A Granular View of Emergency Department Length of Stay: Improving Predictive Power and Extracting Real-Time, Actionable Insights.

STUDY OBJECTIVE: Improved understanding of factors affecting prolonged emergency department (ED) length of stay is crucial to improving patient outcomes. Our investigation builds on prior work by considering ED length of stay in operationally distinct time periods and using benchmark and novel machine learning techniques applied only to data that would be available to ED operators in real time. METHODS: This study was a retrospective review of patient visits over 1 year at 2 urban EDs, including 1 academic and 1 academically affiliated ED, and 2 suburban, community EDs. ED length of stay was partitioned into 3 components: arrival-to-room, room-to-disposition, and admit disposition to departure. Prolonged length of stay for each component was considered beyond 1, 3, and 2 hours, respectively. Classification models (logistic regression, random forest, and XGBoost) were applied, and important features were evaluated. RESULTS: In total, 135,044 unique patient encounters were evaluated for the arrival-to-room, room-to-disposition, and admit disposition-to-departure models, which had accuracy ranges of 84% to 96%, 66% to 77%, and 62% to 72%, respectively. Waiting room and ED volumes were important features in all arrival-to-room models. Room-to-disposition results identified patient characteristics and ED volume as the most important features for prediction. Boarder volume was an important feature of the admit disposition-to-departure models for all sites. Academic site models noted nurse staffing ratios as important, whereas community site models noted hospital capacity and surgical volume as important for admit disposition-to-departure prediction. CONCLUSION: This study identified granular capacity, flow, and nurse staffing predictors of ED length of stay not previously reported in the literature. Our novel methodology allowed for more accurate and operationally meaningful findings compared to prior modeling methods.

Factors Associated with Overutilization of Computed Tomography of the Cervical Spine.

Introduction: Despite the wide availability of clinical decision rules for imaging of the cervical spine after a traumatic injury (eg, NEXUS C-spine rule and Canadian C-spine rule), there is significant overutilization of computed tomography (CT) imaging in patients who are deemed to be at low risk for a clinically significant cervical spine injury by these clinical decision rules. The purpose of this study was to identify the major factors associated with the overuse of CT cervical spine imaging using a logistic regression model. Methods: This was a retrospective review of all adult patients who underwent CT cervical spine imaging for evaluation of a traumatic injury at a tertiary academic emergency department (ED) and three affiliate community EDs in January and February 2019. We performed multivariable logistic regression to identify factors associated with obtaining CT cervical spine imaging despite low-risk classification by the NEXUS C-spine Rule. Results: A total of 1,051 patients underwent CT cervical spine imaging for traumatic indications during the study period, and 889 patients were included in the analysis. Of these patients, 376 (42.3%) were negative by the NEXUS C-spine rule. Variables that were associated with increased likelihood of unnecessary imaging included age over 65, Emergency Severity Index (ESI) score 2 and 3, arrival as a walk-in, and anticoagulation status. Patients who presented to the tertiary academic ED had a significantly lower likelihood of unnecessary imaging. Twenty-one patients (2.4%) were found to have cervical spine fractures on imaging, two of whom were negative by the NEXUS C-spine rule, but neither had a clinically significant fracture. Conclusion: Cervical spine imaging is vastly overused in patients presenting to the ED with traumatic injuries, as adjudicated using the NEXUS C-spine rule as a reference standard. Older age, ESI level, arrival as a walk-in, and taking anticoagulation drugs were associated with overutilization of CT imaging. Conversely, presenting to the tertiary academic ED was associated with a lower likelihood of undergoing unnecessary imaging. This model can guide future interventions to optimize ED CT utilization and minimize unnecessary testing.

Accuracy of physician self-estimation of time spent during patient care in the emergency department.

