Leveraging Herpangina Data to Enhance Hospital-level Prediction of Hand-Foot-and-Mouth Disease Admissions Using UPTST

TL;DR

This paper introduces a novel transformer-based model leveraging herpangina data to improve hospital-level prediction of hand-foot-and-mouth disease admissions, demonstrating superior accuracy and potential broader applications.

Contribution

The paper presents a U-net shaped transformer model with patching and joint prediction strategies, incorporating representation learning for enhanced disease admission forecasting.

Findings

Outperforms existing models in prediction accuracy

Effective for both long- and short-term forecasts

Potential applicability beyond infectious disease prediction

Abstract

Outbreaks of hand-foot-and-mouth disease(HFMD) have been associated with significant morbidity and, in severe cases, mortality. Accurate forecasting of daily admissions of pediatric HFMD patients is therefore crucial for aiding the hospital in preparing for potential outbreaks and mitigating nosocomial transmissions. To address this pressing need, we propose a novel transformer-based model with a U-net shape, utilizing the patching strategy and the joint prediction strategy that capitalizes on insights from herpangina, a disease closely correlated with HFMD. This model also integrates representation learning by introducing reconstruction loss as an auxiliary loss. The results show that our U-net Patching Time Series Transformer (UPTST) model outperforms existing approaches in both long- and short-arm prediction accuracy of HFMD at hospital-level. Furthermore, the exploratory extension experiments show that the model's capabilities extend beyond prediction of infectious disease, suggesting broader applicability in various domains.