Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea

Atina Husnayain; Emily Chia Yu Su

doi:10.3233/SHTI231086

Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea

Atina Husnayain, Emily Chia Yu Su

Public Health Indonesia

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

Abstract

Search data were found to be useful variables for COVID-19 trend prediction. In this study, we aimed to investigate the performance of online search models in state space models (SSMs), linear regression (LR) models, and generalized linear models (GLMs) for South Korean data from January 20, 2020, to July 31, 2021. Principal component analysis (PCA) was run to construct the composite features which were later used in model development. Values of root mean squared error (RMSE), peak day error (PDE), and peak magnitude error (PME) were defined as loss functions. Results showed that integrating search data in the models for short- and long-term prediction resulted in a low level of RMSE values, particularly for SSMs. Findings indicated that type of model used highly impacts the performance of prediction and interpretability of the model. Furthermore, PDE and PME could be beneficial to be included in the evaluation of peaks.

Original language	English
Title of host publication	MEDINFO 2023 — The Future Is Accessible
Subtitle of host publication	Proceedings of the 19th World Congress on Medical and Health Informatics
Editors	Jen Bichel-Findlay, Paula Otero, Philip Scott, Elaine Huesing
Place of Publication	Amsterdam Netherlands
Publisher	IOS Press
Pages	855-859
Number of pages	5
ISBN (Electronic)	9781643684574
ISBN (Print)	9781643684567
DOIs	https://doi.org/10.3233/SHTI231086
Publication status	Published - 25 Jan 2024
Event	World Congress on Medical and Health Informatics 2023 - International Conference Centre, Sydney, Australia Duration: 8 Jul 2023 → 12 Aug 2023 Conference number: 19th https://medinfo2023.org/ https://ebooks.iospress.nl/volume/medinfo-2023-the-future-is-accessible-proceedings-of-the-19th-world-congress-on-medical-and-health-informatics (Published proceedings)

Publication series

Name	Studies in Health Technology and Informatics
Publisher	IOS Press
Volume	310
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	World Congress on Medical and Health Informatics 2023
Abbreviated title	MEDINFO 2023
Country/Territory	Australia
City	Sydney
Period	8/07/23 → 12/08/23
Other	Theme: The Future is Accessible
Internet address	https://medinfo2023.org/ https://ebooks.iospress.nl/volume/medinfo-2023-the-future-is-accessible-proceedings-of-the-19th-world-congress-on-medical-and-health-informatics (Published proceedings)

Keywords

COVID-19
digital epidemiology
internet search
Prediction
time series

Access to Document

10.3233/SHTI231086Licence: CC BY-NC

577660382-oaFinal published version, 421 KBLicence: CC BY-NC

Cite this

Husnayain, A., & Su, E. C. Y. (2024). Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea. In J. Bichel-Findlay, P. Otero, P. Scott, & E. Huesing (Eds.), MEDINFO 2023 — The Future Is Accessible: Proceedings of the 19th World Congress on Medical and Health Informatics (pp. 855-859). (Studies in Health Technology and Informatics; Vol. 310). IOS Press. https://doi.org/10.3233/SHTI231086

Husnayain, Atina ; Su, Emily Chia Yu. / Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea. MEDINFO 2023 — The Future Is Accessible: Proceedings of the 19th World Congress on Medical and Health Informatics. editor / Jen Bichel-Findlay ; Paula Otero ; Philip Scott ; Elaine Huesing. Amsterdam Netherlands : IOS Press, 2024. pp. 855-859 (Studies in Health Technology and Informatics).

@inproceedings{533ceacc58804993bc5beb6d641573a3,

title = "Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea",

abstract = "Search data were found to be useful variables for COVID-19 trend prediction. In this study, we aimed to investigate the performance of online search models in state space models (SSMs), linear regression (LR) models, and generalized linear models (GLMs) for South Korean data from January 20, 2020, to July 31, 2021. Principal component analysis (PCA) was run to construct the composite features which were later used in model development. Values of root mean squared error (RMSE), peak day error (PDE), and peak magnitude error (PME) were defined as loss functions. Results showed that integrating search data in the models for short- and long-term prediction resulted in a low level of RMSE values, particularly for SSMs. Findings indicated that type of model used highly impacts the performance of prediction and interpretability of the model. Furthermore, PDE and PME could be beneficial to be included in the evaluation of peaks.",

keywords = "COVID-19, digital epidemiology, internet search, Prediction, time series",

author = "Atina Husnayain and Su, {Emily Chia Yu}",

year = "2024",

month = jan,

day = "25",

doi = "10.3233/SHTI231086",

language = "English",

isbn = "9781643684567",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "855--859",

editor = "Jen Bichel-Findlay and Paula Otero and Philip Scott and Elaine Huesing",

booktitle = "MEDINFO 2023 — The Future Is Accessible",

address = "Netherlands",

note = "World Congress on Medical and Health Informatics 2023, MEDINFO 2023 ; Conference date: 08-07-2023 Through 12-08-2023",

url = "https://medinfo2023.org/, https://ebooks.iospress.nl/volume/medinfo-2023-the-future-is-accessible-proceedings-of-the-19th-world-congress-on-medical-and-health-informatics",

