Explore the vast range of titles available.

Administrators and clinicians alike have attempted to predict emergency department visits for many years. The ability to predict or “forecast” ED visit volume can allow for more efficient resource allocation, including up-staffing or down-staffing, changing OR schedules, and predicting the need for significant resources. The goal of this study is to examine combinations of variables via machine learning to increase prediction accuracy and determine the factors that are most predictive of overall ED visits. As compared to a simple univariate time series model, we hypothesize that machine learning models will predict St. Joseph Mercy Ann Arbor's patient visit load for the emergency department (ED) with higher accuracy than a simple univariate time series model. Univariate time series models for daily ED visits, including ARIMA, Exponential Smoothing (ETS), and Facebook Inc.'s prophet algorithm were estimated as a baseline comparison. Machine learning models, including random forests and gradient boosted machines (GBM), were trained using data from 2017 to 2018. After final models were created, they were applied to the 2019 data to determine how well these models predicted actual ED patient volumes in data not utilized during the model fitting process. The accuracy of the machine learning and time series models were assessed based on out-of-sample predictive accuracy, compared using root mean squared error (RMSE). Using root mean squared error (RMSE) to assess out-of-sample predictive accuracy of the models, the results showed that the random forest model was the most accurate at predicting daily ED visits in the 2019 test set, followed by the GBM model. These performed only slightly better than the simple exponential smoothing model predictions. The ARIMA model performed poorly in comparison. The day of the week (likely capturing differences between weekdays and weekends) was found to be the most important predictor of patient volumes. Weather-related features such as maximum temperature and SFC pressure appeared to capture some of the seasonality trends related to changes in patient volumes. Machine learning models perform better at predicting daily patient volumes as compared to simple univariate time series models, though not by a substantial amount. Further research can help confirm these limited initial results. Gathering more training data and additional feature engineering could also be beneficial to training the models and potentially improving predictive accuracy.

Background To better understand the impact of the COVID-19 pandemic on hospital healthcare, we studied activity in the emergency department (ED) and acute medicine department of a major UK hospital. Methods Electronic patient records for all adult patients attending ED ( n = 243,667) or acute medicine ( n = 82,899) during the pandemic (2020–2021) and prior year (2019) were analysed and compared. We studied parameters including severity, primary diagnoses, co-morbidity, admission rate, length of stay, bed occupancy, and mortality, with a focus on non-COVID-19 diseases. Results During the first wave of the pandemic, daily ED attendance fell by 37%, medical admissions by 30% and medical bed occupancy by 27%, but all returned to normal within a year. ED attendances and medical admissions fell across all age ranges; the greatest reductions were seen for younger adults in ED attendances, but in older adults for medical admissions. Compared to non-COVID-19 pandemic admissions, COVID-19 admissions were enriched for minority ethnic groups, for dementia, obesity and diabetes, but had lower rates of malignancy. Compared to the pre-pandemic period, non-COVID-19 pandemic admissions had more hypertension, cerebrovascular disease, liver disease, and obesity. There were fewer low severity ED attendances during the pandemic and fewer medical admissions across all severity categories. There were fewer ED attendances with common non-respiratory illnesses including cardiac diagnoses, but no change in cardiac arrests. COVID-19 was the commonest diagnosis amongst medical admissions during the first wave and there were fewer diagnoses of pneumonia, myocardial infarction, heart failure, cellulitis, chronic obstructive pulmonary disease, urinary tract infection and other sepsis, but not stroke. Levels had rebounded by a year later with a trend to higher levels of stroke than before the pandemic. During the pandemic first wave, 7-day mortality was increased for ED attendances, but not for non-COVID-19 medical admissions. Conclusions Reduced ED attendances in the first wave of the pandemic suggest opportunities for reducing low severity presentations to ED in the future, but also raise the possibility of harm from delayed or missed care. Reassuringly, recent rises in attendance and admissions indicate that any deterrent effect of the pandemic on attendance is diminishing.

