The challenge of predicting demand for emergency department services

A Systematic Review of Features Forecasting Patient Arrival Numbers

Adequate nurse staffing is crucial for quality healthcare, necessitating accurate predictions of patient arrival rates. These forecasts can be determined using supervised machine learning methods. Optimization of machine learning methods is largely about minimizing the prediction error. Existing models primarily utilize data such as historical patient visits, seasonal trends, holidays, and calendars. However, it is unclear what other features reduce the prediction error. Our systematic literature review identifies studies that use supervised machine learning to predict patient arrival numbers using nontemporal features, which are features not based on time or dates. We scrutinized 26 284 studies, eventually focusing on 27 relevant ones. These studies highlight three main feature groups: weather data, internet search and usage data, and data on (social) interaction of groups. Internet data and social interaction data appear particularly promising, with some studies reporting reduced errors by up to 33%. Although weather data are frequently used, its utility is less clear. Other potential data sources, including smartphone and social media data, remain largely unexplored. One reason for this might be potential data privacy challenges. In summary, although patient arrival prediction has become more important in recent years, there are still many questions and opportunities for future research on the features used in this area.

Enhancing Emergency Department Management: A Data-Driven Approach to Detect and Predict Surge Persistence

The prediction of patient attendance in emergency departments (ED) is crucial for effective healthcare planning and resource allocation. This paper proposes an early warning system that can detect emerging trends in ED attendance, offering timely alerts for proactive operational planning. Over 13 years of historical ED attendance data (from January 2010 till December 2022) with 1,700,887 data points were used to develop and validate: (1) a Seasonal Autoregressive Integrated Moving Average with eXogenous factors (SARIMAX) forecasting model; (2) an Exponentially Weighted Moving Average (EWMA) surge prediction model, and (3) a trend persistence prediction model. Drift detection was achieved with the EWMA control chart, and the slopes of a kernel-regressed ED attendance curve were used to train various machine learning (ML) models to predict trend persistence. The EWMA control chart effectively detected significant COVID-19 events in Singapore. The surge prediction model generated preemptive signals on changes in the trends of ED attendance over the COVID-19 pandemic period from January 2020 until December 2022. The persistence of novel trends was further estimated using the trend persistence model, with a mean absolute error of 7.54 (95% CI: 6.77-8.79) days. This study advanced emergency healthcare management by introducing a proactive surge detection framework, which is vital for bolstering the preparedness and agility of emergency departments amid unforeseen health crises.

Poisson Modeling Predicts Acute Telestroke Patient Call Volume

Background: Predicting the frequency of calls for telestroke and emergency teleneurology consultation is essential to prepare staffing for the immediate management of time-sensitive strokes. In this study, we evaluate Poisson distribution count data using a generalized linear model that predicts the volume of hourly telestroke calls over a 24-h period. Methods: We performed an Institutional Review Board approved retrospective cohort review of patients (January 2019-December 2022) from an institutional telestroke database at a large nonprofit multihospital system in the United States. All patients ≥18 years with a telestroke activation were included. Telestroke calls were quantified in frequency per day and analyzed by multiple time and date intervals. Poisson probability mass function (PMF) and cumulative distribution function (CDF) were used to predict call probabilities. A univariable Poisson regression model was fit to predict call volumes. Results: A total of 8,499 patients at 21 hospitals met inclusion criteria, the mean calls/day were 5.82 ± 2.54, and mean calls/day within each hour increment ranged from a minimum of 0.07 from 5 a.m. to 6 a.m. to a maximum of 0.45 from 7 p.m. to 8 p.m. The Poisson distribution was the most appropriate parametric probability model for these data, confirmed by the fit of the data to the expected distributions corresponding to the calculated means. The predicted probabilities of call frequencies by hour were calculated using the Poisson PMF and CDF; the probability of two or fewer calls/day by hour ranged from 98.9% to 99.9%. Univariable Poisson regression modeled an increase of future calls/day from 6.7 calls/day in July 2023 to 7.6 calls/day in October 2025. Conclusion: Poisson modeling closely fits telestroke call volumes, predicts the future volumes, and can be applied to any health system in which the mean call volume is known, which may inform the number of physicians needed to cover calls in real-time.

Forecasting emergency department arrivals using INGARCH models

BACKGROUND

Forecasting patient arrivals to hospital emergency departments is critical to dealing with surges and to efficient planning, management and functioning of hospital emerency departments.

OBJECTIVE

We explore whether past mean values and past observations are useful to forecast daily patient arrivals in an Emergency Department.

MATERIAL AND METHODS

We examine whether an integer-valued generalized autoregressive conditional heteroscedastic (INGARCH) model can yield a better conditional distribution fit and forecast of patient arrivals by using past arrival information and taking into account the dynamics of the volatility of arrivals.

RESULTS

We document that INGARCH models improve both in-sample and out-of-sample forecasts, particularly in the lower and upper quantiles of the distribution of arrivals.

CONCLUSION

Our results suggest that INGARCH modelling is a useful model for short-term and tactical emergency department planning, e.g., to assign rotas or locate staff for unexpected surges in patient arrivals.

Avoiding Hospital Admissions and Delayed Transfers of Care by Improved Access to Intermediate Care: A Simulation Study

OBJECTIVE

The current waiting times for intermediate care in the Netherlands prohibit timely access, leading to unwanted and costly hospital admissions. We propose alternative policies for improvement of intermediate care and estimate the effects on the waiting times, hospitalization, and the number of patient replacements.

DESIGN

Simulation study.

SETTING AND PARTICIPANTS

For our case study, data were used of older adults who received intermediate care in Amsterdam, the Netherlands, in 2019. For this target group, in- and outflows and patient characteristics were identified.

METHODS

A process map of the main pathways into and out of the intermediate care was obtained and a discrete event simulation (DES) was built. We demonstrate the use of our DES for intermediate care by evaluating possible policy changes for a real-life case study in Amsterdam.

RESULTS

By means of a sensitivity analysis with the DES, we show that in Amsterdam the waiting times are not a result of a lack in bed capacity but are due to an inefficient triage and application process. Older adults have to wait a median of 1.8 days for admission, leading to hospitalization. If the application process becomes more efficient and evening and weekend admissions are allowed, we find that unwanted hospitalization can be decreased substantially.

CONCLUSION AND IMPLICATIONS

In this study, a simulation model is developed for intermediate care that can serve as a basis for policy decisions. Our case study shows that the waiting times for health care facilities are not always solved by increasing bed capacity. This underlines the necessity for a data-driven approach to identify logistic bottlenecks and find the best ways to solve them.

The role of emergency incident type in identifying first responders' health exposure risks

Fire-based emergency management service (EMS) personnel are dispatched to various incidents daily, many of which have unique occupational risks. To fully understand the variability of incident types and how to best prepare and respond, an exploration of the U.S. coding system of incident types is necessary. This study uses potential exposure to SARS-CoV-2 as a case example to understand if and how coding categories for incident call types may be updated to improve data standardization and emergency response decision making. Researchers received emergency response incident data generated by three fire department computer-aided dispatch (CAD) systems between March and September 2020. Each incident was labeled EMS, Fire, or Other. Of the 162,766 incidents, approximately 8.1% (n = 13,144) noted potential SARS-CoV-2 exposure within their narrative descriptions of which 86.3% were coded as EMS, 9.9% as Fire, and 3.9% as Other. To assess coding variability across incident types, researchers used the original 3-incident type variable and a new 5-incident type variable reassigned by researchers into EMS, Fire, Other, Hazmat, and Motor Vehicle. Logit regressions compared differences in potential exposure using the 3- and 5-incident type variables. When evaluating the 3-incident type variable, those responding to a Fire versus an EMS incident were 84% less likely to be associated with potential exposure to SARS-CoV-2. For the 5-incident type variable, those responding to Fire incidents were 77% less likely to be associated with a potential exposure than those responding to EMS incidents. Changes in potential exposure between the 3- and 5-incident type models show the need to understand how incident types are assigned. This demonstrates the need for data standardization to accurately categorize incident types to improve emergency preparedness and response. Results have implications for incident type coding at fire department municipality and national levels.

