Dataset Information

Predicting Emergency Department "Bouncebacks": A Retrospective Cohort Analysis.

ABSTRACT:

Introduction

The short-term return visit rate among patients discharged from emergency departments (ED) is a quality metric and target for interventions. The ability to accurately identify which patients are more likely to revisit the ED could allow EDs and health systems to develop more focused interventions, but efforts to reduce revisits have not yet found success. Whether patients with a high number of ED visits are at increased risk of a return visit remains underexplored.

Methods

This was a population-based, retrospective, cohort study using administrative data from a large physician partnership. We included patients discharged from EDs from 80 hospitals in seven states from July 2014 - June 2016. We performed multivariable logistic regression of short-term return visits on patient, visit, hospital, and community characteristics. The primary outcome was the proportion of patients who had a return visit within 14 days of an index ED visit.

Results

Among 6,699,717 index visits, the overall risk of 14-day revisit was 12.6%. Frequent visitors accounted for 18.7% of all visits and 40.2% of all 14-day revisits. Frequent visitor status was associated with the highest odds of a revisit (odds ratio [OR] 3.06; 95% confidence interval [CI], 3.041 - 3.073). Other predictors of revisits were cellulitis (OR 2.131; 95% CI, 2.106 - 2.156), alcohol-related disorders (OR 1.579; 95%CI, 1.548 - 1.610), congestive heart failure (OR 1.175; 95% CI, 1.126 - 1.226), and public insurance (Medicaid OR 1.514; 95% CI, 1.501 - 1.528; Medicare OR 1.601; 95% CI, 1.583 - 1.620).

Conclusion

Previous ED use - even a single previous visit - was a stronger predictor of a return visit than any other patient, hospital, or community characteristic. Clinicians should consider previous ED use when considering treatment decisions and risk of return visit, as should stakeholders targeting patients at risk of a return visit.

SUBMITTER: Montoy JCC

PROVIDER: S-EPMC6860392 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting Emergency Department "Bouncebacks": A Retrospective Cohort Analysis.

Montoy Juan Carlos C JCC Tamayo-Sarver Joshua J Miller Gregg A GA Baer Amy E AE Peabody Christopher R CR

The western journal of emergency medicine 20191016 6

<h4>Introduction</h4>The short-term return visit rate among patients discharged from emergency departments (ED) is a quality metric and target for interventions. The ability to accurately identify which patients are more likely to revisit the ED could allow EDs and health systems to develop more focused interventions, but efforts to reduce revisits have not yet found success. Whether patients with a high number of ED visits are at increased risk of a return visit remains underexplored.<h4>Method ...[more]

PMID: 31738713

Similar Datasets

Project description:Many studies have shown the tendency for people without a regular care provider or primary physician to make greater use of emergency departments. We sought to determine the effects of three aspects of care provided by primary physicians (physician specialty, continuity of care and comprehensiveness of care) on their patients' use of the emergency department.Using provincial administrative databases, we created a cohort of 367,315 adults aged 18 years and older. Participants were residents of urban areas of Quebec. Affiliation with a primary physician, the specialty of this physician (i.e., family physician v. specialist), continuity of care (as measured using the Usual Provider Continuity index) and comprehensiveness of care (i.e., number of complete annual examinations) were measured among participants (n = 311,701) who had visited a physician three or more times during a two-year baseline period. We used multivariable negative binomial regression to investigate the relationships between measures of care and the number of visits to emergency departments during a 12-month follow-up period.Among participants under 65 years of age, emergency department use was higher for those not affiliated than for those affiliated with a family physician (incidence rate ratio [IRR] 1.11, 95% confidence interval [CI] 1.05-1.16) or a specialist (IRR 1.10, 95% CI 1.04-1.17). Among patients aged 65 years and older, having a specialist primary physician, as opposed to a family physician, predicted increased use of the emergency department (IRR 1.13, 95% CI 1.09-1.17). Greater continuity of care with a family physician predicted less use of the emergency department only among participants who made 25 or more visits to a physician during the baseline period. Greater continuity of care with a specialist predicted less use of the emergency department overall, particularly among participants with intermediate numbers of multimorbidities and admissions to hospital. Greater comprehensiveness of care by family physicians predicted less use of the emergency department.Efforts to increase the proportion of adults affiliated with a family physician should target older adults, people who visit physicians more frequently and people with multiple comorbidities and admissions to hospital.