Objective: Accurate measurement of physicians' time spent during patient care stands to inform emergency department (ED) improvement efforts. Direct observation is time consuming and cost prohibitive, so we sought to determine if physician self-estimation of time spent during patient care was accurate. Methods: We performed a prospective, convenience-sample study in which research assistants measured time spent by ED physicians in patient care. At the conclusion of each observed encounter, physicians estimated their time spent. Using Mann-Whitney U tests and Spearman's rho, we compared physician estimates to actual time spent and assessed for associations of encounter characteristics and physician estimation. Results: Among 214 encounters across 10 physicians, we observed a medium-sized correlation between actual and estimated time (Spearman's rho = 0.63, p < 0.001), and in aggregate, physicians underestimated time spent by a median of 0.1 min. An equal number of encounters were overestimated and underestimated. Underestimated encounters were underestimated by a median of 5.1 min (interquartile range [IQR] 2.5-9.8) and overestimated encounters were overestimated by a median of 4.3 min (IQR 2.5-11.6)-26.3% and 27.9% discrepancy, respectively. In terms of actual time spent, underestimated encounters (median 19.3 min, IQR 13.5-28.3) were significantly longer than overestimated encounters (median 15.3 min, IQR 11.3-20.5) (p < 0.001). Conclusions: Physician self-estimation of time spent was accurate in aggregate, providing evidence that it is a valid surrogate marker for larger-scale process improvement and research activities, but likely not at the encounter level. Investigations exploring mechanisms to augment physician self-estimation, including modeling and technological support, may yield pathways to make self-estimation valid also at the encounter level.

Code Help: Can This Unique State Regulatory Intervention Improve Emergency Department Crowding?

INTRODUCTION: Emergency department (ED) crowding adversely affects multiple facets of high-quality care. The Commonwealth of Massachusetts mandates specific, hospital action plans to reduce ED boarding via a mechanism termed "Code Help." Because implementation appears inconsistent even when hospital conditions should have triggered its activation, we hypothesized that compliance with the Code Help policy would be associated with reduction in ED boarding time and total ED length of stay (LOS) for admitted patients, compared to patients seen when the Code Help policy was not followed. METHODS: This was a retrospective analysis of data collected from electronic, patient-care, timestamp events and from a prospective Code Help registry for consecutive adult patients admitted from the ED at a single academic center during a 15-month period. For each patient, we determined whether the concurrent hospital status complied with the Code Help policy or violated it at the time of admission decision. We then compared ED boarding time and overall ED LOS for patients cared for during periods of Code Help policy compliance and during periods of Code Help policy violation, both with reference to patients cared for during normal operations. RESULTS: Of 89,587 adult patients who presented to the ED during the study period, 24,017 (26.8%) were admitted to an acute care or critical care bed. Boarding time ranged from zero to 67 hours 30 minutes (median 4 hours 31 minutes). Total ED LOS for admitted patients ranged from 11 minutes to 85 hours 25 minutes (median nine hours). Patients admitted during periods of Code Help policy violation experienced significantly longer boarding times (median 20 minutes longer) and total ED LOS (median 46 minutes longer), compared to patients admitted under normal operations. However, patients admitted during Code Help policy compliance did not experience a significant increase in either metric, compared to normal operations. CONCLUSION: In this single-center experience, implementation of the Massachusetts Code Help regulation was associated with reduced ED boarding time and ED LOS when the policy was consistently followed, but there were adverse effects on both metrics during violations of the policy.

Contributions of Academic Emergency Medicine Programs to U.S. Health Care: Summary of the AAAEM-AACEM Benchmarking Data.