Probabilistic forecasting of hourly emergency department arrivals

An accurate forecast of Emergency Department (ED) arrivals by an hour of the day is critical to meet patients' demand. It enables planners to match ED staff to the number of arrivals, redeploy staff, and reconfigure units. In this study, we develop a model based on Generalised Additive Models and an advanced dynamic model based on exponential smoothing to generate an hourly probabilistic forecast of ED arrivals for a prediction window of 48 hours. We compare the forecast accuracy of these models against appropriate benchmarks, including TBATS, Poisson Regression, Prophet, and simple empirical distribution. We use Root Mean Squared Error to examine the point forecast accuracy and assess the forecast distribution accuracy using Quantile Bias, PinBall Score and Pinball Skill Score. Our results indicate that the proposed models outperform their benchmarks. Our developed models can also be generalised to other services, such as hospitals, ambulances or clinical desk services.

Predicting hospital emergency department visits accurately: A systematic review

OBJECTIVES

The emergency department (ED) is a very important healthcare entrance point, known for its challenging organisation and management due to demand unpredictability. An accurate forecast system of ED visits is crucial to the implementation of better management strategies that optimise resources utilization, reduce costs and improve public confidence. The aim of this review is to investigate the different factors that affect the ED visits forecasting outcomes, in particular the predictive variables and type of models applied.

METHODS

A systematic search was conducted in PubMed, Web of Science and Scopus. The review methodology followed the PRISMA statement guidelines.

RESULTS

Seven studies were selected, all exploring predictive models to forecast ED daily visits for general care. MAPE and RMAE were used to measure models' accuracy. All models displayed good accuracy, with errors below 10%.

CONCLUSIONS

Model selection and accuracy was found to be particularly sensitive to the ED dimension. While ARIMA-based and other linear models have good performance for short-time forecast, some machine learning methods proved to be more stable when forecasting multiple horizons. The inclusion of exogenous variables was found to be advantageous only in bigger EDs.

Use of Real-Time Information to Predict Future Arrivals in the Emergency Department

STUDY OBJECTIVE

We aimed to build prediction models for shift-level emergency department (ED) patient volume that could be used to facilitate prediction-driven staffing. We sought to evaluate the predictive power of rich real-time information and understand 1) which real-time information had predictive power and 2) what prediction techniques were appropriate for forecasting ED demand.

METHODS

We conducted a retrospective study in an ED site in a large academic hospital in New York City. We examined various prediction techniques, including linear regression, regression trees, extreme gradient boosting, and time series models. By comparing models with and without real-time predictors, we assessed the potential gain in prediction accuracy from real-time information.

RESULTS

Real-time predictors improved prediction accuracy on models without contemporary information from 5% to 11%. Among extensive real-time predictors examined, recent patient arrival counts, weather, Google trends, and concurrent patient comorbidity information had significant predictive power. Out of all the forecasting techniques explored, SARIMAX (Seasonal Autoregressive Integrated Moving Average with eXogenous factors) achieved the smallest out-of-sample the root mean square error (RMSE) of 14.656 and mean absolute prediction error (MAPE) of 8.703%. Linear regression was the second best, with out-of-sample RMSE and MAPE equal to 15.366 and 9.109%, respectively.

CONCLUSION

Real-time information was effective in improving the prediction accuracy of ED demand. Practice and policy implications for designing staffing paradigms with real-time demand forecasts to reduce ED congestion were discussed.

Time-series cohort study to forecast emergency department visits in the city of Milan and predict high demand: a 2-day warning system

OBJECTIVES

The emergency department (ED) is one of the most critical areas in any hospital. Recently, many countries have seen a rise in the number of ED visits, with an increase in length of stay and a detrimental effect on quality of care. Being able to forecast future demands would be a valuable support for hospitals to prevent high demand, particularly in a system with limited resources where use of ED services for non-urgent visits is an important issue.

DESIGN

Time-series cohort study.

SETTING

We collected all ED visits between January 2014 and December 2019 in the five larger hospitals in Milan. To predict daily volumes, we used a regression model with autoregressive integrated moving average errors. Predictors included were day of the week and year-round seasonality, meteorological and environmental variables, information on influenza epidemics and festivities. Accuracy of prediction was evaluated with the mean absolute percentage error (MAPE).

PRIMARY OUTCOME MEASURES

Daily all-cause EDs visits.

RESULTS

In the study period, we observed 2 223 479 visits. ED visits were most likely to occur on weekends for children and on Mondays for adults and seniors. Results confirmed the role of meteorological and environmental variables and the presence of day of the week and year-round seasonality effects. We found high correlation between observed and predicted values with a MAPE globally smaller than 8.1%.

CONCLUSIONS

Results were used to establish an ED warning system based on past observations and indicators of high demand. This is important in any health system that regularly faces scarcity of resources, and it is crucial in a system where use of ED services for non-urgent visits is still high.

Queueing Problems in Emergency Departments: A Review of Practical Approaches and Research Methodologies

Problems related to patient scheduling and queueing in emergency departments are gaining increasing attention in theory, in the fields of operations research and emergency and healthcare services, and in practice. This paper aims to provide an extensive review of studies addressing queueing-related problems explicitly related to emergency departments. We have reviewed 229 articles and books spanning seven decades and have sought to organize the information they contain in a manner that is accessible and useful to researchers seeking to gain knowledge on specific aspects of such problems. We begin by presenting a historical overview of applications of queueing theory to healthcare-related problems. We subsequently elaborate on managerial approaches used to enhance efficiency in emergency departments. These approaches include bed management, fast-track, dynamic resource allocation, grouping/prioritization of patients, and triage approaches. Finally, we discuss scientific methodologies used to analyze and optimize these approaches: algorithms, priority models, queueing models, simulation, and statistical approaches.

A Sustainable Model for Emergency Medical Services in Developing Countries: A Novel Approach Using Partial Outsourcing and Machine Learning

INTRODUCTION

Unlike Western countries, many low- and middle-income countries (LMIC), like India, have a de-centralized emergency medical services (EMS) involving both semi-government and non-government organizations. It is alarming that due to the absence of a common ecosystem, the utilization of resources is inefficient, which leads to shortage of available vehicles and larger response time. Fragmentation of emergency supply chain resources motivates us to propose a new vehicle routing and scheduling model equipped with novel features to ensure minimal response time using existing resources.

MATERIALS AND METHODS

The data set of medical and fire-related emergencies from January 2018 to May 2018 of Uttarakhand State in India was provided by GVK Emergency Management and Research Institute (GVK EMRI) also known as 108 EMSs was used in the study. The proposed model integrates all the available EMS vehicles including partial outsourcing to non-ambulatory vehicles like police vans, taxis, etc., using a novel two-echelon heuristic approach. In the first stage, an offline learning model is developed to yield the deployment strategy for EMS vehicles. Seven well researched machine learning (ML) algorithms were analyzed for parameter prediction namely random forest (RF), convolutional neural network (CNN), k-nearest neighbor (KNN), classification and regression tree (CART), support vector machine (SVM), logistic regression (LR), and linear discriminant analysis (LDA). In the second stage, a real-time routing model is proposed for EMS vehicle routing at the time of emergency, considering partial outsourcing.

RESULTS AND DISCUSSION

The results indicate that the RF classifier outperforms the LR, LDA, SVM, CNN, CART and NB classifier in terms of both accuracy as well as F-1 score. The proposed vehicle routing and scheduling model for automated decision-making shows an improvement of 42.1%, 54%, 27.9% and 62% in vehicle assignment time, vehicle travel time from base to scene, travel time from scene to hospital, and total response time, respectively, in urban areas.

