Open AccessForecasting national and regional level intensive care unit bed demand during COVID-19: The case of Italy
Author(s) -
Simone Gitto,
Carmela Di Mauro,
Alessandro Ancarani,
Paolo Mancuso
Publication year - 2021
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0247726
Subject(s) - covid-19 , mean absolute percentage error , consistency (knowledge bases) , unit (ring theory) , econometrics , intensive care unit , statistics , outbreak , operations research , computer science , mean squared error , medicine , economics , mathematics , intensive care medicine , mathematics education , disease , pathology , virology , artificial intelligence , infectious disease (medical specialty)
Given the pressure on healthcare authorities to assess whether hospital capacity allows properly responding to outbreaks such as COVID-19, there is a need for simple, data-driven methods that may provide accurate forecasts of hospital bed demand. This study applies growth models to forecast the demand for Intensive Care Unit admissions in Italy during COVID-19. We show that, with only some mild assumptions on the functional form and using short time-series, the model fits past data well and can accurately forecast demand fourteen days ahead (the mean absolute percentage error (MAPE) of the cumulative fourteen days forecasts is 7.64). The model is then applied to derive regional-level forecasts by adopting hierarchical methods that ensure the consistency between national and regional level forecasts. Predictions are compared with current hospital capacity in the different Italian regions, with the aim to evaluate the adequacy of the expansion in the number of beds implemented during the COVID-19 crisis.