Introduction: Research suggests that pain assessment involves a complex interaction between patients and clinicians. We sought to assess the agreement between pain scores reported by the patients themselves and the clinician’s perception of a patient’s pain in the emergency department (ED). In addition, we attempted to identify patient and physician factors that lead to greater discrepancies in pain assessment. Methods: We conducted a prospective observational study in the ED of a tertiary academic medical center. Using a standard protocol, trained research personnel prospectively enrolled adult patients who presented to the ED. The entire triage process was recorded, and triage data were collected. Pain scores were obtained from patients on a numeric rating scale of 0 to 10. Five physician raters provided their perception of pain ratings after reviewing videos. Results: A total of 279 patients were enrolled. The mean age was 53 years. There were 141 (50.5%) female patients. The median self-reported pain score was 4 (interquartile range 0-6). There was a moderately positive correlation between self-reported pain scores and physician ratings of pain (correlation coefficient, 0.46; P <0.001), with a weighted kappa coefficient of 0.39. Some discrepancies were noted: 102 (37%) patients were rated at a much lower pain score, whereas 52 (19%) patients were given a much higher pain score from physician review. The distributions of chief complaints were different between the two groups. Physician raters tended to provide lower pain scores to younger (P = 0.02) and less ill patients (P = 0.008). Additionally, attending-level physician raters were more likely to provide a higher pain score than resident-level raters (P <0.001). Conclusion: Patients’ self-reported pain scores correlate positively with the pain score provided by physicians, with only a moderate agreement between the two. Under- and over-estimations of pain in ED patients occur in different clinical scenarios. Pain assessment in the ED should consider both patient and physician factors.

ObjectivePatients, families and community members would like emergency department wait time visibility. This would improve patient journeys through emergency medicine. The study objective was to derive, internally and externally validate machine learning models to predict emergency patient wait times that are applicable to a wide variety of emergency departments.MethodsTwelve emergency departments provided 3 years of retrospective administrative data from Australia (2017–2019). Descriptive and exploratory analyses were undertaken on the datasets. Statistical and machine learning models were developed to predict wait times at each site and were internally and externally validated. Model performance was tested on COVID-19 period data (January to June 2020).ResultsThere were 1 930 609 patient episodes analysed and median site wait times varied from 24 to 54 min. Individual site model prediction median absolute errors varied from±22.6 min (95% CI 22.4 to 22.9) to ±44.0 min (95% CI 43.4 to 44.4). Global model prediction median absolute errors varied from ±33.9 min (95% CI 33.4 to 34.0) to ±43.8 min (95% CI 43.7 to 43.9). Random forest and linear regression models performed the best, rolling average models underestimated wait times. Important variables were triage category, last-k patient average wait time and arrival time. Wait time prediction models are not transferable across hospitals. Models performed well during the COVID-19 lockdown period.ConclusionsElectronic emergency demographic and flow information can be used to approximate emergency patient wait times. A general model is less accurate if applied without site-specific factors.

Introduction: Our study aimed to determine 1) the association between time spent in the emergency department (ED) hallway and the development of delirium and 2) the hospital location of delirium development.Methods: This single-center, retrospective chart review included patients 18+ years old admitted to the hospital after presenting, without baseline cognitive impairment, to the ED in 2018. We identified the Delirium group by the following: key words describing delirium; orders for psychotropics, special observation, and restraints; or documented positive Confusion Assessment Method (CAM) screen. The Control group included patients not meeting delirium criteria. We used a multivariable logistic regression model, while adjusting for confounders, to assess the odds of delirium development associated with percentage of ED LOS spent in the hallway.Results: A total of 25,156 patients met inclusion criteria with 1920 (7.6%) meeting delirium criteria. Delirium group vs. Control group patients spent a greater percentage of time in the ED hallway (median 50.5% vs 10.8%, P<0.001); had longer ED LOS (median 11.94 vs 8.12 hours, P<0.001); had more ED room transfers (median 5 vs 4, P<0.001); and had longer hospital LOS (median 5.0 vs 4.6 days, P<0.001). Patients more frequently developed delirium in the ED (77.5%) than on inpatient units (22.5%). The relative odds of a patient developing delirium increased by 3.31 times for each percent increase in ED hallway time (95% confidence interval, 2.85, 3.83).Conclusion: Patients with delirium had more ED hallway exposure, longer ED LOS, and more ED room transfers. Understanding delirium in the ED has substantial implications for improving patient safety.

