Rohit B. Sangal’s research while affiliated with Yale-New Haven Hospital and other places

Diagnostic errors in health care pose significant risks to patient safety and are disturbingly common. In the emergency department (ED), the chaotic and high‐pressure environment increases the likelihood of these errors, as emergency clinicians must make rapid decisions with limited information, often under cognitive overload. Artificial intelligence (AI) offers promising solutions to improve diagnostic errors in three key areas: information gathering, clinical decision support (CDS), and feedback through quality improvement. AI can streamline the information‐gathering process by automating data retrieval, reducing cognitive load, and providing clinicians with essential patient details quickly. AI‐driven CDS systems enhance diagnostic decision making by offering real‐time insights, reducing cognitive biases, and prioritizing differential diagnoses. Furthermore, AI‐powered feedback loops can facilitate continuous learning and refinement of diagnostic processes by providing targeted education and outcome feedback to clinicians. By integrating AI into these areas, the potential for reducing diagnostic errors and improving patient safety in the ED is substantial. However, successfully implementing AI in the ED is challenging and complex. Developing, validating, and implementing AI as a safe, human‐centered ED tool requires thoughtful design and meticulous attention to ethical and practical considerations. Clinicians and patients must be integrated as key stakeholders across these processes. Ultimately, AI should be seen as a tool that assists clinicians by supporting better, faster decisions and thus enhances patient outcomes.

Background Challenging clinical environments faced by emergency departments (EDs) have led to operational changes including implementation of vertical care units and fast‐track units. Little is known regarding the impact of such units on resident physician clinical education. Methods A retrospective, observational study was performed at an urban quaternary care ED evaluating the effect of opening a vertical care unit with a triage physician directing lower acuity patients to be seen by physician associates (PAs)/advanced practice registered nurses (APRNs) on the following parameters: (1) percentage of patients seen by residents, (2) Emergency Severity Index (ESI) of patients seen by residents, (3) number of procedures performed by residents, (4) number of patients per shift seen by residents, (5) percentage of critical care patients seen by residents, and (6) percentage of behavioral health patients seen by residents. Results Comparing the implementation of the vertical care unit to the prior 3 months, postgraduate year (PGY)‐1 residents had greater exposure to ESI Levels 1 and 2 (odds ratio [OR] 2.15) and more critical care (OR 2.58). PGY‐2 and PGY‐3 residents had a lower exposure to ESI 1 and 2 patients (PGY‐2 OR 0.63, PGY‐3 OR 0.61) and less critical care exposure (OR 0.64 for PGY‐2 and OR 0.62 for PGY‐3) after implementation. PGY‐1 residents saw fewer behavioral health patients (OR 0.65) while the other two classes saw more (PGY‐2 OR 1.64, PGY‐3 OR 2.74). ESI 4 and 5 exposure decreased for all classes (PGY‐1 OR 0.15, PGY‐2 OR 0.86, PGY‐3 OR 0.72). No significant difference was found in the proportion of patients treated by residents ( p = 0.85) or the number of procedures performed by residents ( p = 0.25) comparing the implementation of a vertical care unit to the prior 3 months. Conclusions This study suggests no detrimental effects of vertical care unit implementation on multiple resident education outcomes including the number and acuity level of patients seen as well as procedure numbers of resident trainees. While the outcomes measured did not show significant negative effect for the resident compliment as a whole, we noted changes to the distribution of patient acuity based on PGY level. Similar assessments are recommended to determine the educational impact of comparable operational changes in other EDs.

Burnout and workforce attrition present pressing global challenges in healthcare, severely impacting the quality of patient care and the sustainability of health systems worldwide. Artificial intelligence (AI) has immense potential to reduce the administrative and cognitive burdens that contribute to burnout through innovative solutions such as digital scribes, automated billing and advanced data management systems. However, these innovations also carry significant risks, including potential job displacement, increased complexity of medical information and cases, and the danger of diminishing clinical skills. To fully leverage AI’s potential in healthcare, it is essential to prioritise AI technologies that align with stakeholder values and emphasise efforts to re-humanise medical practice. By doing so, AI can contribute to restoring a sense of purpose, fulfilment and efficacy among healthcare workers, reinforcing their essential role as caregivers, rather than distancing them from these core professional attributes.

Background Discharge instructions are a key form of documentation and patient communication in the time of transition from the emergency department (ED) to home. Discharge instructions are time-consuming and often underprioritized, especially in the ED, leading to discharge delays and possibly impersonal patient instructions. Generative artificial intelligence and large language models (LLMs) offer promising methods of creating high-quality and personalized discharge instructions; however, there exists a gap in understanding patient perspectives of LLM-generated discharge instructions. Objective We aimed to assess the use of LLMs such as ChatGPT in synthesizing accurate and patient-accessible discharge instructions in the ED. Methods We synthesized 5 unique, fictional ED encounters to emulate real ED encounters that included a diverse set of clinician history, physical notes, and nursing notes. These were passed to GPT-4 in Azure OpenAI Service (Microsoft) to generate LLM-generated discharge instructions. Standard discharge instructions were also generated for each of the 5 unique ED encounters. All GPT-generated and standard discharge instructions were then formatted into standardized after-visit summary documents. These after-visit summaries containing either GPT-generated or standard discharge instructions were randomly and blindly administered to Amazon MTurk respondents representing patient populations through Amazon MTurk Survey Distribution. Discharge instructions were assessed based on metrics of interpretability of significance, understandability, and satisfaction. Results Our findings revealed that survey respondents’ perspectives regarding GPT-generated and standard discharge instructions were significantly (P=.01) more favorable toward GPT-generated return precautions, and all other sections were considered noninferior to standard discharge instructions. Of the 156 survey respondents, GPT-generated discharge instructions were assigned favorable ratings, “agree” and “strongly agree,” more frequently along the metric of interpretability of significance in discharge instruction subsections regarding diagnosis, procedures, treatment, post-ED medications or any changes to medications, and return precautions. Survey respondents found GPT-generated instructions to be more understandable when rating procedures, treatment, post-ED medications or medication changes, post-ED follow-up, and return precautions. Satisfaction with GPT-generated discharge instruction subsections was the most favorable in procedures, treatment, post-ED medications or medication changes, and return precautions. Wilcoxon rank-sum test of Likert responses revealed significant differences (P=.01) in the interpretability of significant return precautions in GPT-generated discharge instructions compared to standard discharge instructions but not for other evaluation metrics and discharge instruction subsections. Conclusions This study demonstrates the potential for LLMs such as ChatGPT to act as a method of augmenting current documentation workflows in the ED to reduce the documentation burden of physicians. The ability of LLMs to provide tailored instructions for patients by improving readability and making instructions more applicable to patients could improve upon the methods of communication that currently exist.

This Viewpoint discusses how recognizing systemic racism in emergency departments will allow for the mitigation of racial and ethnic disparities and promote equitable treatment for all patients.