from the protocol’s final step: a charrette with nurses. However, there was time to involve client stakeholders in a blue-sky ideation activity, which yielded welcome out-of-the-box solutions.

Retrospective:

• What did I learn?

  • An abundance of methodological skills applied to a critical subject area.

  • There are signs that nursing attitudes will eventually, albeit slowly, evolve. While it’s currently a slow-moving train, I’m curious to see how that changes as NLP and AI catch fire in new ways each year.

• What would I have done differently?

  • Aside from sticking to a better sleep schedule, for a change I honestly can’t think of anything I would’ve done differently.

• What went well? What will I keep doing?

  • The client was deeply engaged at every turn.

  • Keep my cool, and my nose to the grindstone. A demanding schedule tried collective patience, but it was sink or swim and the focus was to stay afloat.

  • To that end, team cohesion, candor, and engagement were paramount to success, a unity that resulted in psychological safety, a good deal of productivity, and interpersonal satisfaction. All primary objectives were meaningfully met, including final client presentations and documentation handoff.