}

Husnayain, A & Su, ECY 2024, Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea. in J Bichel-Findlay, P Otero, P Scott & E Huesing (eds), MEDINFO 2023 — The Future Is Accessible: Proceedings of the 19th World Congress on Medical and Health Informatics. Studies in Health Technology and Informatics, vol. 310, IOS Press, Amsterdam Netherlands, pp. 855-859, World Congress on Medical and Health Informatics 2023, Sydney, New South Wales, Australia, 8/07/23. https://doi.org/10.3233/SHTI231086

Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea. / Husnayain, Atina; Su, Emily Chia Yu.
MEDINFO 2023 — The Future Is Accessible: Proceedings of the 19th World Congress on Medical and Health Informatics. ed. / Jen Bichel-Findlay; Paula Otero; Philip Scott; Elaine Huesing. Amsterdam Netherlands: IOS Press, 2024. p. 855-859 (Studies in Health Technology and Informatics; Vol. 310).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea

AU - Husnayain, Atina

AU - Su, Emily Chia Yu

N1 - Conference code: 19th

PY - 2024/1/25

Y1 - 2024/1/25

N2 - Search data were found to be useful variables for COVID-19 trend prediction. In this study, we aimed to investigate the performance of online search models in state space models (SSMs), linear regression (LR) models, and generalized linear models (GLMs) for South Korean data from January 20, 2020, to July 31, 2021. Principal component analysis (PCA) was run to construct the composite features which were later used in model development. Values of root mean squared error (RMSE), peak day error (PDE), and peak magnitude error (PME) were defined as loss functions. Results showed that integrating search data in the models for short- and long-term prediction resulted in a low level of RMSE values, particularly for SSMs. Findings indicated that type of model used highly impacts the performance of prediction and interpretability of the model. Furthermore, PDE and PME could be beneficial to be included in the evaluation of peaks.

AB - Search data were found to be useful variables for COVID-19 trend prediction. In this study, we aimed to investigate the performance of online search models in state space models (SSMs), linear regression (LR) models, and generalized linear models (GLMs) for South Korean data from January 20, 2020, to July 31, 2021. Principal component analysis (PCA) was run to construct the composite features which were later used in model development. Values of root mean squared error (RMSE), peak day error (PDE), and peak magnitude error (PME) were defined as loss functions. Results showed that integrating search data in the models for short- and long-term prediction resulted in a low level of RMSE values, particularly for SSMs. Findings indicated that type of model used highly impacts the performance of prediction and interpretability of the model. Furthermore, PDE and PME could be beneficial to be included in the evaluation of peaks.

KW - COVID-19

KW - digital epidemiology

KW - internet search

KW - Prediction

KW - time series

UR - http://www.scopus.com/inward/record.url?scp=85183584792&partnerID=8YFLogxK

U2 - 10.3233/SHTI231086

DO - 10.3233/SHTI231086

M3 - Conference Paper

C2 - 38269930

AN - SCOPUS:85183584792

SN - 9781643684567

T3 - Studies in Health Technology and Informatics

SP - 855

EP - 859

BT - MEDINFO 2023 — The Future Is Accessible

A2 - Bichel-Findlay, Jen

A2 - Otero, Paula

A2 - Scott, Philip

A2 - Huesing, Elaine

PB - IOS Press

CY - Amsterdam Netherlands

T2 - World Congress on Medical and Health Informatics 2023

Y2 - 8 July 2023 through 12 August 2023

ER -

Husnayain A, Su ECY. Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea. In Bichel-Findlay J, Otero P, Scott P, Huesing E, editors, MEDINFO 2023 — The Future Is Accessible: Proceedings of the 19th World Congress on Medical and Health Informatics. Amsterdam Netherlands: IOS Press. 2024. p. 855-859. (Studies in Health Technology and Informatics). doi: 10.3233/SHTI231086

Assessing internet search models in predicting daily new COVID-19 cases and deaths in South Korea

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Cite this