Assessment of the outbreak risk, mapping and infection behavior of COVID-19: Application of the autoregressive integrated-moving average (ARIMA) and polynomial models

Pourghasemi, Hamid Reza; Pouyan, Soheila; Farajzadeh, Z; Sãdhasivam, Nitheshnirmal; Heidari, Bahram; Babaei, Sedigheh; Tiefenbacher, John P.

doi:10.1371/journal.pone.0236238

Cited by 36 publications

(29 citation statements)

References 54 publications

(77 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This study explores seven commonly utilized forecasting approaches, including the following: naïve [ 18 ], moving average (MA) [ 9 , 10 ], autoregressive (AR) [ 17 ], growth rate [ 19 ], Holt-Winters (HW) exponential smoothing [ 20 , 21 ], autoregressive moving average (ARMA) [ 22 ], and autoregressive integrated moving average (ARIMA) [ 23 ]. Each forecasting method utilizes different assumptions about how the past values impact the forecast values.…”

Section: Introductionmentioning

confidence: 99%

Short-Range Forecasting of COVID-19 During Early Onset at County, Health District, and State Geographic Levels Using Seven Methods: Comparative Forecasting Study

Lynch¹,

Gore²

2021

J Med Internet Res

View full text Add to dashboard Cite

Background Forecasting methods rely on trends and averages of prior observations to forecast COVID-19 case counts. COVID-19 forecasts have received much media attention, and numerous platforms have been created to inform the public. However, forecasting effectiveness varies by geographic scope and is affected by changing assumptions in behaviors and preventative measures in response to the pandemic. Due to time requirements for developing a COVID-19 vaccine, evidence is needed to inform short-term forecasting method selection at county, health district, and state levels. Objective COVID-19 forecasts keep the public informed and contribute to public policy. As such, proper understanding of forecasting purposes and outcomes is needed to advance knowledge of health statistics for policy makers and the public. Using publicly available real-time data provided online, we aimed to evaluate the performance of seven forecasting methods utilized to forecast cumulative COVID-19 case counts. Forecasts were evaluated based on how well they forecast 1, 3, and 7 days forward when utilizing 1-, 3-, 7-, or all prior–day cumulative case counts during early virus onset. This study provides an objective evaluation of the forecasting methods to identify forecasting model assumptions that contribute to lower error in forecasting COVID-19 cumulative case growth. This information benefits professionals, decision makers, and the public relying on the data provided by short-term case count estimates at varied geographic levels. Methods We created 1-, 3-, and 7-day forecasts at the county, health district, and state levels using (1) a naïve approach, (2) Holt-Winters (HW) exponential smoothing, (3) a growth rate approach, (4) a moving average (MA) approach, (5) an autoregressive (AR) approach, (6) an autoregressive moving average (ARMA) approach, and (7) an autoregressive integrated moving average (ARIMA) approach. Forecasts relied on Virginia’s 3464 historical county-level cumulative case counts from March 7 to April 22, 2020, as reported by The New York Times. Statistically significant results were identified using 95% CIs of median absolute error (MdAE) and median absolute percentage error (MdAPE) metrics of the resulting 216,698 forecasts. Results The next-day MA forecast with 3-day look-back length obtained the lowest MdAE (median 0.67, 95% CI 0.49-0.84, P<.001) and statistically significantly differed from 39 out of 59 alternatives (66%) to 53 out of 59 alternatives (90%) at each geographic level at a significance level of .01. For short-range forecasting, methods assuming stationary means of prior days’ counts outperformed methods with assumptions of weak stationarity or nonstationarity means. MdAPE results revealed statistically significant differences across geographic levels. Conclusions For short-range COVID-19 cumulative case count forecasting at the county, health district, and state levels during early onset, the following were found: (1) the MA method was effective for forecasting 1-, 3-, and 7-day cumulative case counts; (2) exponential growth was not the best representation of case growth during early virus onset when the public was aware of the virus; and (3) geographic resolution was a factor in the selection of forecasting methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Short-Range Forecasting of COVID-19 During Early Onset at County, Health District, and State Geographic Levels Using Seven Methods: Comparative Forecasting Study

Lynch¹,

Gore²

2021

J Med Internet Res

View full text Add to dashboard Cite

show abstract

“…Place: Nineteen studies included only Iran; the other 13 studies included from 6 to 184 countries. Six studies included subnational level estimates: Haghdoost [27], Moghadami [36], Muniz-Rodriguez [37], Pourghasemi (PLoS ONE) [38], Pourghasemi (IJID) [39], and Zhan [40].…”

Section: Resultsmentioning

confidence: 99%

“…End dates of outputs ranged from 2020-02-24 (Zhuang [47]) to 2021-02-02 (Saberi (web site) [21]). Outputs duration ranged from 11 days (Muniz-Rodriguez [37]) to 364 days (IHME [12]).…”

Section: Resultsmentioning

confidence: 99%

“…Role of the symptomatic cases in spread of the disease was accounted for only in some studies; DELPHI [10], Ghaffarzadegan [41], Gu (YYG) [17] , Mashayekhi [28], Saberi (article) [22], Rahimi Rise [29], Srivastava [15]. Some studies provided some sort of subnational estimates as well as national; Haghdoost [27], Moghadami [36], Muniz-Rodriguez [37], Pourghasemi (PLoS ONE) [38], Pourghasemi (IJID) [39], and Zhan [40]. Access to COVID-19 data at provincial and subnational level has obviously been an important limitation for most researchers.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid review of COVID-19 epidemic estimation studies for Iran

Pourmalek

Hemami

Janani

et al. 2021

Preprint

View full text Add to dashboard Cite

Background: To inform researchers about the methodology and results of epidemic estimation studies performed for COVID-19 epidemic in Iran, we aimed to perform a rapid review. Methods: We searched for and included published articles, preprint manuscripts and reports that estimated numbers of cumulative or daily deaths or cases of COVID-19 in Iran. We found 131 studies and included 29 of them. Results: The included studies provided outputs for a total of 84 study-model/scenario combinations. Sixteen studies used 3-4 compartmental disease models. At the end of month two of the epidemic (2020-04-19), the lowest (and highest) values of predictions were 1777 (388951) for cumulative deaths, 20588 (2310161) for cumulative cases, and at the end of month four (2020-06-20), were 3590 (1819392) for cumulative deaths, and 144305 (4266964) for cumulative cases. Highest estimates of cumulative deaths (and cases) for latest date available in 2020 were 418834 on 2020-12-19 (and 41475792 on 2020-12-31). Model estimates predict an ominous course of epidemic progress in Iran. Increase in percent population using masks from the current situation to 95% might prevent 26790 additional deaths (95% confidence interval 19925-35208) by the end of year 2020. Conclusions: Meticulousness and degree of details reported for disease modeling and statistical methods used in the included studies varied widely. Greater heterogeneity was observed regarding the results of predicted outcomes. Consideration of minimum and preferred reporting items in epidemic estimation studies might better inform future revisions of the available models and new models to be developed. Not accounting for under-reporting drives the models’ results misleading.

show abstract

“…The most popular approach in AI design incorporates a long-term short memory-based AI engine utilizing rolling training sets [ 26 , 33 , 37 , 38 , 39 ]. Others used advanced autoregressive integrated moving average [ 18 , 35 , 40 ]. It remains to be seen which of these AI engines perform with higher sensitivity.…”

Section: Resultsmentioning

confidence: 99%

What Can COVID-19 Teach Us about Using AI in Pandemics?

et al. 2020

View full text Add to dashboard Cite

The COVID-19 pandemic put significant strain on societies and their resources, with the healthcare system and workers being particularly affected. Artificial Intelligence (AI) offers the unique possibility of improving the response to a pandemic as it emerges and evolves. Here, we utilize the WHO framework of a pandemic evolution to analyze the various AI applications. Specifically, we analyzed AI from the perspective of all five domains of the WHO pandemic response. To effectively review the current scattered literature, we organized a sample of relevant literature from various professional and popular resources. The article concludes with a consideration of AI’s weaknesses as key factors affecting AI in future pandemic preparedness and response.

show abstract

Assessment of the outbreak risk, mapping and infection behavior of COVID-19: Application of the autoregressive integrated-moving average (ARIMA) and polynomial models

Cited by 36 publications

References 54 publications

Short-Range Forecasting of COVID-19 During Early Onset at County, Health District, and State Geographic Levels Using Seven Methods: Comparative Forecasting Study

Short-Range Forecasting of COVID-19 During Early Onset at County, Health District, and State Geographic Levels Using Seven Methods: Comparative Forecasting Study

Rapid review of COVID-19 epidemic estimation studies for Iran

What Can COVID-19 Teach Us about Using AI in Pandemics?

Contact Info

Product

Resources

About