Predicting Covid-19 emergency medical service incidents from daily hospitalisation trends

INTRODUCTION

The aim of our retrospective study was to quantify the impact of Covid-19 on the temporal distribution of emergency medical services (EMS) demand in Travis County, Austin, Texas and propose a robust model to forecast Covid-19 EMS incidents.

METHODS

We analysed the temporal distribution of EMS calls in the Austin-Travis County area between 1 January 2019 and 31 December 2020. Change point detection was performed to identify the critical dates marking changes in EMS call distributions, and time series regression was applied for forecasting Covid-19 EMS incidents.

RESULTS

Two critical dates marked the impact of Covid-19 on the distribution of EMS calls: March 17th, when the daily number of non-pandemic EMS incidents dropped significantly, and 13 May, by which the daily number of EMS calls climbed back to 75% of the number in pre-Covid-19 time. The new daily count of the hospitalisation of Covid-19 patients alone proves a powerful predictor of the number of pandemic EMS calls, with an r² value equal to 0.85. In particular, for every 2.5 cases, where EMS takes a Covid-19 patient to a hospital, one person is admitted.

CONCLUSION

The mean daily number of non-pandemic EMS demand was significantly less than the period before the Covid-19 pandemic. The number of EMS calls for Covid-19 symptoms can be predicted from the daily new hospitalisation of Covid-19 patients. These findings may be of interest to EMS departments as they plan for future pandemics, including the ability to predict pandemic-related calls in an effort to adjust a targeted response.

Diurnal Variation in SARS-CoV-2 PCR Test Results: Test Accuracy May Vary by Time of Day

False negative tests for SARS-CoV-2 are common and have important public health and medical implications. We tested the hypothesis of diurnal variation in viral shedding by assessing the proportion of positive versus negative SARS-CoV-2 reverse transcription polymerase chain reaction (RT-PCR) tests and cycle time (Ct) values among positive samples by the time of day. Among 86,342 clinical tests performed among symptomatic and asymptomatic patients in a regional health care network in the southeastern United States from March to August 2020, we found evidence for diurnal variation in the proportion of positive SARS-CoV-2 tests, with a peak around 1400 h and 1.7-fold variation over the day after adjustment for age, sex, race, testing location, month, and day of week and lower Ct values during the day for positive samples. These findings have important implications for public health testing and vaccination strategies.

Performance evaluation of Emergency Department patient arrivals forecasting models by including meteorological and calendar information: A comparative study

The volume of daily patient arrivals at Emergency Departments (EDs) is unpredictable and is a significant reason of ED crowding in hospitals worldwide. Timely forecast of patients arriving at ED can help the hospital management in early planning and avoiding of overcrowding. Many different ED patient arrivals forecasting models have previously been proposed by using time series analysis methods. Even though the time series methods such as Linear and Logistic Regression, Autoregressive Integrated Moving Average (ARIMA), Seasonal ARIMA (SARIMA), Exponential Smoothing (ES), and Artificial Neural Network (ANN) have been explored extensively for the ED forecasting model development, the few significant limitations of these methods associated in the analysis of time series data make the models inadequate in many practical situations. Therefore, in this paper, Machine Learning (ML)-based Random Forest (RF) regressor, and Deep Neural Network (DNN)-based Long Short-Term Memory (LSTM) and Convolutional Neural network (CNN) methods, which have not been explored to the same extent as the other time series techniques, are implemented by incorporating meteorological and calendar parameters for the development of forecasting models. The performances of the developed three models in forecasting ED patient arrivals are evaluated. Among the three models, CNN outperformed for short-term (3 days in advance) patient arrivals prediction with Mean Absolute Percentage Error (MAPE) of 9.24% and LSTM performed better for moderate-term (7 days in advance) patient arrivals prediction with MAPE of 8.91% using weather forecast information. Whereas, LSTM model outperformed with MAPE of 8.04% compared to 9.53% by CNN and 10.10% by RF model for current day prediction of patient arrivals using 3 days past weather information. Thus, for short-term ED patient arrivals forecasting, DNN-based model performed better compared to RF regressor ML-based model.

Forecasting emergency department hourly occupancy using time series analysis

STUDY OBJECTIVE

To develop a novel predictive model for emergency department (ED) hourly occupancy using readily available data at time of prediction with a time series analysis methodology.

METHODS

We performed a retrospective analysis of all ED visits from a large academic center during calendar year 2012 to predict ED hourly occupancy. Due to the time-of-day and day-of-week effects, a seasonal autoregressive integrated moving average with external regressor (SARIMAX) model was selected. For each hour of a day, a SARIMAX model was built to predict ED occupancy up to 4-h ahead. We compared the resulting model forecast accuracy and prediction intervals with previously studied time series forecasting methods.

RESULTS

The study population included 65,132 ED visits at a large academic medical center during the year 2012. All adult ED visits during the first 265 days were used as a training dataset, while the remaining ED visits comprised the testing dataset. A SARIMAX model performed best with external regressors of current ED occupancy, average department-wide ESI, and ED boarding total at predicting up to 4-h-ahead ED occupancy (Mean Square Error (MSE) of 16.20, and 64.47 for 1-hr- and 4-h- ahead occupancy, respectively). Our 24-SARIMAX model outperformed other popular time series forecasting techniques, including a 60% improvement in MSE over the commonly used rolling average method, while maintaining similar prediction intervals.

CONCLUSION

Accounting for current ED occupancy, average department-wide ESI, and boarding total, a 24-SARIMAX model was able to provide up to 4 h ahead predictions of ED occupancy with improved performance characteristics compared to other forecasting methods, including the rolling average. The prediction intervals generated by this method used data readily available in most EDs and suggest a promising new technique to forecast ED occupancy in real time.

Using Queue Theory and Load-Leveling Principles to Identify a Simple Metric for Resource Planning in a Pediatric Emergency Department

Increased waiting time in pediatric emergency departments is a well-recognized and complex problem in a resource-limited US health care system. Efforts to reduce emergency department wait times include modeling arrival rates, acuity, process flow, and human resource requirements. The aim of this study was to investigate queue theory and load-leveling principles to model arrival rates and to identify a simple metric for assisting with determination of optimal physical space and human resource requirements. We discovered that pediatric emergency department arrival rates vary based on time of day, day of the week, and month of the year in a predictable pattern and that the hourly change in pediatric emergency department waiting room census may be useful as a simple metric to identify target times for shifting resources to better match supply and demand at no additional cost.

A unified machine learning approach to time series forecasting applied to demand at emergency departments

BACKGROUND

There were 25.6 million attendances at Emergency Departments (EDs) in England in 2019 corresponding to an increase of 12 million attendances over the past ten years. The steadily rising demand at EDs creates a constant challenge to provide adequate quality of care while maintaining standards and productivity. Managing hospital demand effectively requires an adequate knowledge of the future rate of admission. We develop a novel predictive framework to understand the temporal dynamics of hospital demand.

METHODS

We compare and combine state-of-the-art forecasting methods to predict hospital demand 1, 3 or 7 days into the future. In particular, our analysis compares machine learning algorithms to more traditional linear models as measured in a mean absolute error (MAE) and we consider two different hyperparameter tuning methods, enabling a faster deployment of our models without compromising performance. We believe our framework can readily be used to forecast a wide range of policy relevant indicators.

RESULTS

We find that linear models often outperform machine learning methods and that the quality of our predictions for any of the forecasting horizons of 1, 3 or 7 days are comparable as measured in MAE. Our approach is able to predict attendances at these emergency departments one day in advance up to a mean absolute error of ±14 and ±10 patients corresponding to a mean absolute percentage error of 6.8% and 8.6% respectively.

CONCLUSIONS

Simple linear methods like generalized linear models are often better or at least as good as ensemble learning methods like the gradient boosting or random forest algorithm. However, though sophisticated machine learning methods are not necessarily better than linear models, they improve the diversity of model predictions so that stacked predictions can be more robust than any single model including the best performing one.

