A review on COVID-19 forecasting models

Rahimi, Iman; Fang, Chen; Gandomi, Amir H.

doi:10.1007/s00521-020-05626-8

Cited by 209 publications

(151 citation statements)

References 85 publications

(93 reference statements)

Supporting

Mentioning

125

Contrasting

Unclassified

Order By: Relevance

“…Moreover, several attempts are considered modifications of conventional compartmental models for more general and efficient forecasting (e.g., [9,10]). A review of COVID-19 forecasting models is in [11]. In this review, it was shown that deep learning models can reach to human expert level but it requires a relatively large amount of training data.…”

Section: Introductionmentioning

confidence: 99%

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Rashed

Hirata

2021

IJERPH

View full text Add to dashboard Cite

The significant health and economic effects of COVID-19 emphasize the requirement for reliable forecasting models to avoid the sudden collapse of healthcare facilities with overloaded hospitals. Several forecasting models have been developed based on the data acquired within the early stages of the virus spread. However, with the recent emergence of new virus variants, it is unclear how the new strains could influence the efficiency of forecasting using models adopted using earlier data. In this study, we analyzed daily positive cases (DPC) data using a machine learning model to understand the effect of new viral variants on morbidity rates. A deep learning model that considers several environmental and mobility factors was used to forecast DPC in six districts of Japan. From machine learning predictions with training data since the early days of COVID-19, high-quality estimation has been achieved for data obtained earlier than March 2021. However, a significant upsurge was observed in some districts after the discovery of the new COVID-19 variant B.1.1.7 (Alpha). An average increase of 20–40% in DPC was observed after the emergence of the Alpha variant and an increase of up to 20% has been recognized in the effective reproduction number. Approximately four weeks was needed for the machine learning model to adjust the forecasting error caused by the new variants. The comparison between machine-learning predictions and reported values demonstrated that the emergence of new virus variants should be considered within COVID-19 forecasting models. This study presents an easy yet efficient way to quantify the change caused by new viral variants with potential usefulness for global data analysis.

show abstract

Section: Introductionmentioning

confidence: 99%

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Rashed

Hirata

2021

IJERPH

View full text Add to dashboard Cite

show abstract

“…Since the beginning of the COVID-19 pandemic, the academic literature has witnessed a vast surge of modelling studies. Existing reviews highlight the importance of compartmental models of COVID-19, in connection with other models based on time series forecasting and machine learning [ 12 , 13 ]. Compartmental models mathematically encode known and emerging information about the transmission dynamics of the disease and have been locally applied across numerous contexts around the world, including major sites of COVID-19 transmission like China, India, Brazil, the United States, and the United Kingdom [ 14 – 18 ].…”

Section: Related Workmentioning

confidence: 99%

Impact of vaccine supplies and delays on optimal control of the COVID-19 pandemic: mapping interventions for the Philippines

et al. 2021

View full text Add to dashboard Cite

Background Around the world, controlling the COVID-19 pandemic requires national coordination of multiple intervention strategies. As vaccinations are globally introduced into the repertoire of available interventions, it is important to consider how changes in the local supply of vaccines, including delays in administration, may be addressed through existing policy levers. This study aims to identify the optimal level of interventions for COVID-19 from 2021 to 2022 in the Philippines, which as a developing country is particularly vulnerable to shifting assumptions around vaccine availability. Furthermore, we explore optimal strategies in scenarios featuring delays in vaccine administration, expansions of vaccine supply, and limited combinations of interventions. Methods Embedding our work within the local policy landscape, we apply optimal control theory to the compartmental model of COVID-19 used by the Philippine government’s pandemic surveillance platform and introduce four controls: (a) precautionary measures like community quarantines, (b) detection of asymptomatic cases, (c) detection of symptomatic cases, and (d) vaccinations. The model is fitted to local data using an L-BFGS minimization procedure. Optimality conditions are identified using Pontryagin’s minimum principle and numerically solved using the forward–backward sweep method. Results Simulation results indicate that early and effective implementation of both precautionary measures and symptomatic case detection is vital for averting the most infections at an efficient cost, resulting in $$>99\%$$ > 99 % reduction of infections compared to the no-control scenario. Expanding vaccine administration capacity to 440,000 full immunizations daily will reduce the overall cost of optimal strategy by $$25\%$$ 25 % , while allowing for a faster relaxation of more resource-intensive interventions. Furthermore, delays in vaccine administration require compensatory increases in the remaining policy levers to maintain a minimal number of infections. For example, delaying the vaccines by 180 days (6 months) will result in an $$18\%$$ 18 % increase in the cost of the optimal strategy. Conclusion We conclude with practical insights regarding policy priorities particularly attuned to the Philippine context, but also applicable more broadly in similar resource-constrained settings. We emphasize three key takeaways of (a) sustaining efficient case detection, isolation, and treatment strategies; (b) expanding not only vaccine supply but also the capacity to administer them, and; (c) timeliness and consistency in adopting policy measures. Graphic Abstract

show abstract

“…Different models have been designed to predict future positive/death cases [7][8][9][10][11][12]. Machine learning and other artificial intelligence techniques are expected to provide better data analysis and lead to its understanding as well as provide more accurate prediction models [11,[13][14][15][16][17][18][19][20].…”

Section: Introductionmentioning

confidence: 99%

One-Year Lesson: Machine Learning Prediction of COVID-19 Positive Cases with Meteorological Data and Mobility Estimate in Japan

Rashed

Hirata

2021

IJERPH

View full text Add to dashboard Cite

With the wide spread of COVID-19 and the corresponding negative impact on different life aspects, it becomes important to understand ways to deal with the pandemic as a part of daily routine. After a year of the COVID-19 pandemic, it has become obvious that different factors, including meteorological factors, influence the speed at which the disease is spread and the potential fatalities. However, the impact of each factor on the speed at which COVID-19 is spreading remains controversial. Accurate forecasting of potential positive cases may lead to better management of healthcare resources and provide guidelines for government policies in terms of the action required within an effective timeframe. Recently, Google Cloud has provided online COVID-19 forecasting data for the United States and Japan, which would help in predicting future situations on a state/prefecture scale and are updated on a day-by-day basis. In this study, we propose a deep learning architecture to predict the spread of COVID-19 considering various factors, such as meteorological data and public mobility estimates, and applied it to data collected in Japan to demonstrate its effectiveness. The proposed model was constructed using a neural network architecture based on a long short-term memory (LSTM) network. The model consists of multi-path LSTM layers that are trained using time-series meteorological data and public mobility data obtained from open-source data. The model was tested using different time frames, and the results were compared to Google Cloud forecasts. Public mobility is a dominant factor in estimating new positive cases, whereas meteorological data improve their accuracy. The average relative error of the proposed model ranged from 16.1% to 22.6% in major regions, which is a significant improvement compared with Google Cloud forecasting. This model can be used to provide public awareness regarding the morbidity risk of the COVID-19 pandemic in a feasible manner.

show abstract

A review on COVID-19 forecasting models

Cited by 209 publications

References 85 publications

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Infectivity Upsurge by COVID-19 Viral Variants in Japan: Evidence from Deep Learning Modeling

Impact of vaccine supplies and delays on optimal control of the COVID-19 pandemic: mapping interventions for the Philippines

One-Year Lesson: Machine Learning Prediction of COVID-19 Positive Cases with Meteorological Data and Mobility Estimate in Japan

Contact Info

Product

Resources

About