Needs and expectations for artificial intelligence in emergency medicine according to Canadian physicians
Abstract
Background: Artificial Intelligence (AI) is recognized by emergency physicians (EPs) as an important technology that will affect clinical practice. Several AI-tools have already been developed to aid care delivery in emergency medicine (EM). However, many EM tools appear to have been developed without a cross-disciplinary needs assessment, making it difficult to understand their broader importance to general-practice. Clinician surveys about AI tools have been conducted within other medical specialties to help guide future design. This study aims to understand the needs of Canadian EPs for the apt use of AI-based tools. Methods: A national cross-sectional, two-stage, mixed-method electronic survey of Canadian EPs was conducted from January-May 2022. The survey includes demographic and physician practice-pattern data, clinicians' current use and perceptions of AI, and individual rankings of which EM work-activities most benefit from AI. Results: The primary outcome is a ranked list of high-priority AI-tools for EM that physicians want translated into general use within the next 10 years. When ranking specific AI examples, 'automated charting/report generation', 'clinical prediction rules' and 'monitoring vitals with early-warning detection' were the top items. When ranking by physician work-activities, 'AI-tools for documentation', 'AI-tools for computer use' and 'AI-tools for triaging patients' were the top items. For secondary outcomes, EPs indicated AI was 'likely' (43.1%) or 'extremely likely' (43.7%) to be able to complete the task of 'documentation' and indicated either 'a-great-deal' (32.8%) or 'quite-a-bit' (39.7%) of potential for AI in EM. Further, EPs were either 'strongly' (48.5%) or 'somewhat' (39.8%) interested in AI for EM. Conclusions: Physician input on the design of AI is essential to ensure the uptake of this technology. Translation of AI-tools to facilitate documentation is considered a high-priority, and respondents had high confidence that AI could facilitate this task. This study will guide future directions regarding the use of AI for EM and help direct efforts to address prevailing technology-translation barriers such as access to high-quality application-specific data and developing reporting guidelines for specific AI-applications. With a prioritized list of high-need AI applications, decision-makers can develop focused strategies to address these larger obstacles.
Clinical implications
National cross-sectional survey of Canadian emergency physicians (n=230 enrolled, 171 completed all questions) conducted January-May 2022 to identify high-priority AI applications for emergency medicine. Sample represented 5.65% of Canadian EPs practicing in 2019. Primary findings: Automated charting/report generation ranked #1 specific AI tool priority. AI-tools for documentation ranked #1 by work-activity category, followed by AI-tools for computer use and triaging patients. Secondary outcomes showed high confidence in AI capabilities: 86.8% of EPs indicated AI was 'likely' (43.1%) or 'extremely likely' (43.7%) to complete documentation tasks successfully. Strong interest in AI: 88.3% were 'strongly' (48.5%) or 'somewhat' (39.8%) interested in AI for emergency medicine. High potential perceived: 72.5% indicated 'a great deal' (32.8%) or 'quite a bit' (39.7%) of potential for AI in EM. Impact expectations: 60.6% believe jobs will change slightly, 35.9% believe substantially due to AI over next 10 years. AI capability beliefs: Most likely tasks for AI were 'provide documentation' and 'formulate personalized medication/therapy plans'. Physicians neutral on AI's ability to analyze patient info for diagnosis, reach prognosis, formulate treatment plans, or evaluate specialist referrals. Strong consensus that AI 'extremely unlikely' (45.4%) or 'unlikely' (36.2%) to provide empathetic care. Current AI usage: Most common ED work-activities where EPs used AI: computer use tools (29.1%), documentation tools (20.1%), administration/education/research (16.9%). Most commonly heard of but not used: AI-powered X-ray interpretation (64.0%), CT (60.9%), MRI (55.8%), ultrasound (54.3%). Study emphasizes need for user-centered design and physician input in AI development. Documentation burden clearly identified as high-priority target for AI intervention.