Project description:BackgroundWithin the trauma system, the emergency department (ED) is the hospital's first contact and is vital for allocating medical resources. However, there is generally limited information about patients that die in the ED.ObjectiveThe aim of this study was to develop an artificial intelligence (AI) model to predict trauma mortality and analyze pertinent mortality factors for all patients visiting the ED.MethodsWe used the Korean National Emergency Department Information System (NEDIS) data set (N=6,536,306), incorporating over 400 hospitals between 2016 and 2019. We included the International Classification of Disease 10th Revision (ICD-10) codes and chose the following input features to predict ED patient mortality: age, sex, intentionality, injury, emergent symptom, Alert/Verbal/Painful/Unresponsive (AVPU) scale, Korean Triage and Acuity Scale (KTAS), and vital signs. We compared three different feature set performances for AI input: all features (n=921), ICD-10 features (n=878), and features excluding ICD-10 codes (n=43). We devised various machine learning models with an ensemble approach via 5-fold cross-validation and compared the performance of each model with that of traditional prediction models. Lastly, we investigated explainable AI feature effects and deployed our final AI model on a public website, providing access to our mortality prediction results among patients visiting the ED.ResultsOur proposed AI model with the all-feature set achieved the highest area under the receiver operating characteristic curve (AUROC) of 0.9974 (adaptive boosting [AdaBoost], AdaBoost + light gradient boosting machine [LightGBM]: Ensemble), outperforming other state-of-the-art machine learning and traditional prediction models, including extreme gradient boosting (AUROC=0.9972), LightGBM (AUROC=0.9973), ICD-based injury severity scores (AUC=0.9328 for the inclusive model and AUROC=0.9567 for the exclusive model), and KTAS (AUROC=0.9405). In addition, our proposed AI model outperformed a cutting-edge AI model designed for in-hospital mortality prediction (AUROC=0.7675) for all ED visitors. From the AI model, we also discovered that age and unresponsiveness (coma) were the top two mortality predictors among patients visiting the ED, followed by oxygen saturation, multiple rib fractures (ICD-10 code S224), painful response (stupor, semicoma), and lumbar vertebra fracture (ICD-10 code S320).ConclusionsOur proposed AI model exhibits remarkable accuracy in predicting ED mortality. Including the necessity for external validation, a large nationwide data set would provide a more accurate model and minimize overfitting. We anticipate that our AI-based risk calculator tool will substantially aid health care providers, particularly regarding triage and early diagnosis for trauma patients.

Project description:BackgroundVisits to the emergency department are critical opportunities to engage individuals after an overdose. We sought to estimate and compare the 12-month mortality between persons with visits to the emergency department related to opioid overdose and those with non-overdose-related visits.MethodsWe conducted a retrospective cohort study using the Provincial Overdose Cohort, which contains data for patients in British Columbia who had an opioid-related overdose between 2015 and 2017, along with a 20% random sample of BC residents for comparison. We examined all nonfatal visits to the emergency department between Jan. 1, 2015, and Dec. 31, 2016, among persons aged 14 to 74 years and compared the 12-month mortality between those with overdose-related visits and those with non-overdose-related visits. We estimated the hazard ratio for death, with adjustment for age, sex, comorbidity and disposition (discharged or left against medical advice).ResultsWe included 3593 persons with overdose-related visits and 216 453 with non-overdose-related visits to the emergency department. Those with overdose-related visits were younger, were predominantly male and had more mental health conditions. The 12-month crude mortality probability was 5.4% (95% confidence interval [CI] 4.7%-6.2%) in this group and 1.7% (95% CI 1.6%-1.8%) among those with non-overdose-related visits. After adjustment, for persons who were discharged, the 12-month mortality hazard was 3.5 (95% CI 3.0-4.2) times higher among those with overdose-related visits than those with non-overdose-related visits. For persons who left against medical advice, the mortality hazard was 7.1 (95% CI 4.0-12.5) times higher among those with opioid overdose.InterpretationAmong persons with overdose-related visits to the emergency department, 12-month mortality was higher than among those with non-overdose-related visits. Overdose-related visits should prompt urgent evidence-based interventions (e.g., take-home naloxone kits, buprenorphine-naloxone induction) to prevent future deaths.

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.

Dataset Information

Predicting Emergency Department "Bouncebacks": A Retrospective Cohort Analysis.

Introduction

Methods

Results

Conclusion

Publications

Predicting Emergency Department "Bouncebacks": A Retrospective Cohort Analysis.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets