This decommissioned ERA site remains active temporarily to support our final migration steps to https://ualberta.scholaris.ca, ERA's new home. All new collections and items, including Spring 2025 theses, are at that site. For assistance, please contact erahelp@ualberta.ca.
- 33 views
- 60 downloads
An early warning indicator trained on stochastic disease-spreading models with different noises
-
- Author(s) / Creator(s)
-
Abstract
(description taken from article)
The timely detection of disease outbreaks through reliable early warning signals (EWSs) is indispensable for effective public health mitigation strategies. Nevertheless, the intricate dynamics of real-world disease spread, often influenced by diverse sources of noise and limited data in the early stages of outbreaks, pose a significant challenge in developing reliable EWSs, as the performance of existing indicators varies with extrinsic and intrinsic noises. Here, we address the challenge of modeling disease when the measurements are corrupted by additive white noise, multiplicative environmental noise, and demographic noise into a standard epidemic mathematical model. To navigate the complexities introduced by these noise sources, we employ a deep learning algorithm that provides EWS in infectious disease outbreak by training on noise-induced disease-spreading models. The indicator’s effectiveness is demonstrated through its application to real-world COVID-19 cases in Edmonton and simulated time series derived from diverse disease spread models affected by noise. Notably, the indicator captures an impending transition in a time series of disease outbreaks and outperforms existing indicators. This study contributes to advancing early warning capabilities by addressing the intricate dynamics inherent in real-world disease spread, presenting a promising avenue for enhancing public health preparedness and response efforts.
Supplementary Materials
(description taken from article)
White noise data, represented by equation (2.5), simulates random fluctuations that are uniform across time. Environmental noise, represented by equation (2.8), reflects external factors such as environmental disruptions. Demographic noise, represented by equation (2.9), captures temporal variations within population processes, including births, deaths, immigration, emigration, and state transitions. While synthetic data allows for controlled experiments and extensive training sets, real-world data is more complex due to its inherent variability and numerous unpredictable factors. For instance, real COVID-19 data exhibits noise and fluctuations and to mimic these fluctuations, we added random noise intensity to the synthetic data, incorporating different levels of fluctuations. Transition times were randomly chosen between 0 to 1500 in these synthetic time series. Since the exact time of transition in real-world diseases like COVID-19 is unknown, these random transition points enable the deep learning model to anticipate critical transitions despite the uncertainty in transition times. -
- Date created
- 2024-08-09
-
- Type of Item
- Article (Published)