OBJECTIVES: The societal contribution of emergency care in the United States has been described. The role and impact of academic emergency departments (EDs) has been less clear. Our report summarizes the results of a benchmarking effort specifically focused on academic emergency medicine (EM) practices. METHODS: From October through December 2016, the Academy of Academic Administrators of Emergency Medicine (AAAEM) and the Association of Academic Chairs of Emergency Medicine (AACEM) jointly administered a benchmarking survey to allopathic, academic departments and divisions of emergency medicine. Participation was voluntary and nonanonymous. The survey queried various aspects of the three components of the tripartite academic mission: clinical care, education and research, and faculty effort and compensation. Responses reflected a calendar year from July 1, 2015, to June 30, 2016. RESULTS: Of 107 eligible U.S. allopathic, academic departments and divisions of emergency medicine, 79 (74%) responded to the survey overall, although individual questions were not always answered by all responding programs. The 79 responding programs reported 6,876,189 patient visits at 97 primary and affiliated academic clinical sites. A number of clinical operations metrics related to the care of these patients at these sites are reported in this study. All responding programs had active educational programs for EM residents, with a median of 37 residents per program. Nearly half of the overall respondents reported responsibility for teaching medical students in mandatory EM clerkships. Fifty-two programs reported research and publication activity, with a total of $129,494,676 of grant funding and 3,059 publications. Median faculty effort distribution was clinical effort, 66.9%; education effort, 12.7%; administrative effort, 12.0%; and research effort, 6.9%. Median faculty salary was $277,045. CONCLUSIONS: Academic EM programs are characterized by significant productivity in clinical operations, education, and research. The survey results reported in this investigation provide appropriate benchmarking for academic EM programs because they allow for comparison of academic programs to each other, rather than nonacademic programs that do not necessarily share the additional missions of research and education and may have dissimilar working environments.

Patient safety incident capture resulting from incident reports: a comparative observational analysis.

BACKGROUND: Patient safety incident (PSI) discovery is an essential component of quality improvement. When submitted, incident reports may provide valuable opportunities for PSI discovery. However, little objective information is available to date to quantify or demonstrate this value. The objective of this investigation was to assess how often Emergency Department (ED) incident reports submitted by different sources led to the discovery of PSIs. METHODS: A standardized peer review process was implemented to evaluate all incident reports submitted to the ED. Findings of the peer review analysis were recorded prospectively in a quality improvement database. A retrospective analysis of the quality improvement database was performed to calculate the PSI capture rates for incident reports submitted by different source groups. RESULTS: 363 incident reports were analyzed over a period of 18 months; 211 were submitted by healthcare providers (HCPs) and 126 by non-HCPs. PSIs were identified in 108 resulting in an overall capture rate of 31%. HCP-generated reports resulted in a 44% capture rate compared to 10% for non-HCPs (p < 0.001). There was no difference in PSI capture between sub-groups of HCPs and non-HCPs. CONCLUSION: HCP-generated ED incident reports were much more likely to capture PSIs than reports submitted by non-HCPs. However, HCP reports still led to PSI discovery less than half the time. Further research is warranted to develop effective strategies to improve the utility of incident reports from both HCPs and non-HCPs.

Emergency department patient safety incident characterization: an observational analysis of the findings of a standardized peer review process.

BACKGROUND: Emergency Department (ED) care has been reported to be prone to patient safety incidents (PSIs). Improving our understanding of PSIs is essential to prevent them. A standardized, peer review process was implemented to identify and analyze ED PSIs. The primary objective of this investigation was to characterize ED PSIs identified by the peer review process. A secondary objective was to characterize PSIs that led to patient harm. In addition, we sought to provide a detailed description of the peer review process for others to consider as they conduct their own quality improvement initiatives. METHODS: An observational study was conducted in a large, urban, tertiary-care ED. Over a two-year period, all ED incident reports were investigated via a standardized, peer review process. PSIs were identified and analyzed for contributing factors including systems failures and practitioner-based errors. The classification system for factors contributing to PSIs was developed based on systems previously reported in the emergency medicine literature as well as the investigators' experience in quality improvement and peer review. All cases in which a PSI was discovered were further adjudicated to determine if patient harm resulted. RESULTS: In 24 months, 469 cases were investigated, identifying 152 PSIs. In total, 188 systems failures and 96 practitioner-based errors were found to have contributed to the PSIs. In twelve cases, patient harm was determined to have resulted from PSIs. Systems failures were identified in eleven of the twelve cases in which a PSI resulted in patient harm. CONCLUSION: Systems failures were almost twice as likely as practitioner-based errors to contribute to PSIs, and systems failures were present in the majority of cases resulting in patient harm. To effectively reduce PSIs, ED quality improvement initiatives should focus on systems failure reduction.