Dataset Information

Predicting emergency department visits in a large teaching hospital.

ABSTRACT:

Background

Emergency department (ED) visits show a high volatility over time. Therefore, EDs are likely to be crowded at peak-volume moments. ED crowding is a widely reported problem with negative consequences for patients as well as staff. Previous studies on the predictive value of weather variables on ED visits show conflicting results. Also, no such studies were performed in the Netherlands. Therefore, we evaluated prediction models for the number of ED visits in our large the Netherlands teaching hospital based on calendar and weather variables as potential predictors.

Methods

Data on all ED visits from June 2016 until December 31, 2019, were extracted. The 2016-2018 data were used as training set, the 2019 data as test set. Weather data were extracted from three publicly available datasets from the Royal Netherlands Meteorological Institute. Weather observations in proximity of the hospital were used to predict the weather in the hospital's catchment area by applying the inverse distance weighting interpolation method. The predictability of daily ED visits was examined by creating linear prediction models using stepwise selection; the mean absolute percentage error (MAPE) was used as measurement of fit.

Results

The number of daily ED visits shows a positive time trend and a large impact of calendar events (higher on Mondays and Fridays, lower on Saturdays and Sundays, higher at special times such as carnival, lower in holidays falling on Monday through Saturday, and summer vacation). The weather itself was a better predictor than weather volatility, but only showed a small effect; the calendar-only prediction model had very similar coefficients to the calendar+weather model for the days of the week, time trend, and special time periods (both MAPE's were 8.7%).

Conclusions

Because of this similar performance, and the inaccuracy caused by weather forecasts, we decided the calendar-only model would be most useful in our hospital; it can probably be transferred for use in EDs of the same size and in a similar region. However, the variability in ED visits is considerable. Therefore, one should always anticipate potential unforeseen spikes and dips in ED visits that are not shown by the model.

SUBMITTER: Erkamp NS

PROVIDER: S-EPMC8196936 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Introduction:Associations between air pollutants, meteorological conditions and respiratory diseases have been extensively shown. The aim of this study was to investigate associations between daily meteorological data, data on air pollution and emergency department (ED) visits depending on the day of the week, season and year (study period from 2013 to 2015). Methods:Highly correlated environmental data entered a categorical principal components analysis (CATPCA). We analysed cross-correlation functions between the time series of the respective daily environmental factors and daily ED visits. Time lags with peak correlations of environmental variables obtained by the CATPCA on ED visits together with day of the week, year, running day (linear, quadratic and cubic), season and interaction terms entered the univariate analysis of variance (UNIANOVA) model. Results:The analyses demonstrated main effects on ED visits for the day of the week with highest admission rates on Mondays (B=10.69; ?2=0.333; p<0.001). A significant time trend could be observed showing increasing numbers of ED visits per each year (p<0.001). The variable 'running day' (linear, quadratic and cubic) indicated a significant non-linear effect over time. The variable season showed significant results with winter, spring and summer recording fewer ED visits compared with the reference season autumn. Environmental variables showed no direct associations with respiratory ED visits. Discussion:ED visits were significantly associated with temporal variables. Our data did not show direct associations between environmental variables and ED visits.In times of rapid urbanisation, increases in respiratory diseases, temperature and air pollution, our analyses can help focus future studies and enhance strategies to reduce increasing numbers of respiratory diseases and ED visits. Because the potential costs of medical care in hospitals can be high compared with physicians, public health recommendations for reducing the increasing ED visits should be promoted and evaluated.

Project description:BackgroundThe coronavirus disease 2019 (COVID-19) pandemic has critically affected healthcare delivery in the United States. Little is known on its impact on the utilization of emergency department (ED) services, particularly for conditions that might be medically urgent. The objective of this study was to explore trends in the number of outpatient (treat and release) ED visits during the COVID-19 pandemic.MethodsWe conducted a cross-sectional, retrospective study of outpatient emergency department visits from January 1, 2019 to August 31, 2020 using data from a large, urban, academic hospital system in Utah. Using weekly counts and trend analyses, we explored changes in overall ED visits, by patients' area of residence, by medical urgency, and by specific medical conditions.ResultsWhile outpatient ED visits were higher (+6.0%) in the first trimester of 2020 relative to the same period in 2019, the overall volume between January and August of 2020 was lower (-8.1%) than in 2019. The largest decrease occurred in April 2020 (-30.4%), followed by the May to August period (-12.8%). The largest declines were observed for visits by out-of-state residents, visits classified as non-emergent, primary care treatable or preventable, and for patients diagnosed with hypertension, diabetes, headaches and migraines, mood and personality disorders, fluid and electrolyte disorders, and abdominal pain. Outpatient ED visits for emergent conditions, such as palpitations and tachycardia, open wounds, syncope and collapse remained relatively unchanged, while lower respiratory disease-related visits were 67.5% higher in 2020 relative to 2019, particularly from March to April 2020. However, almost all types of outpatient ED visits bounced back after May 2020.ConclusionsOverall outpatient ED visits declined from mid-March to August 2020, particularly for non-medically urgent conditions which can be treated in other more appropriate care settings. Our findings also have implications for insurers, policymakers, and other stakeholders seeking to assist patients in choosing more appropriate setting for their care during and after the pandemic.

