An ensemble approach to short-term forecast of COVID-19 intensive care occupancy in Italian Regions

TL;DR

This paper presents an ensemble method combining regression and autoregressive models for short-term ICU bed occupancy forecasting during COVID-19 in Italy, demonstrating effective regional predictions during the outbreak.

Contribution

The study introduces a novel ensemble approach that integrates two simple models for accurate short-term ICU occupancy prediction during COVID-19.

Findings

Effective ICU occupancy forecasts during the Italian COVID-19 outbreak

Ensemble approach outperforms individual models in predictive accuracy

Validated predictions at regional level with promising results

Abstract

The availability of intensive care beds during the Covid-19 epidemic is crucial to guarantee the best possible treatment to severely affected patients. In this work we show a simple strategy for short-term prediction of Covid-19 ICU beds, that has proved very effective during the Italian outbreak in February to May 2020. Our approach is based on an optimal ensemble of two simple methods: a generalized linear mixed regression model which pools information over different areas, and an area-specific non-stationary integer autoregressive methodology. Optimal weights are estimated using a leave-last-out rationale. The approach has been set up and validated during the epidemic in Italy. A report of its performance for predicting ICU occupancy at Regional level is included.