The Emergency Severity Index (ESI) is the most commonly used system in over 70% of all U.S. emergency departments (ED) that uses predicted resource utilization as a means to triage [1], Mistriage, which includes both undertriage and overtriage has been a persistent issue, affecting 32.2% of total ED visits [2]. Our goal is to develop a machine learning framework that predicts patients' resource needs, thereby improving resource allocation during triage. This retrospective study analyzed ED visits from the Medical Information Mart for Intensive Care IV, dividing the data into training (80%) and testing (20%) cohorts. We utilized data available during triage, including patient vital signs, age, gender, mode of arrival, medication history, and chief complaint. Azure AutoML was used to create different machine learning models trained to predict the 144 target columns including laboratory panels and imaging modalities as well as medications required during patients' ED visits. The 144 models' performance was evaluated using the area under the receiver operating characteristic curve (AUROC), F1 score, accuracy, precision and recall. A total of 391,472 ED visits were analyzed. 144 Voting ensemble models were created for each target. All frameworks achieved on average an AUC score of 0.82 and accuracy of 0.76. We gathered the feature importance for each target and observed that ‘chief complaint’, among others, had a high aggregate feature importance across different targets. This study shows the high accuracy in predicting resource needs for patients in the ED using a machine learning model. This can greatly improve patient flow and resource allocation in already resource limited emergency departments.

Introduction: Healthcare contributes 10% of greenhouse gases in the United States and generates two milion tons of waste each year. Reducing healthcare waste can reduce the environmental impact of healthcare and lower hospitals’ waste disposal costs. However, no literature to date has examined US emergency department (ED) waste management. The purpose of this study was to quantify and describe the amount of waste generated by an ED, identify deviations from waste policy, and explore areas for waste reduction.Methods: We conducted a 24-hour (weekday) ED waste audit in an urban, tertiary-care academic medical center. All waste generated in the ED during the study period was collected, manually sorted into separate categories based on its predominant material, and weighed. We tracked deviations from hospital waste policy using the hospital’s Infection Control Manual, state regulations, and Health Insurance Portability and Accountability Act standards. Lastly, we calculated direct pollutant emissions from ED waste disposal activities using the M+WasteCare Calculator.Results: The ED generated 671.8 kilograms (kg) total waste during a 24-hour collection period. On a per-patient basis, the ED generated 1.99 kg of total waste per encounter. The majority was plastic (64.6%), with paper-derived products (18.4%) the next largest category. Only 14.9% of waste disposed of in red bags met the criteria for regulated medical waste. We identified several deviations from waste policy, including loose sharps not placed in sharps containers, as well as re-processable items and protected health information thrown in medical and solid waste. We also identified over 200 unused items. Pollutant emissions resulting per day from ED waste disposal include 3110 kg carbon dioxide equivalent and 576 grams of other criteria pollutants, heavy metals, and toxins.Conclusion: The ED generates significant amounts of waste. Current ED waste disposal practices reveal several opportunities to reduce total waste generated, increase adherence to waste policy, and reduce environmental impact. While our results will likely be similar to other urban tertiary EDs that serve as Level I trauma centers, future studies are needed to compare results across EDs with different patient volumes or waste generation rates.

