Forecasting emergency department visits in the reference hospital of the Balearic Islands: the role of tourist and weather data

TL;DR

This study develops machine learning models to forecast emergency department visits in Mallorca using tourism, weather, calendar, and demographic data, highlighting the importance of variable selection for accurate short- and long-term predictions.

Contribution

It demonstrates that non-time-series models with relevant exogenous variables can match the accuracy of time-series models for long-term ED visit forecasting.

Findings

Calendar, resident, and tourist data significantly improve prediction accuracy.

Weather data does not enhance forecast performance.

Time-series models outperform non-time-series models for short-term predictions.

Abstract

Accurate forecasting of patient arrivals at emergency departments (EDs) is vital for efficient resource allocation and high-quality patient care. In this study we investigate the relevance of exogenous variables, namely tourism, weather, calendar and demographic variables, in forecasting ED visits in the reference hospital in Palma de Mallorca, a city with significant seasonal population fluctuations due to tourism. Using a machine learning approach, we develop a model that predicts ED visits based solely on these exogenous variables. We test different machine learning algorithms (random forests, support vector machines, and feedforward neural networks) with different combinations of input variables and compare their symmetric mean average percentage errors (SMAPEs). Our findings reveal that calendar information, resident, and tourist population data are statistically significant for the accuracy of the predictions, while the addition of weather data does not provide any further improvement. Comparison of non-time-series with time-series prediction models reveals that the latter provide better accuracy for short prediction horizons (e.g. shorter than a week). Furthermore, time-series models become less or equally accurate to models relying only on exogenous variables for long prediction horizons (e.g. fortnight or month). Our study highlights the importance of carefully selecting predictive variables to ensure short- and long-term, robust and reliable forecasts. This demonstrates that, despite their lower complexity, non-time-series models with well-chosen input variables can be as effective as time-series models when predicting for long time horizons.