Long-term prediction of emergency department revenue and visitor volume using autoregressive integrated moving average model

A systematic review of the modelling of patient arrivals in emergency departments

Background

Accident and Emergency Department (AED) is the frontline of providing emergency care in a hospital and research focusing on improving decision-makings and service level around AED has been driving a rising number of attentions in recent years. A retrospective review among the published papers shows that related research can be classified according to six planning modules: demand forecasting, days-off scheduling, shift scheduling, line-of-work construction, task assignment and staff assignment. As patient arrivals demand forecasts enable smooth AED operational planning and help decision-making, this article conducted a systematic review on the statistical modelling approaches aimed at predicting the volume of AED patients' arrival.

Methods

We carried out a systematic review of AED patient arrivals prediction studies from 2004 to 2021. The Medline, ScienceDirect, and Scopus databases were searched. A two-step screening process was carried out based on the title and abstract or full text, and 35 of 1,677 articles were selected. Our methods and results follow the preferred reporting items for systematic reviews and meta-analyses (PRISMA) guidelines. We categorise AED methods for modelling patient arrivals into four main classes: regression, time series, artificial intelligence and time series regression. Choice of prediction model, selection of factors and model performance are compared. Finally, we discuss the advantages and limitations of the models and suggest future research directions.

Results

A total of 1,677 papers that fulfilled the initial searching criteria was obtained from the three databases. Based on the first exclusion criteria, 1,603 articles were eliminated. The remaining 74 full text articles were evaluated based on the second exclusion criteria. Finally, 35 articles were selected for full review. We find that the use of artificial intelligence-based model has risen in recent years, from the view of predictive model selection. The calendar-based factors are most commonly used compared with other types of dependent variables, from the view of dependent variable selection.

Conclusions

All AEDs are inherently different and different covariables may have different effects on patient arrivals. Certain factors may play a key role in one AED but not others. Based on results of meta-analysis, when modelling patient arrivals, it is essential to understand the actual AED situation and carefully select relevant dominating factors and the most suitable modelling method. Local calibration is also important to ensure good estimates.

Characteristics of emergency room visits in patients with facial injuries in mainland China during the 60-day level I emergency response to COVID-19

Chinese mainland launched the 60-day first-level response to major public health emergencies during the COVID-19 outbreak. This study aimed to determine the incidence and describe the characteristics and predictors of patients who presented to the emergency department (ED) with facial trauma during this period. A retrospective review was conducted on the basis of data on facial trauma presented at the ED of XXX Hospital from 24 January 2020 to 23 March 2020 and the same period in the previous two years. Multivariate linear regression model was employed to explore potential determinants associated with daily number of facial trauma. Significant reduction was observed in the amount of facial trauma during the COVID-19 level I emergency response. The trauma volume evenly distributed over the week. The declined most significantly by age group, 20-29 years, and by time range of visit, 00:00-08:00. Multivariate regression analyses revealed positive relationship between daily minimum temperature and facial trauma volume. The number of facial injuries decreased significantly during the COVID-19 Level 1 emergency response, with the least reduction in total daytime facial trauma and in infant and child facial trauma. And a higher minimum temperature may lead to increased number of facial trauma presentations.

Prediction of Daily Blood Sampling Room Visits Based on ARIMA and SES Model

This paper is aimed at establishing a combined prediction model to predict the demand for medical care in terms of daily visits in an outpatient blood sampling room, which provides a basis for rational arrangement of human resources and planning. On the basis of analyzing the comprehensive characteristics of the randomness, periodicity, trend, and day-of-the-week effects of the daily number of blood collections in the hospital, we firstly established an autoregressive integrated moving average model (ARIMA) model to capture the periodicity, volatility, and trend, and secondly, we constructed a simple exponential smoothing (SES) model considering the day-of-the-week effect. Finally, a combined prediction model of the residual correction is established based on the prediction results of the two models. The models are applied to data from 60 weeks of daily visits in the outpatient blood sampling room of a large hospital in Chengdu, for forecasting the daily number of blood collections about 1 week ahead. The result shows that the MAPE of the combined model is the smallest overall, of which the improvement during the weekend is obvious, indicating that the prediction error of extreme value is significantly reduced. The ARIMA model can extract the seasonal and nonseasonal components of the time series, and the SES model can capture the overall trend and the influence of regular changes in the time series, while the combined prediction model, taking into account the comprehensive characteristics of the time series data, has better fitting prediction accuracy than a single model. The new model can well realize the short-to-medium-term prediction of the daily number of blood collections one week in advance.

The Effects of Temperature on Accident and Emergency Department Attendances in London: A Time-Series Regression Analysis

The epidemiological research relating mortality and hospital admissions to ambient temperature is well established. However, less is known about the effect temperature has on Accident and Emergency (A&E) department attendances. Time-series regression analyses were conducted to investigate the effect of temperature for a range of cause- and age-specific attendances in Greater London (LD) between 2007 to 2012. A seasonally adjusted Poisson regression model was used to estimate the percent change in daily attendances per 1 °C increase in temperature. The risk of overall attendance increased by 1.0% (95% CI 0.8, 1.4) for all ages and 1.4% (1.2, 1.5) among 0- to 15-year-olds. A smaller but significant increase in risk was found for cardiac, respiratory, cerebrovascular and psychiatric presentations. Importantly, for fracture-related attendances, the risk rose by 1.1% (0.7, 1.5) per 1 °C increase in temperature above the identified temperature threshold of 16 °C, with the highest increase of 2.1% (1.5, 3.0) seen among 0- to 15-year-olds. There is a positive association between increasing temperatures and A&E department attendance, with the risk appearing highest in children and the most deprived areas. A&E departments are vulnerable to increased demand during hot weather and therefore need to be adequately prepared to address associated health risks posed by climate change.

Application of time series analysis in modelling and forecasting emergency department visits in a medical centre in Southern Taiwan

OBJECTIVE

Emergency department (ED) overcrowding is acknowledged as an increasingly important issue worldwide. Hospital managers are increasingly paying attention to ED crowding in order to provide higher quality medical services to patients. One of the crucial elements for a good management strategy is demand forecasting. Our study sought to construct an adequate model and to forecast monthly ED visits.

METHODS

We retrospectively gathered monthly ED visits from January 2009 to December 2016 to carry out a time series autoregressive integrated moving average (ARIMA) analysis. Initial development of the model was based on past ED visits from 2009 to 2016. A best-fit model was further employed to forecast the monthly data of ED visits for the next year (2016). Finally, we evaluated the predicted accuracy of the identified model with the mean absolute percentage error (MAPE). The software packages SAS/ETS V.9.4 and Office Excel 2016 were used for all statistical analyses.

RESULTS

A series of statistical tests showed that six models, including ARIMA (0, 0, 1), ARIMA (1, 0, 0), ARIMA (1, 0, 1), ARIMA (2, 0, 1), ARIMA (3, 0, 1) and ARIMA (5, 0, 1), were candidate models. The model that gave the minimum Akaike information criterion and Schwartz Bayesian criterion and followed the assumptions of residual independence was selected as the adequate model. Finally, a suitable ARIMA (0, 0, 1) structure, yielding a MAPE of 8.91%, was identified and obtained as Visit_t=7111.161+(a_t+0.37462 a_t-1).

CONCLUSION

The ARIMA (0, 0, 1) model can be considered adequate for predicting future ED visits, and its forecast results can be used to aid decision-making processes.

Direct medical costs of hospitalisations for mental disorders in Shanghai, China: a time series study

OBJECTIVES

To provide cost burden estimates and long-term trend forecast of mental disorders that need hospitalisations in Shanghai, China.

