Development of a low‐dimensional model to predict admissions from triage at a pediatric emergency department

Abstract

Objectives This study aims to develop and internally validate a low‐dimensional model to predict outcomes (admission or discharge) using commonly entered data up to the post‐triage process to improve patient flow in the pediatric emergency department (ED). In hospital settings where electronic data are limited, a low‐dimensional model with fewer variables may be easier to implement. Methods This prognostic study included ED attendances in 2017 and 2018. The Cross Industry Standard Process for Data Mining methodology was followed. Eligibility criteria was applied to the data set, splitting into 70% train and 30% test. Sampling techniques were compared. Gradient boosting machine (GBM), logistic regression, and naïve Bayes models were created. Variables of importance were obtained from the model with the highest area under the curve (AUC) and used to create a low‐dimensional model. Results Eligible attendances totaled 72,229 (15% admission rate). The AUC was 0.853 (95% confidence interval [CI], 0.846–0.859) for GBM, 0.845 (95% CI, 0.838–0.852) for logistic regression and 0.813 (95% CI, 0.806–0.821) for naïve Bayes. Important predictors in the GBM model used to create a low‐dimensional model were presenting complaint, triage category, referral source, registration month, location type (resuscitation/other), distance traveled, admission history, and weekday (AUC 0.835 [95% CI, 0.829‐0.842]). Conclusions Admission and discharge probability can be predicted early in a pediatric ED using 8 variables. Future work could analyze the false positives and false negatives to gain an understanding of the implementation of these predictions.

Use of Artificial Intelligence in Triage in Hospital Emergency Departments: A Scoping Review

“…The consistent superiority of ML models in determining and prioritizing patients within the ED setting holds the potential to redefine triage precision [23,24,30,34,42,[44][45][46]. Reduced instances of under-triaging and over-triaging, coupled with the remarkable decrease in erroneous triage rates for critically ill patients, underscore the impact on the accuracy of patient prioritization [25,29].…”

“…The Another study reported the development of a low-dimensional ML model to predict whether a patient would be admitted or discharged from the pediatric ED, resulting in an area under the receiver operating characteristic curve (AUROC) of 0.853 [24]. They concluded that early prediction of admission and discharge probabilities during the ED triage process could be utilized to enhance patient flow and contribute to more effective bed management.…”

“…Leonard, 2022 [24] Models that predict admission and discharge can be used for additional decision support information, allow nurses to request beds while waiting for clinical decision-making, or fast track for discharge. Also helps patient flow and hospital overcrowding.…”

“…Eight studies examined the use of AI in determining the need to admit the patient to longer or more intensive care [23,24,30,34,42,[44][45][46]. Six studies investigated hospital admission, while two examined intensive care unit admission.…”

“…One of the difficulties with triage care is determining which patients will require more intensive care or monitoring. One of the common metrics for objective determination on whether to triage is via laboratory tests, vitals, patient history, and presenting symptoms [23,24,30,34,42,[44][45][46]. These programs have the advantage of integrating all aspects of a presenting patient simultaneously to objectively determine a solution.…”