What question did this study set out to answer?

This work aims to develop a framework to accurately predict hourly patient arrivals at emergency departments using machine learning techniques.

May 4, 2026Open Access

Predicting Emergency Department Patient Arrivals at Hospitals Using Machine Learning Techniques

Key Points

This work aims to develop a framework to accurately predict hourly patient arrivals at emergency departments using machine learning techniques.
Developed six forecasting approaches (including Ridge Regression, TCN, LSTM).
Used de-identified hourly patient arrival data and engineered 183 features from temporal indicators.
Optimized models using Bayesian hyperparameter search with an asymmetric loss function.
Ridge Regression achieved the lowest MAE of 3.75 (R2 = 0.52).
TCN and LSTM yielded MAEs of 3.80 and 3.85, respectively.
Ridge performed marginally better than LightGBM (p=0.028), while all ML models significantly outperformed baseline methods (p<0.001).

Abstract

Background/Objective: Emergency Departments (EDs) face persistent challenges with overcrowding, unpredictable patient arrivals, and difficulty forecasting short-term demand. Precise hourly arrival predictions are crucial for effective staffing, optimal resource management, and minimizing entry delays. Methods: This paper develops and evaluates a forecasting framework comparing six approaches (a Seasonal Naive baseline, Exponential Smoothing (ETS), Ridge Regression, LightGBM, a hybrid Temporal Convolutional Network (TCN), and a hybrid Long Short-Term Memory (LSTM) network) using de-identified hourly patient arrival records from an ED in Madinah, Saudi Arabia, covering January–November 2024. A set of 183 engineered features is constructed from cyclical time encodings, weekend and public-holiday indicators, structured autoregressive lags, and volatility measures, with all lag-based features verified to use strictly retrospective information. Models are optimized using Bayesian hyperparameter search and trained under an asymmetric loss function that penalizes underprediction to reflect operational risk. Results: Results on a 14-day hold-out test set show that Ridge Regression achieves the lowest MAE (3.75, R2 = 0.52), with TCN and LSTM essentially tied (MAE 3.80 and 3.85). Diebold–Mariano tests confirm that Ridge, TCN, and LSTM are statistically indistinguishable from one another and that Ridge is marginally significantly better than LightGBM (p=0.028); all four ML models significantly outperform ETS and the Seasonal Naive baseline (p<0.001). On the asymmetric metric, TCN achieves the best AsymRMSE (5.59), reflecting its tendency to err on the safe side of staffing decisions. Robustness is confirmed through sensitivity analysis across penalty factors, feature ablation demonstrating the contribution of each feature group without overfitting, expanding-window cross-validation across three independent monthly test periods, and conformal prediction intervals achieving well-calibrated coverage. Conclusions: These results demonstrate that combining engineered temporal features with either a lightweight linear model or a hybrid sequence model yields accurate hourly ED arrival forecasts; whether the achieved accuracy is operationally sufficient for staffing decisions remains a site-specific question that requires clinical validation beyond the scope of this single-center study.

Read Full Paperexternally

AIに質問

Bookmark

View Full Paper