DESIGN

Daily hospital admissions and medical expenditures for mental disorder hospitalisations between 1 January 2011 and 31 December 2015 were used for analysis. Yearly total health expenditures and expenditures per hospital admission for different populations, as well as per-admission-per-year medical costs of each service for mental disorder hospitalisations, were estimated through data from 2015. We also established time series analyses to determine the long-time trend of total direct medical expenditures for mental disorders and forecasted expenditures until 31 December 2030.

SETTING

Shanghai, China.

PARTICIPANTS

Daily hospital admissions for mental disorders of registered residents living in all 16 districts of Shanghai, who participated in workers' basic medical insurance or the urban residents' basic medical insurance (n=60 306).

RESULTS

From 2011 to 2015, there were increased yearly trends for both hospitalisations (from 10 919 to 14 054) and total costs (from US$23.56 to 42.13 million per year in 2015 currency) in Shanghai. Cost per mental disorder hospitalisation in 2015 averaged US$2998.01. Most direct medical costs were spent on medical supplies. By the end of 2030, the average cost per admission per month for mental disorders was estimated to be US$7394.17 (95% CI US$6782.24 to 8006.10) for mental disorders, and the total health expenditure for mental disorders would reach over US$100.52 million (95% CI US$92.20 to 108.83 million) without additional government interventions.

CONCLUSIONS

These findings suggest total health expenditures for mental disorders in Shanghai will be higher in the future. Effective measures should be taken to reduce the rapid growth of the economic burden of mental disorders.

Implementing a novel model for hospice and palliative care in the emergency department: An experience from a tertiary medical center in Taiwan

Hospice and palliative care has been recognized as an essential part of emergency medicine; however, there is no consensus on the optimal model for the delivery of hospice and palliative care in the emergency department (ED). Therefore, we conducted a novel implementation in a tertiary medical center in Taiwan. In the preintervention period, we recruited a specialist for hospice and palliative medicine in the ED to lead our intervention. In the early stage of the intervention, starting on July 1, 2014, we encouraged and funded ED physicians and nurses to receive training for hospice and palliative medicine and residents of emergency medicine to rotate to the hospice ward. In the late stage of the intervention, we initiated educational programs in the ED, an interdisciplinary meeting with the hospice team every month, sharing information and experience via a cell phone communication app, and setting aside an emergency hospice room for end-of-life patients. We compared the outcomes among pre-, during, and postintervention periods. Compared with 4 in the preintervention period, the cases of do not resuscitate (DNR) per month increased significantly to 30.1 in the early stage of intervention, 23.9 in late stage of intervention, and 34.6 in the postintervention period (all P < .001 compared with the preintervention period). Compared with 10.8% in the preintervention period, the ratio of DNR orders signed in the ED/total DNR orders signed in the study hospital was increased to 17.1% in early stage of intervention, 12.5% in late stage of intervention, and 22.8% in postintervention. Compared with zero in preintervention and early intervention, the cases of consultation with the hospice team increased significantly to 19 cases per month in the late stage of intervention and postintervention. The ability of nurses in hospice and palliative care, including knowledge and the timing and method of consultation with the hospice team, was also significantly improved. We successfully implemented a novel model of hospice and palliative care in the ED via a champion, education, and close collaboration with the hospice team, which could be an important reference for other EDs and intensive care unit in the future.

Modeling Seasonal Influenza Transmission and Its Association with Climate Factors in Thailand Using Time-Series and ARIMAX Analyses

Influenza is a worldwide respiratory infectious disease that easily spreads from one person to another. Previous research has found that the influenza transmission process is often associated with climate variables. In this study, we used autocorrelation and partial autocorrelation plots to determine the appropriate autoregressive integrated moving average (ARIMA) model for influenza transmission in the central and southern regions of Thailand. The relationships between reported influenza cases and the climate data, such as the amount of rainfall, average temperature, average maximum relative humidity, average minimum relative humidity, and average relative humidity, were evaluated using cross-correlation function. Based on the available data of suspected influenza cases and climate variables, the most appropriate ARIMA(X) model for each region was obtained. We found that the average temperature correlated with influenza cases in both central and southern regions, but average minimum relative humidity played an important role only in the southern region. The ARIMAX model that includes the average temperature with a 4-month lag and the minimum relative humidity with a 2-month lag is the appropriate model for the central region, whereas including the minimum relative humidity with a 4-month lag results in the best model for the southern region.