Prediction of emergency department volume and severity during a novel virus pandemic: Experience from the COVID-19 pandemic

Background

During a novel virus pandemic, predicting emergency department (ED) volume is crucial for arranging the limited medical resources of hospitals for balancing the daily patient- and epidemic-related tasks in EDs. The goal of the current study was to detect specific patterns of change in ED volume and severity during a pandemic which would help to arrange medical staff and utilize facilities and resources in EDs in advance in the event of a future pandemic.

Methods

This was a retrospective study of the patients who visited our ED between November 1, 2019 and April 30, 2020. We evaluated the change in ED patient volume and complexity of patients in our medical record system. Patient volume and severity during various periods were identified and compared with data from the past 3 years and the period that SARS occurred.

Results

A reduction in ED volume was evident. The reduction began during the early epidemic period and increased rapidly during the peak period of the epidemic with the reduction continuing during the late epidemic period. No significant difference existed in the percentages of triage levels 1 and 2 between the periods. The admission rate, length of stay in the ED, and average number of patients with out-of-hospital cardiac arrest increased during the epidemic periods.

Conclusion

A significant reduction in ED volume during the COVID-19 pandemic was noted and a predictable pattern was found. This specific change in pattern in the ED volume may be useful for performing adjustments in EDs in the future during a novel virus pandemic. The severity of patients visiting the ED during epidemic periods was inconclusive.

Association Between Emergency Physician Length of Stay Rankings and Patient Characteristics

OBJECTIVE

Emergency physicians are commonly compared by their patients' length of stay (LOS). We test the hypothesis that LOS is associated with patient characteristics and that accounting for these features impacts physician LOS rankings.

METHODS

This was a retrospective observational study of all encounters at an emergency department in 2010 to 2015. We compared the characteristics of patients seen by physicians in different quartiles of LOS. Primary outcome was variation in patient characteristics at time of physician assignment (age, sex, comorbidities, Emergency Severity Index [ESI], and chief complaint) across LOS quartiles. We also quantified the change in LOS rankings after accounting for difference in characteristics of patients seen by different physicians.

RESULTS

A total of 264,776 encounters seen by 62 attending physicians met inclusion criteria. Physicians in the longest LOS quartile saw patients who were older (age = 49.1 vs 48.6 years, difference = +0.5 years, 95% confidence interval [CI] = 0.3 to 0.7) with more comorbidities (Gagne score = 1.3 vs. 0.9, difference = +0.4, 95% CI = 0.4 to 0.4) and higher acuity (ESI = 2.8 vs. 2.9, difference = -0.1, 95% CI = 0.1 to 0.1) than physicians in the shortest LOS quartile. The odds ratio (OR) of physicians in the longest LOS quartile seeing patients over age 50 compared to the shortest LOS quartile was 1.1 (95% CI = 1.0 to 1.1); the OR of physicians in the longest LOS quartile seeing patients with ESI of 1 or 2 was also 1.1 (95% CI = 1.0 to 1.1). Accounting for variation in patient characteristics seen by different physicians resulted in substantial reordering of physician LOS rankings: 62.9% (39/62) of physicians reclassified into a different quartile with mean absolute percentile change of 25.8 (95% CI = 20.3 to 31.3). A total of 62.5% (10/16) of physicians in the shortest LOS quartile and 56.3% (9/16) in the longest LOS quartile moved into a different quartile after accounting for variation in patient characteristics.

CONCLUSIONS

Length of stay was significantly associated with patient characteristics, and accounting for variation in patient characteristics resulted in substantial reordering of relative physician rankings by LOS. Comparisons of emergency physicians by LOS that do not account for patient characteristics should be reconsidered.

Impact of Ramadan on Emergency Department Patients Flow; a Cross-Sectional Study in UAE

Introduction:

Ramadan, the ninth month of the Islamic lunar calendar, is, to Muslims, the holiest month of the year. During this month, young, able-bodied Muslims are commanded to abstain from food and drink from dawn to dusk.

Objective:

The objective of the study is to analyze emergency department (ED) patients flow during the holy month of Ramadan and compare it to non-Ramadan days. We hypothesized that Ramadan would affect ED attendance by altering peak hours, and expected a dip in attendance around evening time (after sunset).

Methods:

In Abu Dhabi, United Arab Emirates, a retrospective study was conducted at a tertiary hospital (2014–2016). The data was strategically separated and patient presence was analyzed year-wise, weekday basis and based on the hourly presence of the patients in the ED of the chosen hospital.

Results:

A total of 45,116 ED’s patient visits were analyzed over the mentioned study period. There was a difference in the total volume of Ramadan and non-Ramadan patient between the years 2014–2016. In all of the years, the highest percentage of visits was during the non-Ramadan days and this had a small fluctuation from 53% in 2014 to 52% in 2016 (p=0.001). It was observed from the collected data that 53% of the patients were present in the hospital during the fasting hours whereas 47% were present during the non-fasting hours (p<0.001).

Conclusion:

We were successfully able to derive a pattern from the data of 3 years in relation to the patient flow in the ED of the hospital. Moreover, we observed the difference in the patient arrival pattern between the Ramadan and non-Ramadan days in the hospital along with the predominant categorization of patient chief complaints. Our study identified a unique pattern of ED hourly visits during Ramadan.

Peak Outpatient and Emergency Department Visit Forecasting for Patients With Chronic Respiratory Diseases Using Machine Learning Methods: Retrospective Cohort Study

BACKGROUND

The overcrowding of hospital outpatient and emergency departments (OEDs) due to chronic respiratory diseases in certain weather or under certain environmental pollution conditions results in the degradation in quality of medical care, and even limits its availability.

OBJECTIVE

To help OED managers to schedule medical resource allocation during times of excessive health care demands after short-term fluctuations in air pollution and weather, we employed machine learning (ML) methods to predict the peak OED arrivals of patients with chronic respiratory diseases.

METHODS

In this paper, we first identified 13,218 visits from patients with chronic respiratory diseases to OEDs in hospitals from January 1, 2016, to December 31, 2017. Then, we divided the data into three datasets: weather-based visits, air quality-based visits, and weather air quality-based visits. Finally, we developed ML methods to predict the peak event (peak demand days) of patients with chronic respiratory diseases (eg, asthma, respiratory infection, and chronic obstructive pulmonary disease) visiting OEDs on the three weather data and environmental pollution datasets in Guangzhou, China.

RESULTS

The adaptive boosting-based neural networks, tree bag, and random forest achieved the biggest receiver operating characteristic area under the curve, 0.698, 0.714, and 0.809, on the air quality dataset, the weather dataset, and weather air quality dataset, respectively. Overall, random forests reached the best classification prediction performance.

CONCLUSIONS

The proposed ML methods may act as a useful tool to adapt medical services in advance by predicting the peak of OED arrivals. Further, the developed ML methods are generic enough to cope with similar medical scenarios, provided that the data is available.

Association of Clinical Characteristics With Variation in Emergency Physician Preferences for Patients

Importance

Much of the wide variation in health care has been associated with practice variation among physicians. Physicians choosing to see patients with more (or fewer) care needs could also produce variations in care observed across physicians.

Objective

To quantify emergency physician preferences by measuring nonrandom variations in patients they choose to see.

Design, Setting, and Participants

This cross-sectional study used a large, detailed clinical data set from an electronic health record system of a single academic hospital. The data set included all emergency department (ED) encounters of adult patients from January 1, 2010, to May 31, 2015, as well as ED visits information. Data were analyzed from September 1, 2018, to March 31, 2019.

Exposure

Patient assignment to a particular emergency physician.

Main Outcomes and Measures

Variation in patient characteristics (age, sex, acuity [Emergency Severity Index score], and comorbidities) seen by emergency physicians before patient selection, adjusted for temporal factors (seasonal, weekly, and hourly variation in patient mix).

Results

This study analyzed 294 915 visits to the ED seen by 62 attending physicians. Of the 294 915 patients seen, the mean (SD) age was 48.6 (19.8) years and 176 690 patients (59.9%) were women. Many patient characteristics, such as age (F = 2.2; P < .001), comorbidities (F = 1.7; P < .001), and acuity (F = 4.7; P < .001), varied statistically significantly. Compared with the lowest-quintile physicians for each respective characteristic, the highest-quintile physicians saw patients who were older (mean age, 47.9 [95% CI, 47.8-48.1] vs 49.7 [95% CI, 49.5-49.9] years, respectively; difference, +1.8 years; 95% CI, 1.5-2.0 years) and sicker (mean comorbidity score: 0.4 [95% CI, 0.3-0.5] vs 1.8 [95% CI, 1.7-1.8], respectively; difference, +1.3; 95% CI, 1.2-1.4). These differences were absent or highly attenuated during overnight shifts, when only 1 physician was on duty and there was limited room for patient selection. Compared with earlier in the shift, the same physician later in the shift saw patients who were younger (mean age, 49.7 [95% CI, 49.4-49.7] vs 44.6 [95 % CI, 44.3-44.9] years, respectively; difference, -5.1 years; 95% CI, 4.8-5.5) and less sick (mean comorbidity score: 0.7 [95% CI, 0.7-0.8] vs 1.1 [95% CI, 1.1-1.1], respectively; difference, -0.4; 95% CI, 0.4-0.4). Accounting for preference variation resulted in substantial reordering of physician ranking by care intensity, as measured by ED charges, with 48 of 62 physicians (77%) being reclassified into a different quintile and 9 of 12 physicians (75%) in the highest care intensity quintile moving into a lower quintile. A regression model demonstrated that 22% of reported ED charges were associated with physician preference.

Conclusions and Relevance

This study found preference variation across physicians and within physicians during the course of a shift. These findings suggest that current efforts to reduce practice variation may not affect the variation associated with physician preferences, which reflect underlying differences in patient needs and not physician practice.

Emergency Department Capacity Planning: A Recurrent Neural Network and Simulation Approach

Emergency departments (EDs) play a vital role in the whole healthcare system as they are the first point of care in hospitals for urgent and critically ill patients. Therefore, effective management of hospital's ED is crucial in improving the quality of the healthcare service. The effectiveness depends on how efficiently the hospital resources are used, particularly under budget constraints. Simulation modeling is one of the best methods to optimize resources and needs inputs such as patients' arrival time, patient's length of stay (LOS), and the route of patients in the ED. This study develops a simulation model to determine the optimum number of beds in an ED by minimizing the patients' LOS. The hospital data are analyzed, and patients' LOS and the route of patients in the ED are determined. To determine patients' arrival times, the features associated with patients' arrivals at ED are identified. Mean arrival rate is used as a feature in addition to climatic and temporal variables. The exhaustive feature-selection method has been used to determine the best subset of the features, and the mean arrival rate is determined as one of the most significant features. This study is executed using the one-year ED arrival data together with five-year (43.824 study hours) ED arrival data to improve the accuracy of predictions. Furthermore, ten different machine learning (ML) algorithms are used utilizing the same best subset of these features. After a tenfold cross-validation experiment, based on mean absolute percentage error (MAPE), the stateful long short-term memory (LSTM) model performed better than other models with an accuracy of 47%, followed by the decision tree and random forest methods. Using the simulation method, the LOS has been minimized by 7% and the number of beds at the ED has been optimized.

The Application of GSCM in Eliminating Healthcare Waste: Hospital EDC as an Example

Eliminating unnecessary healthcare waste in hospitals and providing better healthcare quality are the core issues of green supply chain management (GSCM). Hence, this study used a hospital's emergency department crowding (EDC) problem to illustrate how to establish an emergency medicine service (EMS) simulation system to obtain a robust parameters setting for solving hospitals' EDC and waste problems, thereby increasing healthcare quality. Inappropriate resource allocation results in more serious EDC; more serious EDC results in increasing operating costs. Therefore, in the healthcare system, waste includes inappropriate costs and inappropriate resource allocation. The EMS of a medical center in central Taiwan was the object of the study. In this study, the dynamic Taguchi method was used to set the signal factor, noise factor, and control factors to simulate the EMS system to obtain the optimal parameters setting. The performance was set to Emergency Department Work Index (EDWINC) and system time (waiting time and service time) per patient. The signal factor was set to the number of physicians; the noise factor was set to patient arrival rate; the control factors included persuading Triage 4 and Triage 5 outpatients, checkup process, bed occupation rate in the emergency department (ED), and medical checkup sequence for Triage 4 and Triage 5 patients. This study makes two significant contributions. First, the study introduces the GSCM concept to the healthcare setting to bring green innovation to hospitals. Hospital administrators may hence design better GSCM activities to facilitate healthcare processes to provide better healthcare outcomes. Second, the study applied the dynamic Taguchi method to the EMS and neural network (NN) to construct a computational model revealing the cause (factors) and effect (performances) relationship. In addition, the genetic algorithm (GA), a solution method, was used to obtain the optimal parameters setting of the EDC in Taiwan. Hence, after obtaining the solutions, the unnecessary waste in EDC-inappropriate costs and inappropriate resource allocation-is reduced.

Productivity-driven physician scheduling in emergency departments

The objective of this study is two-fold: to propose an alternative approach for computing the productivity of physicians in emergency departments (EDs); and, to allocate productivity-driven schedules to ED physicians so as to align physician productivity with demand (patient arrivals), without decreasing fairness between physicians, in order to improve patient wait times. Historical data between 2008 and 2017 from the Sacré-Coeur Montreal Hospital ED is analysed and used to predict the demand and to estimate the productivity of each physician. These estimates are incorporated into a mathematical programming model that identifies feasible schedules to physicians that minimise the difference between patients' demand and physicians' productivity, along with the violation of physicians' preferences and fairness in the distribution of shifts. Results on real-world-based data show that when physician productivity is included in the allocation of schedules, demand under-covering is reduced by 10.85% and the fairness between physicians is maintained. However, physicians' preferences (e.g., sum of the differences between the number of wanted shifts and the number of allocated shifts) deteriorates by 7.61%. By incorporating the productivity of physicians in the scheduling process, we see a reduction in EDs overcrowding and an improvement in the overall quality of health-care services.

Patient classification based on volume and case-mix in the emergency department and their association with performance

Predicting daily patient volume is necessary for emergency department (ED) strategic and operational decisions, such as resource planning and workforce scheduling. For these purposes, forecast accuracy requires understanding the heterogeneity among patients with respect to their characteristics and reasons for visits. To capture the heterogeneity among ED patients (case-mix), we present a patient coding and classification scheme (PCCS) based on patient demographics and diagnostic information. The proposed PCCS allows us to mathematically formalize the arrival patterns of the patient population as well as each class of patients. We can then examine the volume and case-mix of patients presenting to an ED and investigate their relationship to the ED's quality and time-based performance metrics. We use data from five hospitals in February, July and November for the years of 2007, 2012, and 2017 in the city of Calgary, Alberta, Canada. We find meaningful arrival time patterns of the patient population as well as classes of patients in EDs. The regression results suggest that patient volume is the main predictor of time-based ED performance measures. Case-mix is, however, the key predictor of quality of care in EDs. We conclude that considering both patient volume and the mix of patients are necessary for more accurate strategic and operational planning in EDs.

Real-time forecasting of emergency department arrivals using prehospital data

Background

Crowding in emergency departments (EDs) is a challenge globally. To counteract crowding in day-to-day operations, better tools to improve monitoring of the patient flow in the ED is needed. The objective of this study was the development of a continuously updated monitoring system to forecast emergency department (ED) arrivals on a short time-horizon incorporating data from prehospital services.

