Using community syndromic surveillance to anticipate enterovirus-related school class suspensions: A real-time LSTM approach - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Leveraging Community Syndromic Surveillance to Predict School Closures Due to Enterovirus: A Real-Time LSTM Method

  • By

  • Chinmayee Rayguru

  • Hong-Lian Jian

  • Yi-Fan Peng

  • Kevin J Chen

  • Po-Huang Chiang

  • Ta-Chien Chan

  • July 13, 2026

Share

  • 1

    Enterovirus infections in Taiwan increased by 619.5% after declining during the COVID-19 pandemic, according to evidence cited in the study.

  • 2

    Traditional surveillance methods relying on fixed statistical thresholds may fail when disease patterns evolve or exhibit complex, nonlinear trends.

  • 3

    The study developed district-specific LSTM models that used 30 days of EV-like syndromic data to generate forecasts up to 14 days in advance.

  • 4

    Residual-based alarms from pediatric outpatient surveillance were compared with abnormal preschool and primary school class suspension days across Taipei.

  • 5

    The LSTM framework achieved accuracies of 0.94 for preschool data and 0.96 for primary school data and generally generated alarms before abnormal class suspension days.

Original Source(s)

Using community syndromic surveillance to anticipate enterovirus-related school class suspensions: A real-time LSTM approach

  • by Chinmayee Rayguru, Hong-Lian Jian, Yi-Fan Peng, Kevin J Chen, Po-Huang Chiang, Ta-Chien Chan

  • July 13, 2026

Related Content

Water, Energy, and Food Insecurities as Determinants of Health

HHS Successfully Concludes Hantavirus Response Effort; Monitoring Ends with No Positive U.S. Case

Expedition cruises, island hopping, and zoonotic risk: governance and operational lessons from the MV Hondius Andes hantavirus outbreak