Project description:BackgroundUnscheduled emergency department return visits (EDRVs) are key indicators for monitoring the quality of emergency medical care. A high return rate implies that the medical services provided by the emergency department (ED) failed to achieve the expected results of accurate diagnosis and effective treatment. Older adults are more susceptible to diseases and comorbidities than younger adults, and they exhibit unique and complex clinical characteristics that increase the difficulty of clinical diagnosis and treatment. Older adults also use more emergency medical resources than people in other age groups. Many studies have reviewed the causes of EDRVs among general ED patients; however, few have focused on older adults, although this is the age group with the highest rate of EDRVs.ObjectiveThis aim of this study is to establish a model for predicting unscheduled EDRVs within a 72-hour period among patients aged 65 years and older. In addition, we aim to investigate the effects of the influencing factors on their unscheduled EDRVs.MethodsWe used stratified and randomized data from Taiwan's National Health Insurance Research Database and applied data mining techniques to construct a prediction model consisting of patient, disease, hospital, and physician characteristics. Records of ED visits by patients aged 65 years and older from 1996 to 2010 in the National Health Insurance Research Database were selected, and the final sample size was 49,252 records.ResultsThe decision tree of the prediction model achieved an acceptable overall accuracy of 76.80%. Economic status, chronic illness, and length of stay in the ED were the top three variables influencing unscheduled EDRVs. Those who stayed in the ED overnight or longer on their first visit were less likely to return. This study confirms the results of prior studies, which found that economically underprivileged older adults with chronic illness and comorbidities were more likely to return to the ED.ConclusionsMedical institutions can use our prediction model as a reference to improve medical management and clinical services by understanding the reasons for 72-hour unscheduled EDRVs in older adult patients. A possible solution is to create mechanisms that incorporate our prediction model and develop a support system with customized medical education for older patients and their family members before discharge. Meanwhile, a reasonably longer length of stay in the ED may help evaluate treatments and guide prognosis for older adult patients, and it may further reduce the rate of their unscheduled EDRVs.

Project description:ObjectiveTo predict hospital admission at the time of ED triage using patient history in addition to information collected at triage.MethodsThis retrospective study included all adult ED visits between March 2014 and July 2017 from one academic and two community emergency rooms that resulted in either admission or discharge. A total of 972 variables were extracted per patient visit. Samples were randomly partitioned into training (80%), validation (10%), and test (10%) sets. We trained a series of nine binary classifiers using logistic regression (LR), gradient boosting (XGBoost), and deep neural networks (DNN) on three dataset types: one using only triage information, one using only patient history, and one using the full set of variables. Next, we tested the potential benefit of additional training samples by training models on increasing fractions of our data. Lastly, variables of importance were identified using information gain as a metric to create a low-dimensional model.ResultsA total of 560,486 patient visits were included in the study, with an overall admission risk of 29.7%. Models trained on triage information yielded a test AUC of 0.87 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.88) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on patient history yielded an AUC of 0.86 for LR (95% CI 0.86-0.87), 0.87 for XGBoost (95% CI 0.87-0.87) and 0.87 for DNN (95% CI 0.87-0.88). Models trained on the full set of variables yielded an AUC of 0.91 for LR (95% CI 0.91-0.91), 0.92 for XGBoost (95% CI 0.92-0.93) and 0.92 for DNN (95% CI 0.92-0.92). All algorithms reached maximum performance at 50% of the training set or less. A low-dimensional XGBoost model built on ESI level, outpatient medication counts, demographics, and hospital usage statistics yielded an AUC of 0.91 (95% CI 0.91-0.91).ConclusionMachine learning can robustly predict hospital admission using triage information and patient history. The addition of historical information improves predictive performance significantly compared to using triage information alone, highlighting the need to incorporate these variables into prediction models.