Mass Casualty Events (MCI) which have a direct and persisting impact on the safety and well-being of an emergency department (ED) and its staff, secondary to specific targeting of the healthcare setting, represent a distinct and complex operational challenge. ED physicians may be faced with the prospect of providing ongoing patient care while simultaneously experiencing direct threats to their own health or physical safety. In our study we considered the unique operational challenges encountered, and management strategies adopted, by the ED staff and its leadership to an all-hazard MCI impacting an academic urban emergency department. We conducted a retrospective, observational study of data from a tertiary academic medical center of patients arriving to the ED during a protracted MCI lasting from May 11th to May 21st, 2021. No arriving patients were excluded from analysis. Patient demographics, ED resource utilization, throughput, disposition and other pertinent data were considered. Analysis was done of three distinct patient populations including the event-group (EG), a non-event-group (NEG) and a control group (CG). Descriptive statistics were used to evaluating observational findings. We reviewed the records of 8527 total patients presenting to the Shamir Medical Center ED during the event and control periods. Of those, 283 patients were identified as an EG consisting of casualties from the MCI. 3563 patients were identified as the NEG presenting with complaints not related to the event. Our CG consisted of the 4681 patients who presented in the two weeks prior to the MCI. EG patients were noted to have important characteristics including higher relative numbers of men n = 173 (61.6 %), higher CTAS triage acuities [n = 10 (3.8 %), classified as CTAS 1], and an increase utilization of specialty consultation and admission consistent with observed injury patterns, most notably for the orthopedic services [orthopedic consultations: n = 126 (44.5 %) / orthopedic admissions: n = 13 (4.6 %)]. Findings from our observational study suggested that in the absence of larger public health interventions a manmade MCI, with direct threats to an ED and its staff, could force EDs to concurrently address the unique clinical needs of two distinct patient populations while simultaneously needing to take measures to protect hospital staff. Additionally, a higher burden of patient volumes and clinical acuity are likely to be encountered by select specialty consultation services. Further studies could focus on quantitative analysis to better understand the operational impact of these types of events on both patients and staff.

Background Early warning systems (EWSs) are used to assist clinical judgment in the detection of acute deterioration to avoid or reduce adverse events including unanticipated cardiopulmonary arrest, admission to the intensive care unit and death. Sometimes healthcare professionals (HCPs) do not trigger the alarm and escalate for help according to the EWS protocol and it is unclear why this is the case. The aim of this qualitative evidence synthesis was to answer the question ‘why do HCPs fail to escalate care according to EWS protocols?’ The findings will inform the update of the National Clinical Effectiveness Committee (NCEC) National Clinical Guideline No. 1 Irish National Early Warning System (INEWS). Methods A systematic search of the published and grey literature was conducted (until February 2018). Data extraction and quality appraisal were conducted by two reviewers independently using standardised data extraction forms and quality appraisal tools. A thematic synthesis was conducted by two reviewers of the qualitative studies included and categorised into the barriers and facilitators of escalation. GRADE CERQual was used to assess the certainty of the evidence. Results Eighteen studies incorporating a variety of HCPs across seven countries were included. The barriers and facilitators to the escalation of care according to EWS protocols were developed into five overarching themes: Governance, Rapid Response Team (RRT) Response, Professional Boundaries, Clinical Experience, and EWS parameters. Barriers to escalation included: Lack of Standardisation, Resources, Lack of accountability, RRT behaviours, Fear, Hierarchy, Increased Conflict, Over confidence, Lack of confidence, and Patient variability. Facilitators included: Accountability, Standardisation, Resources, RRT behaviours, Expertise, Additional support, License to escalate, Bridge across boundaries, Clinical confidence, empowerment, Clinical judgment, and a tool for detecting deterioration. These are all individual yet inter-related barriers and facilitators to escalation. Conclusions The findings of this qualitative evidence synthesis provide insight into the real world experience of HCPs when using EWSs. This in turn has the potential to inform policy-makers and HCPs as well as hospital management about emergency response system-related issues in practice and the changes needed to address barriers and facilitators and improve patient safety and quality of care.