Exploring Feasibility of Multivariate Deep Learning Models in Predicting COVID-19 Epidemic

Abstract

Background: Mathematical models are powerful tools to study COVID-19. However, one fundamental challenge in current modeling approaches is the lack of accurate and comprehensive data. Complex epidemiological systems such as COVID-19 are especially challenging to the commonly used mechanistic model when our understanding of this pandemic rapidly refreshes.Objective: We aim to develop a data-driven workflow to extract, process, and develop deep learning (DL) methods to model the COVID-19 epidemic. We provide an alternative modeling approach to complement the current mechanistic modeling paradigm.Method: We extensively searched, extracted, and annotated relevant datasets from over 60 official press releases in Hubei, China, in 2020. Multivariate long short-term memory (LSTM) models were developed with different architectures to track and predict multivariate COVID-19 time series for 1, 2, and 3 days ahead. As a comparison, univariate LSTMs were also developed to track new cases, total cases, and new deaths.Results: A comprehensive dataset with 10 variables was retrieved and processed for 125 days in Hubei. Multivariate LSTM had reasonably good predictability on new deaths, hospitalization of both severe and critical patients, total discharges, and total monitored in hospital. Multivariate LSTM showed better results for new and total cases, and new deaths for 1-day-ahead prediction than univariate counterparts, but not for 2-day and 3-day-ahead predictions. Besides, more complex LSTM architecture seemed not to increase overall predictability in this study.Conclusion: This study demonstrates the feasibility of DL models to complement current mechanistic approaches when the exact epidemiological mechanisms are still under investigation.

Risk of COVID-19 Infection in Public Transportation: The Development of a Model

“…To date, many studies have been conducted on COVID-19 transmission to effectively contain its spread. Representative infection transmission models, such as the susceptible–infected–removed model [ 3 , 4 , 5 , 6 , 7 ] and data-driven time series [ 8 , 9 ], are macroscopic models. These models have the advantage of including macro-parameters and data.…”

Deep learning for Covid-19 forecasting: State-of-the-art review.

“…Similarly, ConvLSTM achieved the best results in a comparative study against 5 other models using data from 8 different countries over the period Jan 22 - Sep 6, 2020 and achieved MAPE in the range 0.628 - 6.021 [18] . Other LSTM variants such as multivariate LSTM and encoder-decoder LSTM have also shown promising results [15] . A summary of the current studies is provided in Table 5 .…”

“… Study Methodology Data MAPE Chandra et al, 2022 [14] Compared LSTM and its variants in 2-month ahead forecasting of cases in India and found that ED-LSTM achieves the lowest error. India; Apr 2020 - Sep, 2021 Chen et al, 2021 [15] Used M-LSTM with 10 input variables. The mutivariate model was shown to perform better than the individual univariate models.…”

Spatio-temporal prediction of the COVID-19 pandemic in US counties: modeling with a deep LSTM neural network

“…Specifically, the family of deep recurrent neural networks have proven to be an attractive approach for epidemic forecast 56 due to their acute capability to learn time series. Among these methods, uni-variate 57 and multi-variate 58 , 59 LSTM models have been successful at predicting influenza and COVID-19, mainly due to their capability to memorize long-term dependencies. DeepGLEAM 60 uses a stochastic Diffusion Convolutional RNN (DCRNN) model, which considers short (commuting) and long range (air flight) mobility network connections, to forecast COVID-19 deaths at county and state granularities.…”