Dataset Information

Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay.

ABSTRACT:

Objective

Emergency departments (EDs) continue to pursue optimal patient flow without sacrificing quality of care. The speed with which a healthcare provider receives pertinent information, such as results from clinical orders, can impact flow. We seek to determine if clinical ordering behavior can be predicted at triage during an ED visit.

Materials and methods

Using data available during triage, we trained multilabel machine learning classifiers to predict clinical orders placed during an ED visit. We benchmarked 4 classifiers with 2 multilabel learning frameworks that predict orders independently (binary relevance) or simultaneously (random k-labelsets). We evaluated algorithm performance, calculated variable importance, and conducted a simple simulation study to examine the effects of algorithm implementation on length of stay and cost.

Results

Aggregate performance across orders was highest when predicting orders independently with a multilayer perceptron (median F1 score = 0.56), but prediction frameworks that simultaneously predict orders for a visit enhanced predictive performance for correlated orders. Visit acuity was the most important predictor for most orders. Simulation results indicated that direct implementation of the model would increase ordering costs (from $21 to $45 per visit) but reduce length of stay (from 158 minutes to 151 minutes) over all visits.

Discussion

Simulated implementations of the predictive algorithm decreased length of stay but increased ordering costs. Optimal implementation of these predictions to reduce patient length of stay without incurring additional costs requires more exploration.

Conclusions

It is possible to predict common clinical orders placed during an ED visit with data available at triage.

SUBMITTER: Hunter-Zinck HS

PROVIDER: S-EPMC7647143 | biostudies-literature | 2019 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay.

Hunter-Zinck Haley S HS Peck Jordan S JS Strout Tania D TD Gaehde Stephan A SA

Journal of the American Medical Informatics Association : JAMIA 20191201 12

<h4>Objective</h4>Emergency departments (EDs) continue to pursue optimal patient flow without sacrificing quality of care. The speed with which a healthcare provider receives pertinent information, such as results from clinical orders, can impact flow. We seek to determine if clinical ordering behavior can be predicted at triage during an ED visit.<h4>Materials and methods</h4>Using data available during triage, we trained multilabel machine learning classifiers to predict clinical orders placed ...[more]

PMID: 31578568

Similar Datasets

Project description:Performance measures, particularly pay for performance, may have unintended consequences for safety-net institutions caring for disproportionate shares of Medicaid or uninsured patients.To describe emergency department (ED) compliance with proposed length-of-stay measures for admissions (8 hours or 480 minutes) and discharges, transfers, and observations (4 hours or 240 minutes) by safety-net status.The 2008 National Hospital Ambulatory Medical Care Survey (NHAMCS) ED data were stratified by safety-net status (Centers for Disease Control and Prevention definition) and disposition (admission, discharge, observation, transfer). The 2008 NHAMCS is a national probability sample of 396 hospitals (90.2% unweighted response rate) and 34 134 patient records. Visits were excluded for patients younger than 18 years, missing length-of-stay data or dispositions of missing, other, left against medical advice, or dead on arrival. Median and 90th percentile ED lengths of stay were calculated for each disposition and admission/discharge subcategories (critical care, psychiatric, routine) stratified by safety-net status. Multivariable analyses determined associations with length-of-stay measure compliance.Emergency Department length-of-stay measure compliance by disposition and safety-net status.Of the 72.1% ED visits (N = 24 719) included in the analysis, 42.3% were to safety-net EDs and 57.7% were to non-safety-net EDs. The median length of stay for safety-net was 269 minutes (interquartile range [IQR], 178-397 minutes) for admission vs 281 minutes (IQR, 178-401 minutes) for non-safety-net EDs; 156 minutes (IQR, 95-239 minutes) for discharge vs 148 minutes (IQR, 88-238 minutes); 355 minutes (IQR, 221-675 minutes) for observations vs 298 minutes (IQR, 195-440 minutes); and 235 minutes (IQR, 155-378 minutes) for transfers vs 239 minutes (IQR, 142-368 minutes). Safety-net status was not independently associated with compliance with ED length-of-stay measures; the odds ratio was 0.83 for admissions (95% CI, 0.52-1.34); 1.03 for discharges (95% CI, 0.83-1.27); 1.05 for observations (95% CI, 0.57-1.95), 1.30 for transfers (95% CI, 0.70-2.45]); or subcategories except for psychiatric discharges (1.67, [95% CI, 1.02-2.74]).Compliance with proposed ED length-of-stay measures for admissions, discharges, transfers, and observations did not differ significantly between safety-net and non-safety-net hospitals.

Project description:ObjectiveThis study aims to develop and compare different models to predict the Length of Stay (LoS) and the Prolonged Length of Stay (PLoS) of inpatients admitted through the emergency department (ED) in general patient settings. This aim is not only to promote any specific model but rather to suggest a decision-supporting tool (i.e., a prediction framework).MethodsWe analyzed a dataset of patients admitted through the ED to the "Sant"Orsola Malpighi University Hospital of Bologna, Italy, between January 1 and October 26, 2022. PLoS was defined as any hospitalization with LoS longer than 6 days. We deployed six classification algorithms for predicting PLoS: Random Forest (RF), Support Vector Machines (SVM), Gradient Boosting (GB), AdaBoost, K-Nearest Neighbors (KNN), and logistic regression (LoR). We evaluated the performance of these models with the Brier score, the area under the ROC curve (AUC), accuracy, sensitivity (recall), specificity, precision, and F1-score. We further developed eight regression models for LoS prediction: Linear Regression (LR), including the penalized linear models Least Absolute Shrinkage and Selection Operator (LASSO), Ridge and Elastic-net regression, Support vector regression, RF regression, KNN, and eXtreme Gradient Boosting (XGBoost) regression. The model performances were measured by their mean square error, mean absolute error, and mean relative error. The dataset was randomly split into a training set (70%) and a validation set (30%).ResultsA total of 12,858 eligible patients were included in our study, of whom 60.88% had a PloS. The GB classifier best predicted PloS (accuracy 75%, AUC 75.4%, Brier score 0.181), followed by LoR classifier (accuracy 75%, AUC 75.2%, Brier score 0.182). These models also showed to be adequately calibrated. Ridge and XGBoost regressions best predicted LoS, with the smallest total prediction error. The overall prediction error is between 6 and 7 days, meaning there is a 6-7 day mean difference between actual and predicted LoS.ConclusionOur results demonstrate the potential of machine learning-based methods to predict LoS and provide valuable insights into the risks behind prolonged hospitalizations. In addition to physicians' clinical expertise, the results of these models can be utilized as input to make informed decisions, such as predicting hospitalizations and enhancing the overall performance of a public healthcare system.

Dataset Information

Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay.

Objective

Materials and methods

Results

Discussion

Conclusions

Publications

Predicting emergency department orders with multilabel machine learning techniques and simulating effects on length of stay.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets