Left without being seen in a hybrid point of service collection model emergency department

A study of "left against medical advice" emergency department patients: an optimized explainable artificial intelligence framework

The issue of left against medical advice (LAMA) patients is common in today's emergency departments (EDs). This issue represents a medico-legal risk and may result in potential readmission, mortality, or revenue loss. Thus, understanding the factors that cause patients to "leave against medical advice" is vital to mitigate and potentially eliminate these adverse outcomes. This paper proposes a framework for studying the factors that affect LAMA in EDs. The framework integrates machine learning, metaheuristic optimization, and model interpretation techniques. Metaheuristic optimization is used for hyperparameter optimization-one of the main challenges of machine learning model development. Adaptive tabu simulated annealing (ATSA) metaheuristic algorithm is utilized for optimizing the parameters of extreme gradient boosting (XGB). The optimized XGB models are used to predict the LAMA outcomes for patients under treatment in ED. The designed algorithms are trained and tested using four data groups which are created using feature selection. The model with the best predictive performance is then interpreted using the SHaply Additive exPlanations (SHAP) method. The results show that best model has an area under the curve (AUC) and sensitivity of 76% and 82%, respectively. The best model was explained using SHAP method.

Factors impacting trauma-specific quality of life following injury: A multi-center assessment in Lebanon

OBJECTIVE

Injuries account for a large portion of the global burden of disease, representing over 10% of all disability adjusted life years (DALYs). This study analyzes the economic impact of injury for those experiencing moderate-to-severe injury in Beirut, Lebanon. It further examines the impact of different demographic and socioeconomic factors on trauma-specific quality of life 1-2 years following injury.

METHODS

This was a prospective cohort study following patients 1-2 years after being treated for injury at one of three hospitals in Beirut, Lebanon. Patients interviewed by phone. In addition to questions on financial impact, access to healthcare, and socioeconomic status, the Trauma-specific Quality of Life (TQoL) Questionnaire was used to assess quality of life following injury. Multivariable linear models were constructed to examine TQoL and demographics among institutes.

RESULTS

116 patients completed interviews. The average out-of-pocket cost of injury was 2975.42 USD, 65% of which was borrowed. 21% of people lost employment due to injury. Patients at Geitawi Hospital and the Rafic Hariri Governmental Hospital borrowed more on average and had higher reductions in employment than patients at the American University of Beirut Medical Center (AUBMC). There was a loss of income for those employed at the time of injury, with a mean monthly loss of 261.6 USD. The economic impact of injury was 10,329.00 USD. 25% of patients reported difficulty with accessing follow-up care, predominantly due to cost. Mean-adjusted Trauma-specific Quality of life (TQoL) was highest at AUBMC. Education was associated with functional recovery in the TQoL questionnaire; for every additional year of education there was an increase in the functional recovery domain of 0.03.

CONCLUSION

Individuals that experienced moderate-to-severe injury in Beirut, Lebanon, suffered financial repercussions, including reductions in income, less employment, or unemployment. Across all patients surveyed, higher level of education was associated with better functional quality of life. More study into the intricacies of accessing healthcare care in Lebanon, especially given the current economic and political climate, are crucial to maintain the health of those experiencing injury and can help inform targeted interventions.

Emergency Department Patients Who Leave Before Treatment Is Complete

Introduction

Emergency department (ED) patients who leave before treatment is complete (LBTC) represent medicolegal risk and lost revenue. We sought to examine LBTC return visits characteristics and potential revenue effects for a large healthcare system.

Methods

This retrospective, multicenter study examined all encounters from January 1–December 31, 2019 at 18 EDs. The LBTC patients were divided into left without being seen (LWBS), defined as leaving prior to completed medical screening exam (MSE), and left subsequent to being seen (LSBS), defined as leaving after MSE was complete but before disposition. We recorded 30-day returns by facility type including median return hours, admission rate, and return to index ED. Expected realization rate and potential charges were calculated for each patient visit.

Results

During the study period 626,548 ED visits occurred; 20,158 (3.2%) LBTC index encounters occurred, and 6745 (33.5%) returned within 30 days. The majority (41.7%) returned in <24 hours with 76.1% returning in 10 days and 66.4% returning to index ED. Median return time was 43.3 hours, and 23.2% were admitted. Urban community EDs had the highest 30-day return rate (37.8%, 95% confidence interval, 36.41–39.1). Patients categorized as LSBS had longer median return hours (66.0) and higher admission rates (29.8%) than the LWBS cohort. There was a net potential realization rate of $9.5 million to the healthcare system.

Conclusion

In our system, LSBS patients had longer return times and higher admission rates than LWBS patients. There was significant potential financial impact for the system. Further studies should examine how healthcare systems can reduce risk and financial impacts of LBTC patients.

Patients leaving without being seen from the emergency department: A prediction model using machine learning on a nationwide database

OBJECTIVE

The objective of this study was to develop a US-representative prediction model identifying factors with a greater likelihood of patients leaving without being seen.

METHODS

We conducted a retrospective cohort analysis using a 2016 nationwide emergency department (ED) sample. Patient factors considered for analysis were the following: age, sex, acuity, chronic diseases, weekend visit, quarter of presentation, median household income quartile for patient's zip code, primary/secondary insurance, total charges for the visit, and urban/rural household. Hospital factors considered were urban/rural location, trauma center/teaching hospital, and annual ED volume. Multivariable logistic regression was used to find significant predictors and their interactions. A random forest algorithm was used to determine the order of importance of factors.

RESULTS

A total of 32,680,232 hospital-based ED visits with 466,047 incidences of leaving without being seen were included. The cohort comprised 55.5% females, with a median (IQR) age of 37 (21-58) years. Positively associating factors were male sex (odds ratio [OR], 1.22; 99% confidence interval [CI], 1.17-1.26), lower acuity (P < 0.001), and annual ED visits ≥60,000 (OR, 1.44; 99% CI, 1.21-1.7) versus <20,000. Negatively associating factors were primary insurance being Medicare/Tricare or private insurance (P < 0.001); weekend presentations (OR, 0.87; 99% CI, 0.85-0.89); age >64 or <18 years (P < 0.001); and higher median household income for patient's zip code second (OR, 0.86; 99% CI, 0.77-0.97), third (OR, 0.8; 99% CI, 0.7-0.91), and fourth (OR, 0.7; 99% CI, 0.6-0.8) quartiles versus the first quartile. Significant interactions existed between age, acuity, primary insurance, and chronic conditions. Primary insurance was the most predictive.

CONCLUSION

Our derivation model reiterated several modifiable and non-modifiable risk factors for leaving without being seen established previously while rejecting the importance of others.

Methodological Approaches to Support Process Improvement in Emergency Departments: A Systematic Review

The most commonly used techniques for addressing each Emergency Department (ED) problem (overcrowding, prolonged waiting time, extended length of stay, excessive patient flow time, and high left-without-being-seen (LWBS) rates) were specified to provide healthcare managers and researchers with a useful framework for effectively solving these operational deficiencies. Finally, we identified the existing research tendencies and highlighted opportunities for future work. We implemented the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to undertake a review including scholarly articles published between April 1993 and October 2019. The selected papers were categorized considering the leading ED problems and publication year. Two hundred and three (203) papers distributed in 120 journals were found to meet the inclusion criteria. Furthermore, computer simulation and lean manufacturing were concluded to be the most prominent approaches for addressing the leading operational problems in EDs. In future interventions, ED administrators and researchers are widely advised to combine Operations Research (OR) methods, quality-based techniques, and data-driven approaches for upgrading the performance of EDs. On a different tack, more interventions are required for tackling overcrowding and high left-without-being-seen rates.