COVID-19 ICU demand forecasting: A two-stage Prophet-LSTM approach

https://doi.org/10.1016/j.asoc.2022.109181Get rights and content

Highlights

  • We propose a novel two-stage integration of Prophet and LSTM forecasting models.

  • We use Prophet-LSTM to predict daily COVID-19 ICU entrances for a Brazilian city.

  • We explore vaccination rates, non-pharmaceutical interventions, and other indexes as predictors.

  • Prophet-LSTM produced MAEs 14.2% and 17.3% smaller than Prophet and LSTM standalone models.

  • Prophet-LSTM produced MAEs from 13% to 45% smaller than univariate and multivariate benchmarks.

Abstract

Recent literature has revealed a growing interest in methods for anticipating the demand for medical items and personnel at hospital, especially during turbulent scenarios such as the COVID-19 pandemic. In times like those, new variables appear and affect the once known demand behavior. This paper investigates the hypothesis that the combined Prophet-LSTM method results in more accurate forecastings for COVID-19 hospital Intensive Care Units (ICUs) demand than both standalone models, Prophet and LSTM (Long Short-Term Memory Neural Network). We also compare the model to well-established demand forecasting benchmarks. The model is tested to a representative Brazilian municipality that serves as a medical reference to other cities within its region. In addition to traditional time series components, such as trend and seasonality, other variables such as the current number of daily COVID-19 cases, vaccination rates, non-pharmaceutical interventions, social isolation index, and regional hospital beds occupation are also used to explain the variations in COVID-19 hospital ICU demand. Results indicate that the proposed method produced Mean Average Errors (MAE) from 13% to 45% lower than well established statistical and machine learning forecasting models, including the standalone models.

Keywords

Neural networks
Forecasting
Time series
Machine learning
Decision support systems

Cited by (0)

View Abstract