Faculty Bibliography

Virtual urgent care (VUC) has become an increasingly utilized resource for acute care delivery. Frequent utilization of VUC may reflect unmet longitudinal care needs and contribute to fragmented care. While high-utilizer patterns are well described in emergency departments, they have not been systematically characterized in telemedicine. We evaluated a clinical decision support (CDS) nudge designed to identify and address high utilizers of VUC at a large academic health system. An electronic health record alert triggered when patients met predefined high-utilizer criteria (>3 visits in 30 days, >12 in six months, or >20 in 12 months) and prompted providers to document a structured follow-up plan using a SmartPhrase. Among 473 eligible patients, 162 (34%) received the SmartPhrase. After adjustment for baseline utilization using negative binomial regression, SmartPhrase use was associated with a 22% relative reduction in VUC visits over the subsequent 30 days (incidence rate ratio 0.78, p = .03). Bootstrapped analyses confirmed a significant reduction in the SmartPhrase group (-1.47 visits; 95% CI [-2.19 to -0.62]), while no significant change occurred in the comparison group. These findings suggest that a low-cost, workflow-integrated CDS nudge may reduce short-term telehealth overutilization by prompting structured follow-up discussions and encouraging longitudinal care planning.

STUDY OBJECTIVES/OBJECTIVE:Clinical demands in the emergency department (ED) may contribute to decision and attention fatigue as clinician time-on-shift increases, impacting patient care. Emergency department pharmacists review orders and intervene to correct problems related to safety and appropriateness. This study's objective was to evaluate and characterize the rate of pharmacist interventions on ED medication orders. We hypothesized that pharmacist interventions would increase with clinician time-on-shift. METHODS:We performed a retrospective study of 2 EDs within a single health system between January 2022 and November 2023. Medication and pharmacy intervention details were extracted and linked to clinician schedules, pharmacist schedules, and ED crowding scores. Mixed-effects logistic regression modeling identified factors associated with pharmacist interventions. RESULTS:Pharmacists intervened on 9,054 (1.5%) of 622,171 medication orders placed by 308 clinicians. Pharmacy intervention rate increased with clinician time-on-shift (odds ratio 1.04 for each hour; 95% confidence interval 1.03 to 1.05), with meaningful variation in this effect between individual clinicians. Stratified by clinician type (attendings, residents, or physician assistants) and shift timing (overnight versus daytime shifts), the association between time-on-shift and pharmacy intervention rate remained positive. Stratified by site (A versus B), the association was positive at site A but not at site B. CONCLUSION/CONCLUSIONS:The likelihood of orders requiring pharmacist interventions increased as ED clinicians' time-on-shift increased. This association was consistently observed across differing clinician types and shift timing, but variable across the 2 sites of the study. Clinical staffing models and quality of care could be improved by addressing stressors and fatigue accumulation informed by this analytical model.

OBJECTIVES/OBJECTIVE:Fentanyl test strips (FTS) have the potential to moderate drug use behavior amidst an unregulated drug supply, yet are underutilized in medical settings. We aimed to describe emergency department (ED) FTS distribution across a large NYC health system and examine characteristics associated with clinicians' ordering FTS compared with the current standard-of-care, take-home naloxone (THN), to identify opportunities to optimize FTS distribution. METHODS:We conducted a retrospective review of THN and FTS provision across a large urban health system in its first year of FTS distribution. We evaluated the demographic and clinical characteristics of visits in which clinicians ordered FTS, compared with THN only. RESULTS:From July 20, 2022 to July 20, 2023, 237 (of 423) clinicians ordered THN for 1279 unique individuals in 1376 eligible visits (436 with FTS, 940 without). In pairwise analysis, FTS receipt was associated with being male, younger, non-White, lacking commercial insurance; substance-related or overdose-related visit chief complaint or diagnosis, attending physician, and patient-directed discharge ( P <0.05 for each). In multivariable regression, higher odds of FTS receipt were associated with male gender (OR=2.4; 95% CI=1.8-3.5), a substance-related chief complaint (OR=2.0; 95% CI=1.2-3.2) or visit diagnosis (OR=5.5; 95% CI=3.8-8.0), and overdose visit diagnosis (OR=1.7; 95% CI=1.1-2.8). Lower odds of FTS receipt were associated with older age (OR=0.98; 95% CI=0.97-0.99), noncommunity hospital sites (OR=0.71; 95% CI=0.60-0.83), and non-attending clinicians (OR=0.83; 95% CI=0.69-0.98). CONCLUSIONS:Integrating FTS into an existing ED THN program was feasible without disrupting clinical workflow. ED encounters where FTS were dispensed differed significantly from THN-only, revealing opportunities to optimize FTS ordering.