Direct medical costs of hospitalizations for cardiovascular diseases in Shanghai, China: trends and projections

Few studies in China have focused on direct expenditures for cardiovascular diseases (CVDs), making cost trends for CVDs uncertain. Epidemic modeling and forecasting may be essential for health workers and policy makers to reduce the cost burden of CVDs.To develop a time series model using Box-Jenkins methodology for a 15-year forecasting of CVD hospitalization costs in Shanghai.Daily visits and medical expenditures for CVD hospitalizations between January 1, 2008 and December 31, 2012 were analyzed. Data from 2012 were used for further analyses, including yearly total health expenditures and expenditures per visit for each disease, as well as per-visit-per-year medical costs of each service for CVD hospitalizations. Time series analyses were performed to determine the long-time trend of total direct medical expenditures for CVDs and specific expenditures for each disease, which were used to forecast expenditures until December 31, 2030.From 2008 to 2012, there were increased yearly trends for both hospitalizations (from 250,354 to 322,676) and total costs (from US $ 388.52 to 721.58 million per year in 2014 currency) in Shanghai. Cost per CVD hospitalization in 2012 averaged US $ 2236.29, with the highest being for chronic rheumatic heart diseases (US $ 4710.78). Most direct medical costs were spent on medication. By the end of 2030, the average cost per visit per month for all CVDs was estimated to be US $ 4042.68 (95% CI: US $ 3795.04-4290.31) for all CVDs, and the total health expenditure for CVDs would reach over US $1.12 billion (95% CI: US $ 1.05-1.19 billion) without additional government interventions.Total health expenditures for CVDs in Shanghai are estimated to be higher in the future. These results should be a valuable future resource for both researchers on the economic effects of CVDs and for policy makers.

PrediQt-Cx: post treatment health related quality of life prediction model for cervical cancer patients

Background

Cervical cancer is the third largest cause of cancer mortality in India. The objectives of the study were to compare the pre and the post treatment quality of life in cervical cancer patients and to develop a prediction model to provide an insight into the possibilities in the treatment modules.

Methodology/Principal Findings

A total of 198 patients were assessed with two structured questionnaires of Health Related Quality of Life (The European Organisation for Research and Treatment of Cancer, EORTC QLQ C-30 and CX-24). The baseline observations were recorded when the patients first reported (T1) and second evaluation was done at 6 months post treatment (T2). The mean age of detection was 50.9 years with the literacy level being non-educated or less than high school. Majority of them were married/cohabiting 179 (90.4%). On histopathological examination (HPE) squamous cell carcinoma was found to be the most common cell type carcinoma 147 (74.2%) followed by Adenocarcinoma 31 (15.7%). Radical hysterectomy was the most common treatment modality 76 (38.4%), followed by Wertheims Hysterectomy 46 (23.2%) and Radiochemotherapy 59 (29.8%). The mean score of global health of cervical cancer patients post treatment was 77.90, which was significantly higher than the pre - treatment score (54.32). Mean “symptoms score” post treatment was 21.69 with an aggravation of 7.32 compared to pre treatment scores. Patients experienced substantial decrease in sexual activity post treatment.

Conclusions/Significance

The prediction model(PrediQt-Cx), based on Support Vector Machine(SVM) for predicting post treatment HRQoL in cervical cancer patients was developed and internally cross validated. After external validation PrediQt-Cx can be easily employed to support decision making by clinicians and patients from north India region, through openly made available for access at http://prediqt.org.

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study

BACKGROUND

Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regression (MLR) models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL) after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR.

METHODOLOGY/PRINCIPAL FINDINGS

A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC.

CONCLUSIONS/SIGNIFICANCE

Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.