Did the Tokyo Olympic Games enhance the transmission of COVID-19? An interpretation with machine learning. (July 2022)
- Record Type:
- Journal Article
- Title:
- Did the Tokyo Olympic Games enhance the transmission of COVID-19? An interpretation with machine learning. (July 2022)
- Main Title:
- Did the Tokyo Olympic Games enhance the transmission of COVID-19? An interpretation with machine learning
- Authors:
- Hirata, Akimasa
Kodera, Sachiko
Diao, Yinliang
Rashed, Essam A. - Abstract:
- Abstract: Background: In the summer of 2021, the Olympic Games were held in Tokyo during the state of emergency due to the spread of COVID-19 pandemic. New daily positive cases (DPC) increased before the Olympic Games, and then decreased a few weeks after the Games. However, several cofactors influencing DPC exist; consequently, careful consideration is needed for future international events during an epidemic. Methods: The impact of the Olympic Games on new DPC were evaluated in the Tokyo, Osaka, and Aichi Prefectures using a well-trained and -evaluated long short-term memory (LSTM) network. In addition, we proposed a compensation method based on effective reproduction number (ERN) to assess the effect of the national holidays on the DPC. Results: During the spread phase, the estimated DPC with LSTM was 30%–60% lower than that of the observed value, but was consistent with the compensated value of the ERN for the three prefectures. During the decay phase, the estimated DPC was consistent with the observed values. The timing of the decay coincided with achievement of a fully-vaccinated rate of 10%–15% of people aged <65 years. Conclusions: The up- and downsurge of the pandemic wave observed in July and September are likely attributable to high ERN during national holiday periods and to the vaccination effect, especially for people aged <65 years. The effect of national holidays in Tokyo was rather notable in Aichi and Osaka, which are distant from Tokyo. The effect of theAbstract: Background: In the summer of 2021, the Olympic Games were held in Tokyo during the state of emergency due to the spread of COVID-19 pandemic. New daily positive cases (DPC) increased before the Olympic Games, and then decreased a few weeks after the Games. However, several cofactors influencing DPC exist; consequently, careful consideration is needed for future international events during an epidemic. Methods: The impact of the Olympic Games on new DPC were evaluated in the Tokyo, Osaka, and Aichi Prefectures using a well-trained and -evaluated long short-term memory (LSTM) network. In addition, we proposed a compensation method based on effective reproduction number (ERN) to assess the effect of the national holidays on the DPC. Results: During the spread phase, the estimated DPC with LSTM was 30%–60% lower than that of the observed value, but was consistent with the compensated value of the ERN for the three prefectures. During the decay phase, the estimated DPC was consistent with the observed values. The timing of the decay coincided with achievement of a fully-vaccinated rate of 10%–15% of people aged <65 years. Conclusions: The up- and downsurge of the pandemic wave observed in July and September are likely attributable to high ERN during national holiday periods and to the vaccination effect, especially for people aged <65 years. The effect of national holidays in Tokyo was rather notable in Aichi and Osaka, which are distant from Tokyo. The effect of the Olympic Games on the spread and decay of the pandemic wave is neither dominant nor negligible due to the shifting of the national holiday dates to coincide with the Olympic Games. Highlights: The COVID-19 spread during Olympic Games was computationally estimated. Infection upsurge is partly caused by people's activity during national holidays. Infection downsurge is mainly attributable to the vaccination effect. Effect of Olympic Games on the COVID-19 spread was not dominant but innegligible. … (more)
- Is Part Of:
- Computers in biology and medicine. Volume 146(2022)
- Journal:
- Computers in biology and medicine
- Issue:
- Volume 146(2022)
- Issue Display:
- Volume 146, Issue 2022 (2022)
- Year:
- 2022
- Volume:
- 146
- Issue:
- 2022
- Issue Sort Value:
- 2022-0146-2022-0000
- Page Start:
- Page End:
- Publication Date:
- 2022-07
- Subjects:
- Machine learning -- COVID-19 -- Olympic games -- Viral transmission -- Numerical modeling
Medicine -- Data processing -- Periodicals
Biology -- Data processing -- Periodicals
610.285 - Journal URLs:
- http://www.sciencedirect.com/science/journal/00104825/ ↗
http://www.elsevier.com/journals ↗ - DOI:
- 10.1016/j.compbiomed.2022.105548 ↗
- Languages:
- English
- ISSNs:
- 0010-4825
- Deposit Type:
- Legaldeposit
- View Content:
- Available online (eLD content is only available in our Reading Rooms) ↗
- Physical Locations:
- British Library DSC - 3394.880000
British Library DSC - BLDSS-3PM
British Library HMNTS - ELD Digital store - Ingest File:
- 21661.xml