PROBLEM/OBJECTIVE:Graduate medical education requires learners to acquire broad clinical exposures to meet core competencies for unsupervised practice, but variability in clinical learning environments and reliance on resource-intensive assessments hinder precise assessment of trainees' clinical experiences. Electronic health records hold promise for precision medical education, yet manual mapping of International Classification of Diseases, Tenth Revision (ICD-10) codes to specialty-specific clinical practice domains limits scalability. APPROACH/METHODS:The authors leveraged electronic health record data and artificial intelligence (AI) to map residents' encounter diagnoses to the American Board of Emergency Medicine's Model of the Clinical Practice of Emergency Medicine (MCPEM). Resident encounters across 3 sites at a single academic system (January 1 to October 31, 2023) were analyzed with an AI model, mapped to MCPEM categories with ICD-10 descriptors, and quantified with vectors to match to the closest MCPEM category. Faculty raters validated the most common mappings iteratively, which were subsequently integrated into interactive learner dashboards. OUTCOMES/RESULTS:Among 119,320 encounters, 5,960 unique ICD-10 descriptors (1,126 stem codes) were identified. For the 650 most common diagnoses, 507 (78.0%) of emergency department diagnosis text descriptors were determined as valid mappings to an MCPEM subcategory. In mappings where faculty were discordant with the lowest distance mapping, 171 of 305 alternative subcategory mappings (56.0%) achieved agreement, increasing the concordance between reviewers to 515 of 650 (79.2%) overall. Interactive dashboards displayed resident-level case mix mapped to MCPEM categories, with anonymized peer comparisons and program-level aggregates, enabling identification of patterns and gaps by domain. NEXT STEPS/CONCLUSIONS:Planned work includes iterating AI-automated mappings by expanding inputs beyond diagnoses, engaging wider stakeholder review of mapping validations, and assessing generalizability to other specialties' content outlines to produce a scalable and reproducible model to increase the precision of feedback loops to inform graduate medical education, the clinical learning environment, and training design.

BACKGROUND:Clinical Informatics (CI) fellowship training equips physicians with the skills to design, implement, and evaluate health information systems in support of patient care. While core curricula emphasize academic health system experiences, fellows may have limited exposure to industry settings where much innovation originates. Away electives with vendors, startups, payers, or standards bodies offer unique opportunities to expand perspectives, but little is known about how such rotations are structured, supported, or valued. OBJECTIVES/OBJECTIVE:To characterize the structure, perceived value, and logistical challenges of industry electives among CI fellowship programs, and to synthesize best practices for integrating these experiences into training. METHODS:We surveyed current and former CI fellows and their program directors from two ACGME-accredited programs between September 2024 and March 2025. Fellows were required to complete at least four weeks of an industry elective. Free-text responses were analyzed using inductive thematic analysis, and a consensus-driven process was used to generate practical considerations for program design. RESULTS:Seven fellows reported on industry electives at non-health-center sites such as startups, vendors, and standards bodies. Their responses revealed four themes: (1) enhanced skill development and exposure to technologies and workflows not available in academic settings; (2) logistical barriers, including limited institutional support, short duration, and complex legal agreements; (3) tangible deliverables such as dashboards, analytic tools, abstracts, and grants; and (4) professional networking that often shaped career trajectories, with some fellows receiving job offers. Practical considerations included identifying partner sites, designating supervisors, negotiating agreements early, defining objectives and deliverables, and addressing financial and logistical support. CONCLUSION/CONCLUSIONS:Industry electives provide career-shaping experiences for CI fellows, expanding exposure to innovation and fostering collaboration between academia and industry. With clear objectives, aligned competencies, and institutional support, these rotations can strengthen training and prepare fellows for diverse roles across healthcare and technology.

OBJECTIVES/UNASSIGNED:To propose a structured framework for evaluating and comparing clinical informatics fellowship programs using the People, Process, and Technology (PPT) model. MATERIALS AND METHODS/UNASSIGNED:We adapted Leavitt's organizational theory to create a three-pillar framework operationalized with features relevant to fellowship applicants and directors. We then applied this framework to a random sample of 18 program websites. RESULTS/UNASSIGNED:The PPT framework categorizes key fellowship characteristics into People (eg, mentorship, co-fellows, diversity), Process (eg, clinical duties, research emphasis, education), and Technology (eg, EHR systems, technical training, remote work). A visual grid illustrates variation in operational versus research focus and levels of mentorship. Website analysis revealed inconsistent transparency and detail. DISCUSSION/UNASSIGNED:The PPT framework provides a systematic, accessible approach for applicants to assess fellowship fit and for programs to communicate their strengths. CONCLUSION/UNASSIGNED:Standardizing fellowship descriptions using the PPT model may improve alignment between applicant goals and program offerings, enhancing both the application process and training experience.

