JMIR Publications

ABSTRACT

Background:

Artificial intelligence (AI) has the potential to enhance clinical decision-making in high-acuity settings such as intensive care units (ICUs) and emergency departments (EDs). However, despite promising performance, many AI-driven clinical decision support systems (AI-CDSS) face poor adoption due to issues of trust, workflow disruption, and alert fatigue. Understanding the human factors that shape clinician acceptance is critical to guide safe and effective implementation of AI-CDSS in acute care. Theoretical frameworks including the Systems Engineering Initiative for Patient Safety (SEIPS) 2.0 model and the Technology Acceptance Model (TAM) suggest that successful adoption requires addressing sociotechnical interactions among clinician trust, system design, organizational readiness, and task complexity, yet few empirical studies have applied these frameworks to AI-CDSS in acute care settings.

Objective:

This study aimed to evaluate emergency medicine and critical care clinicians’ perceptions of AI-CDSS and to identify key factors influencing adoption, including trust, design preferences, and workflow integration.

Methods:

A SEIPS 2.0 informed mixed-methods study evaluated ICU and ED clinicians from Emory Healthcare on perceptions of AI in clinical practice. An expert-reviewed survey (N=57) assessed clinician perceptions, trust, and implementation preferences. Semi-structured interviews (N=11) included A/B testing of AI-CDSS and clinical sepsis scenario to explore decision-making in context. Transcripts were thematically analyzed using Braun and Clarke's framework in ATLAS.ti. Quantitative data were analyzed descriptively.

Results:

Trust in AI varied significantly by patient acuity (Cochran's Q=30.40, p<0.0001): stable patients (75.4%, 95% CI: 62.9-84.8%), deteriorating patients (47.4%, 95% CI: 35.0-60.1%), and ICU/ED patients (43.9%, 95% CI: 31.8-56.7%). Internal consistency was acceptable-to-good across three scales (Cronbach's alpha: AI Perception=0.891, Trust=0.743, Implementation=0.740). Barriers included over-reliance, insufficient training, and data quality concerns. For the CDSS-AI design, clinicians preferred opt-in alerts (90%), evidence-linked recommendations (63%), and avoiding overt mention of AI increased acceptance (73%). Thematic analysis yielded 36 themes across six domains: trust and transparency, alert usability, workflow fit, data concerns, training needs, and perceived clinical impact. Clinicians favored AI-CDSS that preserved autonomy, minimized disruption, and provided transparent rationale.

Conclusions:

Adoption of AI-CDSS in critical care is not solely a technical issue, but a human-factors challenge centered on trust, transparency, and workflow compatibility. Applying the SEIPS 2.0 framework, we propose a phased implementation approach: beginning with lower-acuity applications where clinician trust is highest, then gradually extending to higher-acuity scenarios with enhanced transparency and override mechanisms. This graduated strategy addresses the critical interdependencies among people (trust), tools (design), organization (training), and task (clinical complexity) identified in this study.