TY - JOUR
T1 - Towards development of functional climate-driven early warning systems for climate-sensitive infectious diseases
T2 - Statistical models and recommendations
AU - Haque, Shovanur
AU - Mengersen, Kerrie
AU - Barr, Ian
AU - Wang, Liping
AU - Yang, Weizhong
AU - Vardoulakis, Sotiris
AU - Bambrick, Hilary
AU - Hu, Wenbiao
N1 - Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.
Funding Information:
Advanced analytical techniques, including statistical modelling, machine learning algorithms, and spatiotemporal analysis, are applied to these integrated data (Fig. 1) to identify early signals of disease outbreaks, track their progression, and assess their potential impact. An example of such a tool is the HealthMap system, which employs data mining and natural language processing techniques to aggregate and visualize disease outbreak information from various sources, including news reports, social media, and official health alerts (Brownstein et al., 2009). This tool enhances situational awareness and aids in the rapid identification of potential health threats. Another automated surveillance system, BioCaster, integrates text mining techniques, severity indicator recognition, ontology-based inferencing, and cross-language term equivalence, making it a comprehensive and effective tool for disease surveillance and early detection (Collier et al., 2008). BioCaster has been reintroduced in 2021 with advancements in methodology. The system utilizes state-of-the-art neural network language models for early disease detection from news sources. Recent upgrades include neural machine translation in multiple languages, neural classification of outbreak reports, and a cloud-based visualization dashboard (Meng et al., 2022). EpiCaster is an integrated web application developed for evaluating and forecasting various epidemics, such as Flu and Ebola across different global regions. It enables users to assess epidemic severity at detailed spatio-temporal levels, offering dynamic heat maps and graphs to visualize disease trends. EpiCaster integrates data from sources like Google Flu Trends (GFT) and the World Health Organization (WHO), presenting forecasts generated from diverse epidemiological models. Users can select specific models through the interface and explore disease propagation alongside tailored intervention strategies (Deodhar et al., 2015). Flu Near You (FNY) is a crowdsourced disease surveillance system initiated in 2011 by the American Public Health Association (APHA), HealthMap of Boston Children's Hospital, and the Skoll Global Threats Fund. Operating in the United States and Canada, FNY provides a platform through its website, mobile app, and Facebook for volunteers to submit weekly surveys about their ILI (Influenza-Like Illness) symptoms. This information is collected, analysed, and displayed on the FNY website, allowing comparisons with Centers for Disease Control and Prevention (CDC) data and Google Flu Trends via maps and charts (Chunara et al., 2013; Smolinski et al., 2015)..We acknowledge the HEAL (Healthy Environments And Lives) National Research Network, which receives funding from the National Health and Medical Research Council (NHMRC) Special Initiative in Human Health and Environmental Change (Grant No. 2008937). We also acknowledge the National Foundation for Australia-China Relations (Grant No. 220011), the Australian Department of Foreign Affairs and Trade.
Funding Information:
We acknowledge the HEAL (Healthy Environments And Lives) National Research Network, which receives funding from the National Health and Medical Research Council ( NHMRC ) Special Initiative in Human Health and Environmental Change (Grant No. 2008937). We also acknowledge the National Foundation for Australia-China Relations (Grant No. 220011), the Australian Department of Foreign Affairs and Trade .
Publisher Copyright:
© 2024 The Authors
PY - 2024/5/15
Y1 - 2024/5/15
N2 - Climate, weather and environmental change have significantly influenced patterns of infectious disease transmission, necessitating the development of early warning systems to anticipate potential impacts and respond in a timely and effective way. Statistical modelling plays a pivotal role in understanding the intricate relationships between climatic factors and infectious disease transmission. For example, time series regression modelling and spatial cluster analysis have been employed to identify risk factors and predict spatial and temporal patterns of infectious diseases. Recently advanced spatio-temporal models and machine learning offer an increasingly robust framework for modelling uncertainty, which is essential in climate-driven disease surveillance due to the dynamic and multifaceted nature of the data. Moreover, Artificial Intelligence (AI) techniques, including deep learning and neural networks, excel in capturing intricate patterns and hidden relationships within climate and environmental data sets. Web-based data has emerged as a powerful complement to other datasets encompassing climate variables and disease occurrences. However, given the complexity and non-linearity of climate-disease interactions, advanced techniques are required to integrate and analyse these diverse data to obtain more accurate predictions of impending outbreaks, epidemics or pandemics. This article presents an overview of an approach to creating climate-driven early warning systems with a focus on statistical model suitability and selection, along with recommendations for utilizing spatio-temporal and machine learning techniques. By addressing the limitations and embracing the recommendations for future research, we could enhance preparedness and response strategies, ultimately contributing to the safeguarding of public health in the face of evolving climate challenges.
AB - Climate, weather and environmental change have significantly influenced patterns of infectious disease transmission, necessitating the development of early warning systems to anticipate potential impacts and respond in a timely and effective way. Statistical modelling plays a pivotal role in understanding the intricate relationships between climatic factors and infectious disease transmission. For example, time series regression modelling and spatial cluster analysis have been employed to identify risk factors and predict spatial and temporal patterns of infectious diseases. Recently advanced spatio-temporal models and machine learning offer an increasingly robust framework for modelling uncertainty, which is essential in climate-driven disease surveillance due to the dynamic and multifaceted nature of the data. Moreover, Artificial Intelligence (AI) techniques, including deep learning and neural networks, excel in capturing intricate patterns and hidden relationships within climate and environmental data sets. Web-based data has emerged as a powerful complement to other datasets encompassing climate variables and disease occurrences. However, given the complexity and non-linearity of climate-disease interactions, advanced techniques are required to integrate and analyse these diverse data to obtain more accurate predictions of impending outbreaks, epidemics or pandemics. This article presents an overview of an approach to creating climate-driven early warning systems with a focus on statistical model suitability and selection, along with recommendations for utilizing spatio-temporal and machine learning techniques. By addressing the limitations and embracing the recommendations for future research, we could enhance preparedness and response strategies, ultimately contributing to the safeguarding of public health in the face of evolving climate challenges.
KW - Climate
KW - Early warning
KW - Infectious diseases
KW - Machine learning
KW - Spatio-temporal
KW - Statistical model
UR - http://www.scopus.com/inward/record.url?scp=85186351662&partnerID=8YFLogxK
U2 - 10.1016/j.envres.2024.118568
DO - 10.1016/j.envres.2024.118568
M3 - Review article
C2 - 38417659
SN - 0013-9351
VL - 249
SP - 1
EP - 15
JO - Environmental Research
JF - Environmental Research
M1 - 118568
ER -