As artificial intelligence tools become increasingly integrated into emergency department workflows, healthcare providers face a growing risk of legal liability stemming from improper use, particularly with respect to data privacy and Health Insurance Portability and Accountability Act (HIPAA) compliance. This article explores a realistic clinical scenario in which an emergency physician inadvertently violates HIPAA using a publicly available AI tool, such as ChatGPT, Gemini, Llama, and Grok, without a valid Business Associate Agreement in place. We review the legal framework of the HIPAA Privacy, Security, and Breach Notification Rules and delineate the respective liabilities of healthcare institutions and individual clinicians. Key distinctions are made between incidental, accidental, and unauthorized disclosures of protected health information, and we provide clear guidance on post-breach mitigation steps. The article also discusses the statistical likelihood of protected health information reidentification or reproduction by AI models and outlines risks associated with state-level data protection laws. Ultimately, we offer practical recommendations for physicians seeking to leverage AI responsibly in clinical care, including verifying institutional Business Associate Agreements, understanding platform-specific privacy policies, and consulting with privacy officers before entering any patient data. As AI rapidly evolves, clinicians must remain vigilant in safeguarding patient information to avoid legal exposure and uphold ethical standards of care.

Artificial intelligence (AI) tools and technologies are increasingly being integrated into emergency medicine (EM) practice, not only offering potential benefits such as improved efficiency, better patient experience, and increased safety, but also resulting in potential risks including exacerbation of biases. These biases, inadvertently embedded in AI algorithms or training data, can adversely affect clinical decision making for diverse patient populations. Bias is a universal human attribute, subject to introduction into any human interaction. The risk with AI is magnification of, or even normalization of, patterns of biases across the health care ecosystem within tools that in time may be considered authoritative. This article, the work of members of the American College of Emergency Physicians (ACEP) AI Task Force, aims to equip emergency physicians (EPs) with a practical framework for understanding, identifying, and addressing bias in clinical and operational AI tools encountered in the emergency department (ED). For this publication, we have defined bias as a systematic flaw in a decision-making process that results in unfair or unintended outcomes that can be inadvertently embedded in AI algorithms or training data. This can result in adverse effects on clinical decision making for diverse patient populations. We begin by reviewing common sources of AI bias relevant to EM, including data, algorithmic, measurement, and human-interaction factors, and then, we discuss the potential pitfalls. Following this, we use illustrative examples from EM practice (eg, triage tools, risk stratification, and medical devices) to demonstrate how bias can manifest. We subsequently discuss the evolving regulatory landscape, structured assessment frameworks (including predeployment, continuous monitoring, and postdeployment steps), key principles (like sociotechnical perspectives and stakeholder engagement), and specific tools. Finally, this review outlines the EP's vital role in mitigation of AI-related biases through advocacy, local validation, clinical feedback, demanding transparency, and maintaining clinical judgment over automation.

OBJECTIVES/UNASSIGNED:This study aimed to assess the current utilization of artificial intelligence (AI) tools among emergency physicians, their attitudes toward AI in clinical practice, and how a national physician professional organization could best support its members regarding AI. METHODS/UNASSIGNED:A cross-sectional survey was emailed to American College of Emergency Physicians members and made available to conference attendees at a national symposium. The survey collected demographic information, details on the use of noninstitutional and institutional AI tools, attitudes toward AI, and desired forms of support. Descriptive statistics were used to summarize the data. RESULTS/UNASSIGNED:A total of 658 physicians responded, primarily practicing attendings (78%) and residents (9%), with 60% aged 35 to 54 years and 67% identifying as male; these respondents represented 2% of the membership of American College of Emergency Physicians. Noninstitutional AI tool use (eg, ChatGPT and independent electrocardiogram interpretation) was reported by 31% of respondents. Institutional AI was integrated into 52% of respondents' practices, with 18% regularly using ambient AI documentation and 22% using AI-assisted clinical decision support. AI tools for point-of-care ultrasound were available to 10%, and AI-assisted radiology interpretation was used by 14%, mainly for X-rays and computed tomography. Operational AI for triage, capacity management, and staff optimization were reported by 15%, while 9% used AI-assisted coding and billing. Moreover, 75% believed AI improves clinical efficiency, 57% felt it enhanced care quality, but 12% expressed concern about job displacement, 16% are unsure whether AI tools would adequately comply with Health Insurance Portability and Accountability Act regulations, and 38% noted potential biases. About half desire educational support and guidelines. CONCLUSION/UNASSIGNED:In this nonrepresentative emergency physician survey, respondents reported moderate rates of adoption of AI tools and generally positive attitudes toward AI's impact on efficiency and care quality. However, respondents also reported important concerns about job displacement, Health Insurance Portability and Accountability Act regulation compliance, and potential biases. Larger studies are needed to more fully understand emergency physician views on AI.