Dataset Information

Predicting hospital admission and returns to the emergency department for elderly patients.

ABSTRACT: Methods to accurately identify elderly patients with a high likelihood of hospital admission or subsequent return to the emergency department (ED) might facilitate the development of interventions to expedite the admission process, improve patient care, and reduce overcrowding. This study sought to identify variables found among elderly ED patients that could predict either hospital admission or return to the ED.All visits by patients 75 years of age or older during 2007 at an academic ED serving a large community of elderly were reviewed. Clinical and demographic data were used to construct regression models to predict admission or ED return. These models were then validated in a second group of patients 75 and older who presented during two 1-month periods in 2008.Of 4,873 visits, 3,188 resulted in admission (65.4%). Regression modeling identified five variables statistically related to the probability of admission: age, triage score, heart rate, diastolic blood pressure, and chief complaint. Upon validation, the c-statistic of the receiver operating characteristic (ROC) curve was 0.73, moderately predictive of admission. We were unable to produce models that predicted ED return for these elderly patients.A derived and validated triage-based model is presented that provides a moderately accurate probability of hospital admission of elderly patients. If validated experimentally, this model might expedite the admission process for elderly ED patients. Our models failed, as have others, to accurately predict ED return among elderly patients, underscoring the challenge of identifying those individuals at risk for early ED returns.

SUBMITTER: LaMantia MA

PROVIDER: S-EPMC5985811 | biostudies-literature | 2010 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting hospital admission and returns to the emergency department for elderly patients.

LaMantia Michael A MA Platts-Mills Timothy F TF Biese Kevin K Khandelwal Christine C Forbach Cory C Cairns Charles B CB Busby-Whitehead Jan J Kizer John S JS

Academic emergency medicine : official journal of the Society for Academic Emergency Medicine 20100301 3

<h4>Objectives</h4>Methods to accurately identify elderly patients with a high likelihood of hospital admission or subsequent return to the emergency department (ED) might facilitate the development of interventions to expedite the admission process, improve patient care, and reduce overcrowding. This study sought to identify variables found among elderly ED patients that could predict either hospital admission or return to the ED.<h4>Methods</h4>All visits by patients 75 years of age or older d ...[more]

PMID: 20370757

Similar Datasets

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/objectivesTelephone follow-up calls could optimize the transition from the emergency department (ED) to home for older patients. However, the effects on hospital return rates are not clear. We investigated whether telephone follow-up reduces unplanned hospitalizations and/or unplanned ED return visits within 30 days of ED discharge.DesignPragmatic randomized controlled trial with allocation by month; odd months intervention group, even months control group.SettingTwo ED locations of a non-academic teaching hospital in The Netherlands.ParticipantsCommunity-dwelling adults aged ≥70 years, discharged home from the ED were randomized to the intervention group (N = 4732) or control group (N = 5104).InterventionIntervention group patients: semi-scripted telephone call from an ED nurse within 24 h after discharge to identify post-discharge problems and review discharge instructions. Control group patients: scripted satisfaction survey telephone call.MeasurementsPrimary outcome: total number of unplanned hospitalizations and/or ED return visits within 30 days of ED discharge.Secondary outcomesseparate numbers of unplanned hospitalizations and ED return visits. Subgroup analysis by age, sex, living condition, and degree of crowding in the ED at discharge.ResultsOverall, 42% were males, and median age was 78 years. In the intervention group, 1516 of 4732 patients (32%) consented, and in the control group 1659 of 5104 (33%) patients. Unplanned 30-day hospitalization and/or ED return visit was found in 16% of intervention group patients and 14% of control group patients (odds ratio 1.16; 95% confidence interval: 0.96-1.42). Also, no statistically significant differences were found in secondary outcome measures. Within the subgroups, the intervention did not have beneficial effects for the intervention group.ConclusionTelephone follow-up after ED discharge in older patients did not result in reduction of unplanned hospital admissions and/or ED return visits within 30 days. These results raise the question of whether other outcomes could be improved by post-discharge ED telephone follow-up.