Methods

Time of notification and ED arrival was obtained for all 191,939 arrivals at the ED of a Norwegian university hospital from 2010 to 2018. An arrival notification was an automatically captured time stamp which indicated the first time the ED was notified of an arriving patient, typically by a call from an ambulance to the emergency service communication center. A Poisson time-series regression model for forecasting the number of arrivals on a 1-, 2- and 3-h horizon with continuous weekly and yearly cyclic effects was implemented. We incorporated time of arrival notification by modelling time to arrival as a time varying hazard function. We validated the model on the last full year of data.

Results

In our data, 20% of the arrivals had been notified more than 1 hour prior to arrival. By incorporating time of notification into the forecasting model, we saw a substantial improvement in forecasting accuracy, especially on a one-hour horizon. In terms of mean absolute prediction error, we observed around a six percentage-point decrease compared to a simplified prediction model. The increase in accuracy was particularly large for periods with large inflow.

Conclusions

The proposed model shows increased predictability in ED patient inflow when incorporating data on patient notifications. This approach to forecasting arrivals can be a valuable tool for logistic, decision making and ED resource management.

Electronic supplementary material

The online version of this article (10.1186/s12873-019-0256-z) contains supplementary material, which is available to authorized users.

Parallel Simulation Decision-Making Method for a Response to Unconventional Public Health Emergencies Based on the Scenario–Response Paradigm and Discrete Event System Theory

Given the non-repeatability, complexity, and unpredictability of unconventional public health emergencies, building accurate models and making effective response decisions based only on traditional prediction–response decision-making methods are difficult. To solve this problem, under the scenario–response paradigm and theories on parallel emergency management and discrete event system (DES), the parallel simulation decision-making framework (PSDF), which includes the methods of abstract modeling, simulation operation, decision-making optimization, and parallel control, is proposed for unconventional public health emergency response processes. Furthermore, with the example of the severe acute respiratory syndrome (SARS) response process, the evolutionary scenarios that include infected patients and diagnostic processes are transformed into simulation processes. Then, the validity and operability of the DES–PSDF method proposed in this paper are verified by the results of a simulation experiment. The results demonstrated that, in the case of insufficient prior knowledge, effective parallel simulation models can be constructed and improved dynamically by multi-stage parallel controlling. Public health system bottlenecks and relevant effective response solutions can also be obtained by iterative simulation and optimizing decisions. To meet the urgent requirements of emergency response, the DES–PSDF method introduces a new response decision-making concept for unconventional public health emergencies.

An approach by human and material resources combination to reduce hospitals crowding

Purpose

This paper aims to propose an approach by human and material resources combination to reduce hospitals crowding. Hospitals crowding is becoming a serious problem. Many research works present several methods and approaches to deal with this problem. However, to the best of the authors’ knowledge – after a deep reading of literature – in all the proposed approaches, human and material resources are studied separately while they must be combined (to a given number of material resources an optimal number of human resources must be assigned and vice versa) to reflect reality and provide better results.

Design/methodology/approach

Hospital inpatient unit is chosen as framework. This unit crowding reduction is carried out by its capacity increasing. Indeed, inpatient unit modeling is performed to find the adequate combinations of human and material resources numbers insuring this unit stability and providing optimal service rates. At first, inpatient unit is modeled using queuing networks and considering only two resources (beds and nurses). Then, the obtained service rate formula is improved by including other resources and parameters using Baskett, Chandy, Muntz and Palecios (BCMP) queuing networks. This work is applied to “Princess Lalla Meryem” hospital inpatient unit.

Findings

Results are patients’ average number reduction by an average (in each block) of three patients, patients’ average waiting time reduction by an average of 9.98 h and non-admitted patients (to inpatient wards) access percentage of 39.26 per cent on average.

Originality/value

Previous works focus their studies on either human resources or material resources. Only a few works study both resources types, but separately. The context of those studies does not meet the real hospital context (where human resources are combined with material resources). Therefore, the provided results are not very reliable. In this paper, an approach by human and material resources combination is proposed to increase inpatient unit care capacity. Indeed, this approach consists of developing inpatient unit service rate formula in terms of human and material resources numbers.

An exhaustive review and analysis on applications of statistical forecasting in hospital emergency departments

Emergency departments (EDs) provide medical treatment for a broad spectrum of illnesses and injuries to patients who arrive at all hours of the day. The quality and efficient delivery of health care in EDs are associated with a number of factors, such as patient overall length of stay (LOS) and admission, prompt ambulance diversion, quick and accurate triage, nurse and physician assessment, diagnostic and laboratory services, consultations and treatment. One of the most important ways to plan the healthcare delivery efficiently is to make forecasts of ED processes. The aim this study is thus to provide an exhaustive review for ED stakeholders interested in applying forecasting methods to their ED processes. A categorisation, analysis and interpretation of 102 papers is performed for review. This exhaustive review provides an insight for researchers and practitioners about forecasting in EDs in terms of showing current state and potential areas for future attempts.

Applying sequential pattern mining to investigate cerebrovascular health outpatients' re-visit patterns

BACKGROUND AND OBJECTIVE

Increases in outpatients seeking medical check-ups are expanding the number of health examination data records, which can be utilized for medical strategic planning and other purposes. However, because hospital visits by outpatients seeking medical check-ups are unpredictable, those patients often cannot receive optimal service due to limited facilities of hospitals. To resolve this problem, this study attempted to predict re-visit patterns of outpatients.

METHOD

Two-phase sequential pattern mining (SPM) and an association mining method were chosen to predict patient returns using sequential data. The data were grouped according to the outpatients' personal information and evaluated by a discriminant analysis to check the significance of the grouping. Furthermore, SPM was employed to generate frequency patterns from each group and extract a general association pattern of return.

RESULTS

Results of sequence patterns and association mining in this study provided valuable insights in terms of outpatients' re-visit behaviors for regular medical check-ups. Cosine and Jaccard are two symmetric measures which were used in this study to indicate the degree of association between two variables. For instance, Jaccard values of variable abnormal blood pressure associated with an abnormal body-mass index (BMI) and/or abnormal blood sugar were respectively 47.5% and 100%, for the two-visit and three-visit behavior patterns. These results indicated that the corresponding pair of variables was more reliable when covering the three-visit behavior pattern than the two-visit behavior. Thus, appropriate preventive measures or suggestions for other medical treatments can be prepared for outpatients that have this pattern on their third visit. The higher degree of association implies that the corresponding behavior pattern might influence outpatients' intentions to regularly seek medical check-ups concerning the risk of stroke. Furthermore, a radiology diagnosis (i.e., magnetic resonance imaging or neck vascular ultrasound) plays an important role in the association with a re-visit behavior pattern with respective 50% and 70% Cosine and Jaccard values in general behavior {f11}∧{f01}. These findings can serve as valuable information to increase the quality of medical services and marketing, by suggesting appropriate treatment for the subsequent visit after learning the behavior patterns.

CONCLUSIONS

The proposed method can provide valuable information related to outpatients' re-visit behavior patterns based on hidden knowledge generated from sequential patterns and association mining results. For marketing purposes, medical practitioners can take behavior patterns studied in this paper into account to raise patients' awareness of several possible medical conditions that might arise on subsequent visits and encourage them to take preventive measures or suggest other medical treatments.

Emergency department arrival times in Florida heart failure patients utilizing Fisher-Rao curve registration: A descriptive population-based study

BACKGROUND

Emergency room utilization and hospital readmission rates are disproportionately high for heart failure patients (HF). Emergency department (ED) utilization is intimately intertwined with hospital readmissions.

OBJECTIVE

Describe the arrival time distribution of HF patients presenting to the ED.

METHOD

The study analyzed heart failure discharge data from the Florida State Emergency Department Database and the Florida State Inpatient Database from the Healthcare Cost and Utilization Project of the Agency for Healthcare Research and Quality. Data were treated as a Poisson process and analyzed using functional data analysis tools.

RESULTS

HF arrivals are multi-modal with the largest peak arrival time in the middle of the day as well as a smaller peak in the early morning hours, especially in rural areas.

