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

## TL;DR

This study explores how tourism and calendar data help predict emergency department visits in a tourist city, finding that non-time-series models can be as effective as complex models for long-term forecasts.

## Contribution

The study introduces a machine learning approach using exogenous variables to forecast ED visits, emphasizing the effectiveness of non-time-series models with well-chosen inputs.

## Key findings

- Calendar and population data significantly improve prediction accuracy.
- Weather data does not enhance model performance.
- Non-time-series models perform as well as time-series models for long-term forecasts.

## 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.