Project description:Background and objectivesIn 2011, there were approximately 131 million visits to an emergency department in the United States. Emergency department visits have increased over time, far outpacing growth of the general population. There is a paucity of data evaluating emergency department visits among kidney transplant recipients. We sought to evaluate the incidence and risk factors for emergency department visits after initial hospital discharge after transplantation in the United States.Design, setting, participants, & measurementsWe identified 10,533 kidney transplant recipients from California, New York, and Florida between 2009 and 2012 using the State Inpatient and Emergency Department Databases included in the Healthcare Cost and Utilization Project. We used multivariable Poisson and Cox proportional hazard models to evaluate adjusted incidence rates and time to emergency department visits after transplantation.ResultsThere were 17,575 emergency department visits over 13,845 follow-up years (overall rate =126.9/100 patient-years; 95% confidence interval, 125.1 to 128.8). The cumulative incidences of emergency department visits at 1, 12, and 24 months were 12%, 40%, and 57%, respectively, with median time =19 months; 48% of emergency department visits led to hospital admission. Risk factors for higher emergency department rates included younger age, women, black and Hispanic race/ethnicity, public insurance, depression, diabetes, peripheral vascular disease, and emergency department use before transplant. There was wide variation in emergency department visits by individual transplant center (10th percentile =70.0/100 patient-years; median =124.6/100 patient-years; and 90th percentile =187.4/100 patient-years).ConclusionsThe majority of kidney transplant recipients will visit an emergency department in the first 2 years post-transplantation, with significant variation by patient characteristics and individual centers. As such, coordination of care through the emergency department is a critical component of post-transplant management, and specific acumen of transplant-related care is needed among emergency department providers. Additional research assessing best processes of care for post-transplant management and health care expenditures and outcomes associated with emergency department visits for transplant recipients are warranted.

Project description:BACKGROUND:Although homelessness and opioid overdose are major public health issues in the U.S., evidence is limited as to whether homelessness is associated with an increased risk of opioid overdose. OBJECTIVE:To compare opioid-related outcomes between homeless versus housed individuals in low-income communities. DESIGN, SETTING, AND PARTICIPANTS:Cross-sectional analysis of individuals who had at least one ED visit or hospitalization in four states (Florida, Maryland, Massachusetts, and New York) in 2014. MEASUREMENTS:Risk of opioid overdose and opioid-related ED visits/hospital admissions were compared between homeless versus low-income housed individuals, adjusting for patient characteristics and hospital-specific fixed effects (effectively comparing homeless versus low-income housed individuals treated at the same hospital). We also examined whether risk of opioid-related outcomes varied by patients' sex and race/ethnicity. RESULTS:A total of 96,099 homeless and 2,869,230 low-income housed individuals were analyzed. Homeless individuals had significantly higher risk of opioid overdose (adjusted risk, 1.8% for homeless vs. 0.3% for low-income housed individuals; adjusted risk difference [aRD], +1.5%; 95%CI, +1.0% to +2.0%; p < 0.001) and opioid-related ED visit/hospital admission (10.4% vs. 1.5%; aRD, +8.9%; 95%CI, +7.2% to +10.6%; p < 0.001) compared to low-income housed individuals. Non-Hispanic White females had the highest risk among the homeless population, whereas non-Hispanic White males had the highest risk among the low-income housed population. LIMITATIONS:Individuals with no ED visit or hospitalization in 2014 were not included. CONCLUSION:Homeless individuals had disproportionately higher adjusted risk of opioid-related outcomes compared to low-income housed individuals treated at the same hospital. Among homeless individuals, non-Hispanic White females incurred the highest risk. These findings highlight the importance of recognizing the homeless population-especially the non-Hispanic White female homeless population-as a high-risk population for opioid overdose.

Project description:BACKGROUND:The recent literature reports promising results from using intelligent systems to support decision making in healthcare operations. Using these systems may lead to improved diagnostic and treatment protocols and to predict hospital bed demand. Predicting hospital bed demand in emergency department (ED) attendances could help resource allocation and reduce pressure on busy hospitals. However, there is still limited knowledge on whether intelligent systems can operate as fully autonomous, user-independent systems. OBJECTIVE:Compare the performance of a computer-based algorithm and humans in predicting hospital bed demand (admissions and discharges) based on the initial SOAP (Subjective, Objective, Assessment, Plan) records of the ED. METHODS:This was a retrospective cohort study that compared the performance of humans and machines in predicting hospital bed demand from an ED. It considered electronic medical records (EMR) of 9030 patients (230 used as a testing set, and hence evaluated both by humans and by an algorithm, and 8800 used as a training set exclusively by the algorithm) who visited the ED of a tertiary care and teaching public hospital located in Porto Alegre, Brazil between January and December 2014. The machine role was played by Support Vector Machine Classifier and the human prediction was performed by four ED physicians. Predictions were compared in terms of sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUROC). RESULTS:All graders achieved similar accuracies. The accuracy by AUROC for the testing set was 0.82 [95% confidence interval (CI) of 0.77-0.87], 0.80 (95% CI: 0.75-0.85), 0.76 (95% CI: 0.71-0.81) for novice physicians, machine, experienced physicians, respectively. Processing time per test EMR was 0.00812±0.0009 seconds. In contrast, novice physicians took on average 156.80 seconds per test EMR, while experienced physicians took on average 56.40 seconds per test EMR. CONCLUSIONS:Our data indicated that the system could predict patient admission or discharge states with 80% accuracy, which was similar the performance of novice and experienced physicians. These results suggested that the algorithm could operate as an autonomous and independent system to complete this task.