CONCLUSIONS

The arrival pattern has minor differences in rural and urban areas. HF clinic appointments should be established in the early morning hours when these patients utilize the ED.

A study on the impact of prioritising emergency department arrivals on the patient waiting time

In the past decade, the crowding of the emergency department has gained considerable attention of researchers as the number of medical service providers is typically insufficient to fulfil the demand for emergency care. In this paper, we solve the stochastic emergency department workforce planning problem and consider the planning of nurses and physicians simultaneously for a real-life case study in Belgium. We study the patient arrival pattern of the emergency department in depth and consider different patient acuity classes by disaggregating the arrival pattern. We determine the personnel staffing requirements and the design of the shifts based on the patient arrival rates per acuity class such that the resource staffing cost and the weighted patient waiting time are minimised. In order to solve this multi-objective optimisation problem, we construct a Pareto set of optimal solutions via the 𝜖-constraints method. For a particular staffing composition, the proposed model minimises the patient waiting time subject to upper bounds on the staffing size using the Sample Average Approximation Method. In our computational experiments, we discern the impact of prioritising the emergency department arrivals. Triaging results in lower patient waiting times for higher priority acuity classes and to a higher waiting time for the lowest priority class, which does not require immediate care. Moreover, we perform a sensitivity analysis to verify the impact of the arrival and service pattern characteristics, the prioritisation weights between different acuity classes and the incorporated shift flexibility in the model.

The relationship between emergency department volume and patient complexity

INTRODUCTION

Forecasting emergency department (ED) visits is a well-studied topic. The importance of understanding the complexity of patients along with the days and times of varying patient volumes is critical for planning medical and ancillary staffing. Though multiple studies stratify their results based on severity of disease, severity was determined by triage status. The goal of this study was to utilize a novel method to evaluate the correlation between daily emergency department patient complexity, based on Current Procedure Terminology (CPT) code, and day of the week.

METHODS

This was a retrospective study of subjects presenting to the ED between January 1, 2010 and December 31, 2015. We identified the correlation between subjects with each CPT code who were evaluated on a specific day of the week and evaluated the day before, the day of and the day after a legal holiday.

RESULTS

During the study period 312,550 (48%) male and 336,348 (52%) female subjects were identified. No correlation between daily ED patient complexity, based on CPT code, and day of the week (p=0.75) or any legal holidays were identified. Individual significant differences were noted among day of the week and particular CPT code as well as legal holiday and particular CPT code with no appreciable trend or pattern.

CONCLUSIONS

There was no correlation between daily ED patient complexity based on CPT code and day of the week or daily ED patient acuity and legal holiday. In light of these data, emergency department staffing and resource allocation patterns may need to be revisited.

A universal deep learning approach for modeling the flow of patients under different severities

BACKGROUND AND OBJECTIVE

The Accident and Emergency Department (A&ED) is the frontline for providing emergency care in hospitals. Unfortunately, relative A&ED resources have failed to keep up with continuously increasing demand in recent years, which leads to overcrowding in A&ED. Knowing the fluctuation of patient arrival volume in advance is a significant premise to relieve this pressure. Based on this motivation, the objective of this study is to explore an integrated framework with high accuracy for predicting A&ED patient flow under different triage levels, by combining a novel feature selection process with deep neural networks.

METHODS

Administrative data is collected from an actual A&ED and categorized into five groups based on different triage levels. A genetic algorithm (GA)-based feature selection algorithm is improved and implemented as a pre-processing step for this time-series prediction problem, in order to explore key features affecting patient flow. In our improved GA, a fitness-based crossover is proposed to maintain the joint information of multiple features during iterative process, instead of traditional point-based crossover. Deep neural networks (DNN) is employed as the prediction model to utilize their universal adaptability and high flexibility. In the model-training process, the learning algorithm is well-configured based on a parallel stochastic gradient descent algorithm. Two effective regularization strategies are integrated in one DNN framework to avoid overfitting. All introduced hyper-parameters are optimized efficiently by grid-search in one pass.

RESULTS

As for feature selection, our improved GA-based feature selection algorithm has outperformed a typical GA and four state-of-the-art feature selection algorithms (mRMR, SAFS, VIFR, and CFR). As for the prediction accuracy of proposed integrated framework, compared with other frequently used statistical models (GLM, seasonal-ARIMA, ARIMAX, and ANN) and modern machine models (SVM-RBF, SVM-linear, RF, and R-LASSO), the proposed integrated "DNN-I-GA" framework achieves higher prediction accuracy on both MAPE and RMSE metrics in pairwise comparisons.

CONCLUSIONS

The contribution of our study is two-fold. Theoretically, the traditional GA-based feature selection process is improved to have less hyper-parameters and higher efficiency, and the joint information of multiple features is maintained by fitness-based crossover operator. The universal property of DNN is further enhanced by merging different regularization strategies. Practically, features selected by our improved GA can be used to acquire an underlying relationship between patient flows and input features. Predictive values are significant indicators of patients' demand and can be used by A&ED managers to make resource planning and allocation. High accuracy achieved by the present framework in different cases enhances the reliability of downstream decision makings.

Hospital Surge Capacity: A Web-Based Simulation Tool for Emergency Planners

The National Center for the Study of Preparedness and Catastrophic Event Response (PACER) has created a publicly available simulation tool called Surge (accessible at http://www.pacerapps.org) to estimate surge capacity for user-defined hospitals. Based on user input, a Monte Carlo simulation algorithm forecasts available hospital bed capacity over a 7-day period and iteratively assesses the ability to accommodate disaster patients. Currently, the tool can simulate bed capacity for acute mass casualty events (such as explosions) only and does not specifically simulate staff and supply inventory. Strategies to expand hospital capacity, such as (1) opening unlicensed beds, (2) canceling elective admissions, and (3) implementing reverse triage, can be interactively evaluated. In the present application of the tool, various response strategies were systematically investigated for 3 nationally representative hospital settings (large urban, midsize community, small rural). The simulation experiments estimated baseline surge capacity between 7% (large hospitals) and 22% (small hospitals) of staffed beds. Combining all response strategies simulated surge capacity between 30% and 40% of staffed beds. Response strategies were more impactful in the large urban hospital simulation owing to higher baseline occupancy and greater proportion of elective admissions. The publicly available Surge tool enables proactive assessment of hospital surge capacity to support improved decision-making for disaster response. (Disaster Med Public Health Preparedness. 2018;12:513–522)

Predicting Urban Medical Services Demand in China: An Improved Grey Markov Chain Model by Taylor Approximation

The sharp increase of the aging population has raised the pressure on the current limited medical resources in China. To better allocate resources, a more accurate prediction on medical service demand is very urgently needed. This study aims to improve the prediction on medical services demand in China. To achieve this aim, the study combines Taylor Approximation into the Grey Markov Chain model, and develops a new model named Taylor-Markov Chain GM (1,1) (T-MCGM (1,1)). The new model has been tested by adopting the historical data, which includes the medical service on treatment of diabetes, heart disease, and cerebrovascular disease from 1997 to 2015 in China. The model provides a predication on medical service demand of these three types of disease up to 2022. The results reveal an enormous growth of urban medical service demand in the future. The findings provide practical implications for the Health Administrative Department to allocate medical resources, and help hospitals to manage investments on medical facilities.

Early Detection of Peak Demand Days of Chronic Respiratory Diseases Emergency Department Visits Using Artificial Neural Networks

Chronic respiratory diseases, mainly asthma and chronic obstructive pulmonary disease (COPD), affect the lives of people by limiting their activities in various aspects. Overcrowding of hospital emergency departments (EDs) due to respiratory diseases in certain weather and environmental pollution conditions results in the degradation of quality of medical care, and even limits its availability. A useful tool for ED managers would be to forecast peak demand days so that they can take steps to improve the availability of medical care. In this paper, we developed an artificial neural network based classifier using multilayer perceptron with back propagation algorithm that predicts peak event (peak demand days) of patients with respiratory diseases, mainly asthma and COPD visiting EDs in Dallas County of Texas in the United States. The precision and recall for peak event class were 77.1% and 78.0%, respectively, and those for nonpeak events were 83.9% and 83.2%, respectively. The overall accuracy of the system is 81.0%.