Project description:The aim of this study is to evaluate the usefulness of the pre-hospital National Early Warning Score (pNEWS) and the pre-hospital Modified Early Warning Score (pMEWS) for predicting admission and in-hospital mortality in elderly patients presenting to the emergency department (ED). We also compare the value of the pNEWS with that of the ED NEWS (eNEWS) and ED MEWS (eMEWS) for predicting admission and in-hospital mortality. This retrospective, single-centre observational study was carried out in the ED of Jikei University Kashiwa Hospital, in Chiba, Japan, from 1st April 2017 to 31st March 2018. All patients aged 65 years or older were included in this study. The pNEWS/eNEWS were derived from seven common physiological vital signs: respiratory rate, peripheral oxygen saturation, the presence of inhaled oxygen parameters, body temperature, systolic blood pressure, pulse rate and Alert, responds to Voice, responds to Pain, Unresponsive (AVPU) score, whereas the pMEWS/eMEWS were derived from six common physiological vital signs: respiratory rate, peripheral oxygen saturation, body temperature, systolic blood pressure, pulse rate and AVPU score. Discrimination was assessed by plotting the receiver operating characteristic (ROC) curve and calculating the area under the ROC curve (AUC). The median pNEWS, pMEWS, eNEWS and eMEWS were significantly higher at admission than at discharge (p < 0.001). The median pNEWS, pMEWS, eNEWS and eMEWS of non-survivors were significantly higher than those of the survivors (p < 0.001). The AUC for predicting admission was 0.559 for the pNEWS and 0.547 for the pMEWS. There was no significant difference between the AUCs of the pNEWS and the pMEWS for predicting admission (p = 0.102). The AUCs for predicting in-hospital mortality were 0.678 for the pNEWS and 0.652 for the pMEWS. There was no significant difference between the AUCs of the pNEWS and the pMEWS for predicting in-hospital mortality (p = 0.081). The AUC for predicting admission was 0.628 for the eNEWS and 0.591 for the eMEWS. The AUC of the eNEWS was significantly greater than that of the eMEWS for predicting admission (p < 0.001). The AUC for predicting in-hospital mortality was 0.789 for the eNEWS and 0.720 for the eMEWS. The AUC of the eNEWS was significantly greater than that of the eMEWS for predicting in-hospital mortality (p < 0.001). For admission and in-hospital mortality, the AUC of the eNEWS was significantly greater than that of the pNEWS (p < 0.001, p < 0.001), and the AUC of the eMEWS was significantly greater than that of the pMEWS (p < 0.01, p < 0.05). Our single-centre study has demonstrated the low utility of the pNEWS and the pMEWS as predictors of admission and in-hospital mortality in elderly patients, whereas the eNEWS and the eMEWS predicted admission and in-hospital mortality more accurately. Evidence from multicentre studies is needed before introducing pre-hospital versions of risk-scoring systems.

Project description:BackgroundEmergency 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.MethodsData 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.ResultsThe 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%).ConclusionsBecause 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.

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.

Project description:PurposeMore than 1 million patients annually seek care in an emergency department for kidney stones but a minority require hospital admission or a urological procedure. We describe predictors of hospital admission or urological intervention.Materials and methodsThis secondary analysis of prospective data included patients with an obstructing ureteral stone that was confirmed by computerized tomography in an emergency department. All patients also underwent point of care limited renal ultrasound. The need for urological intervention at 90 days was assessed by a followup interview. Logistic regression was used to identify predictors of admission and urological intervention, which were further stratified by disposition. Separate regression models with and without computerized tomography findings (point of care limited renal ultrasound only) were compared using c-statistics.ResultsAmong a cohort of 475 patients with a symptomatic stone on computerized tomography 95 (20%) were admitted and 68 (72%) received an intervention. Of 380 discharged patients 66 (17%) required urological intervention. Admitted patients were more likely to have undergone a prior procedure, have evidence of kidney injury or infection, need opiate analgesia or have larger stones or hydronephrosis on point of care limited renal ultrasound. Predictors of intervention varied by disposition. However, regression models with and without computerized tomography findings demonstrated similar c-statistics. Discharged patients with larger stones, a longer pain duration at presentation and prior procedures were more likely to undergo intervention.ConclusionsIntervention was common among admitted patients but it occurred in a minority of those discharged. Predictors of intervention varied by disposition. Models incorporating computerized tomography findings were similar to those that did not incorporate such findings. These data support ultrasound first or delayed computerized tomography diagnostic pathways for patients deemed clinically suitable for discharge home.

Dataset Information

Predicting hospital admission and returns to the emergency department for elderly patients.

Publications

Predicting hospital admission and returns to the emergency department for elderly patients.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets