Forecasting mortality associated emergency department crowding

TL;DR

This study develops a machine learning model to predict emergency department crowding and associated mortality risks using retrospective data, enabling proactive measures to improve patient outcomes.

Contribution

The paper introduces a LightGBM-based predictive model for ED crowding and mortality risk, demonstrating accurate forecasts using administrative data.

Findings

Afternoon crowding predicted at 11 a.m. with AUC 0.82

Morning crowding predicted at 8 a.m. with AUC up to 0.79

Forecasting mortality-associated crowding is feasible

Abstract

Emergency department (ED) crowding is a global public health issue that has been repeatedly associated with increased mortality. Predicting future service demand would enable preventative measures aiming to eliminate crowding along with it's detrimental effects. Recent findings in our ED indicate that occupancy ratios exceeding 90% are associated with increased 10-day mortality. In this paper, we aim to predict these crisis periods using retrospective data from a large Nordic ED with a LightGBM model. We provide predictions for the whole ED and individually for it's different operational sections. We demonstrate that afternoon crowding can be predicted at 11 a.m. with an AUC of 0.82 (95% CI 0.78-0.86) and at 8 a.m. with an AUC up to 0.79 (95% CI 0.75-0.83). Consequently we show that forecasting mortality-associated crowding using anonymous administrative data is feasible.