Investigating Why Clinicians Deviate from Standards of Care: Liberating Patients from Mechanical Ventilation in the ICU

TL;DR

The paper tackles the persistent gap between evidence-based Wake Up and Breathe guidelines and real-world ICU practice by conducting a qualitative, multi-site field study of nurses and respiratory therapists. It reveals that uncertainty about patient eligibility and interprofessional coordination—not explicit disagreement with the protocol—drives procrastination and missed opportunities for extubation; clinicians prioritize tasks with high certainty under heavy workload. The authors propose design directions for intelligent EHR supports, including automatic eligibility assessment, adaptable guideline execution, and unit-level coordination dashboards, framed within a socio-technical, collaborative workflow approach. The work highlights the need to reframe protocol adherence as team-based coordination and to explore AI-enabled coordination tools that integrate with clinical workflows to improve patient liberation from mechanical ventilation and potentially generalize to other ICU protocols.

Abstract

Clinical practice guidelines, care pathways, and protocols are designed to support evidence-based practices for clinicians; however, their adoption remains a challenge. We set out to investigate why clinicians deviate from the ``Wake Up and Breathe'' protocol, an evidence-based guideline for liberating patients from mechanical ventilation in the intensive care unit (ICU). We conducted over 40 hours of direct observations of live clinical workflows, 17 interviews with frontline care providers, and 4 co-design workshops at three different medical intensive care units. Our findings indicate that unlike prior literature suggests, disagreement with the protocol is not a substantial barrier to adoption. Instead, the uncertainty surrounding the application of the protocol for individual patients leads clinicians to deprioritize adoption in favor of tasks where they have high certainty. Reflecting on these insights, we identify opportunities for technical systems to help clinicians in effectively executing the protocol and discuss future directions for HCI research to support the integration of protocols into clinical practice in complex, team-based healthcare settings.

Figures (1)

• Figure 1: Ideal workflow for Spontaneous Awakening Trial (SAT) and Spontaneous Breathing Trial (SBT) for a single patient (top) and unit-level patients (bottom). Nurses (teal), RTs (orange), physicians and all other clinicians performing patient rounds (purple) are shown as swim lanes. Notice that the RT ideally arrives at each patient's room shortly after the nurse caring for that patient has started the SAT.