Simulation to Predict Effect of Citywide Events on Emergency Department Operations

Medical emergency preparedness has been an issue of medical relevance since the advent of hospital care. Studies have simulated emergency department (ED) overcrowding but not yet characterized effects of large-scale, planned events that drastically alter a city's demography, such as in Philadelphia, Pennsylvania during the 2015 World Meeting of Families. A discrete event simulation of the ED at the Children's Hospital of Philadelphia was designed and validated using past data. The model was used to predict the patient length of stay (LOS) and number of admitted patients if the arrival stream to the ED were to change by 50% from typical arrivals in either direction. We compared the model's estimations with data produced during the papal visit that had 39.65% fewer patient arrivals. For validation, the simulated mean LOS was 226.1 ± 173.3 minutes (mean ± SD) for all patients and 352.1 ± 170.3 minutes for admitted patients. Real-world mean LOSs for the fiscal year 2014 were 230.6 ± 134.8 for all patients and 345.0 ± 147.7 for admitted patients. For the estimation of the World Meeting of Families, the simulation accurately estimated the LOS of both patients overall and admitted patients within 10%. These results show that it is possible to use simulations to project the patient flow effects in EDs in case of large-scale events. Providing efficient care is essential to emergency operations, and projections of demand are crucial for targeting appropriate changes during large-scale events. Analysis of validated computer simulations allows for evidence-based decision making in a complex clinical environment.

Circadian variability of the initial Glasgow Coma Scale score in traumatic brain injury patients

INTRODUCTION

The Glasgow Coma Scale (GCS) score is the primary method of assessing consciousness after traumatic brain injury (TBI), and the clinical standard for classifying TBI severity. There is scant literature discerning the influence of circadian rhythms or emergency department (ED) arrival hour on this important clinical tool.

METHODS

Retrospective cohort analysis of adult patients suffering blunt TBI using the National Sample Program of the National Trauma Data Bank, years 2003-2006. ED arrival GCS score was characterized by midday (10 a.m.-4 p.m.) and midnight (12 a.m.-6 a.m.) cohorts (N=24548). Proportions and standard errors are reported for descriptive data. Multivariable regressions using odds ratios (OR), mean differences (B), and their associated 95% confidence intervals [CI] were performed to assess associations between ED arrival hour and GCS score. Statistical significance was assessed at p<0.05.

RESULTS

Patients were 42.48±0.13-years-old and 69.5% male. GCS score was 12.68±0.13 (77.2% mild, 5.2% moderate, 17.6% severe-TBI). Overall, patients were injured primarily via motor vehicle accidents (52.2%) and falls (24.2%), and 85.7% were admitted to hospital (33.5% ICU). Injury severity score did not differ between day and nighttime admissions.Nighttime admissions associated with decreased systemic comorbidities (p<0.001) and increased likelihood of alcohol abuse and drug intoxication (p<0.001). GCS score demonstrated circadian rhythmicity with peak at 12 p.m. (13.03±0.08) and nadir at 4am (12.12±0.12). Midnight patients demonstrated lower GCS (12 a.m.-6 a.m.: 12.23±0.04; 10 a.m.-4 p.m.: 12.95±0.03, p<0.001). Multivariable regression adjusted for demographic and injury factors confirmed that midnight-hours independently associated with decreased GCS (B=-0.29 [-0.40, -0.19]).In patients who did not die in ED or go directly to surgery (N=21862), midnight-hours (multivariable OR 1.73 [1.30-2.31]) associated with increased likelihood of ICU admission; increasing GCS score (per-unit OR 0.82 [0.80-0.83]) associated with decreased odds. Notably, the interaction factor ED GCS score*ED arrival hour independently demonstrated OR 0.96 [0.94-0.98], suggesting that the influence of GCS score on ICU admission odds is less important at night than during the day.

CONCLUSIONS

Nighttime TBI patients present with decreased GCS scores and are admitted to ICU at higher rates, yet have fewer prior comorbidities and similar systemic injuries. The interaction between nighttime hours and decreased GCS score on ICU admissions has important implications for clinical assessment/triage.

Retrospective one-million-subject fixed-cohort survey of utilization of emergency departments due to traumatic causes in Taiwan, 2001-2010

BACKGROUND

Epidemiological study was needed to evaluate trends in emergency department (ED) utilization that could be taken into account when making policy decisions regarding the delivery and distribution of medical resources.

METHODS

A retrospective fixed-cohort study of emergency medical utilization from 2001 to 2010 was performed based on one-million people sampled in 2010 in Taiwan. Focusing on traumatic cases, the annual incidences in various groups split according to sex and age were calculated, and further information regarding location of trauma and type of trauma was obtained.

RESULTS

In 2010, significantly greater proportions of male and younger subjects were visitors to EDs with a traumatic injury. During 2001-2010, the number of both traumatic cases and non-traumatic cases presenting at EDs significantly increased (average annual percentage change, AAPC 4.7 and 3.6, respectively) and a significantly greater direct medical cost associated with traumatic cases than non-traumatic cases was noted. Focusing on traumatic cases, most of these cases were directed to highest-level hospitals, accounting for 73.5-78.8 % of all traumatic cases, with a significant AAPC of 5.6. The traumatic ED visit annual incidence in males was 58.63 in 2001, which significantly increased to 69.35 per 1000 persons in 2010 (AAPC 1.5); and in females was 38.96 in 2001, which significantly increased to 50.73 per 1000 persons in 2010 (AAPC 2.5). Most of the traumatic cases treated in EDs were minor injuries, such as contusion with the skin intact, open wound of the upper limbs, open wound of the head, neck, or trunk, and other superficial injury (accounting for about 60 % of all cases). The traumatic categories of sprains/strains of joints and adjacent muscles, fractures of upper limbs, fractures of lower limbs, and fractures of the spine/trunk required greater medical resources and significantly positive AAPC values (4.3, 4.0, 4.5 and 6.8, respectively).

CONCLUSIONS

Increased ED utilization due to traumatic causes, as assessed by the annual number of cases and incidence, average direct medical cost and highest-level hospital utilization, was observed from 2001 to 2010. Orthopedic-related injuries, including soft tissue trauma of extremities and various fractures, were the categories with the greatest increase in incidence.

Real-time prediction of inpatient length of stay for discharge prioritization

OBJECTIVE

Hospitals are challenged to provide timely patient care while maintaining high resource utilization. This has prompted hospital initiatives to increase patient flow and minimize nonvalue added care time. Real-time demand capacity management (RTDC) is one such initiative whereby clinicians convene each morning to predict patients able to leave the same day and prioritize their remaining tasks for early discharge. Our objective is to automate and improve these discharge predictions by applying supervised machine learning methods to readily available health information.

MATERIALS AND METHODS

The authors use supervised machine learning methods to predict patients' likelihood of discharge by 2 p.m. and by midnight each day for an inpatient medical unit. Using data collected over 8000 patient stays and 20 000 patient days, the predictive performance of the model is compared to clinicians using sensitivity, specificity, Youden's Index (i.e., sensitivity + specificity - 1), and aggregate accuracy measures.

RESULTS

The model compared to clinician predictions demonstrated significantly higher sensitivity (P < .01), lower specificity (P < .01), and a comparable Youden Index (P > .10). Early discharges were less predictable than midnight discharges. The model was more accurate than clinicians in predicting the total number of daily discharges and capable of ranking patients closest to future discharge.

CONCLUSIONS

There is potential to use readily available health information to predict daily patient discharges with accuracies comparable to clinician predictions. This approach may be used to automate and support daily RTDC predictions aimed at improving patient flow.