Combining digital data streams and epidemic networks for real time outbreak detection

• URL: http://arxiv.org/abs/2511.07163v1
• Date: Mon, 10 Nov 2025 14:53:52 GMT
• Title: Combining digital data streams and epidemic networks for real time outbreak detection
• Authors: Ruiqi Lyu, Alistair Turcan, Bryan Wilder,
• Abstract summary: We present LRTrend, a machine learning framework to identify outbreaks in real time.<n> LRTrend effectively aggregates diverse health and behavioral data streams within one region.<n>It learns disease-specific epidemic networks to aggregate information across regions.
• Score: 14.31847187460321
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Responding to disease outbreaks requires close surveillance of their trajectories, but outbreak detection is hindered by the high noise in epidemic time series. Aggregating information across data sources has shown great denoising ability in other fields, but remains underexplored in epidemiology. Here, we present LRTrend, an interpretable machine learning framework to identify outbreaks in real time. LRTrend effectively aggregates diverse health and behavioral data streams within one region and learns disease-specific epidemic networks to aggregate information across regions. We reveal diverse epidemic clusters and connections across the United States that are not well explained by commonly used human mobility networks and may be informative for future public health coordination. We apply LRTrend to 2 years of COVID-19 data in 305 hospital referral regions and frequently detect regional Delta and Omicron waves within 2 weeks of the outbreak's start, when case counts are a small fraction of the wave's resulting peak.

Related papers

• Epidemiology-informed Graph Neural Network for Heterogeneity-aware Epidemic Forecasting [46.63739322178277]
  Recent studies have demonstrated the strong potential of of-temporal neural networks (STGNNs) in extracting heterogeneous-temporal epidemic patterns. HeatGNN learns epidemiology-informed locations embedding different locations that reflect their own transmission mechanisms over time. HeatGNN outperforms various strong baselines of HeatHeat on different sizes of Heat.
  arXiv  Detail & Related papers  (2024-11-26T12:29:45Z)
• Predictors of disease outbreaks at continentalscale in the African region: Insights and predictions with geospatial artificial intelligence using earth observations and routine disease surveillance data [0.0]
  This study covers a significant portion of the African continent (about 17,885,000 km2). We first applied global and local spatial autocorrelation for malaria, cholera, meningitis, and yellow fever case counts. We then used machine learning to predict the weekly presence of these diseases in the second-level administrative district.
  arXiv  Detail & Related papers  (2024-11-10T11:43:51Z)
• Event Detection from Social Media for Epidemic Prediction [76.90779562626541]
  We develop a framework to extract and analyze epidemic-related events from social media posts. Experimentation reveals how ED models trained on COVID-based SPEED can effectively detect epidemic events for three unseen epidemics. We show that reporting sharp increases in the extracted events by our framework can provide warnings 4-9 weeks earlier than the WHO epidemic declaration for Monkeypox.
  arXiv  Detail & Related papers  (2024-04-02T06:31:17Z)
• Epidemic outbreak prediction using machine learning models [0.0]
  In this article, we try to predict the epidemic outbreak (influenza, hepatitis and malaria) for the state of New York, USA using machine and deep learning algorithms. The algorithm takes historical data to predict the possible number of cases for 5 weeks into the future. Non-clinical factors like google search trends,social media data and weather data have also been used to predict the probability of an outbreak.
  arXiv  Detail & Related papers  (2023-10-30T17:28:44Z)
• Digital Surveillance Networks of 2014 Ebola Epidemics and Lessons for COVID-19 [0.0]
  2014 Ebola outbreaks can offer lessons for the COVOID-19. We are increasingly seeing a delay and disconnect of the transmission of locally situated information.
  arXiv  Detail & Related papers  (2022-06-18T16:06:29Z)
• Impact of initial outbreak locations on transmission risk of infectious diseases in an intra-urban area [4.738791349182193]
  Infectious diseases usually originate from a specific location within a city. Due to the heterogenous distribution of population and public facilities, infectious diseases break out at different locations would cause different transmission risk and control difficulty. This study aims to investigate the impact of initial outbreak locations on the risk of transmission and reveal the driving force behind high outbreak-risk locations.
  arXiv  Detail & Related papers  (2022-03-23T08:21:32Z)
• Early Detection of COVID-19 Hotspots Using Spatio-Temporal Data [66.70036251870988]
  The Centers for Disease Control and Prevention (CDC) has worked with other federal agencies to identify counties with increasing coronavirus 2019 (CO-19) incidence (hotspots) This paper presents a sparse model for early detection of COVID-19 hotspots (at the county level) in the United States. Deep neural networks are introduced to enhance the model's representative power while still enjoying the interpretability of the kernel.
  arXiv  Detail & Related papers  (2021-05-31T19:28:17Z)
• Health Status Prediction with Local-Global Heterogeneous Behavior Graph [69.99431339130105]
  Estimation of health status can be achieved with various kinds of data streams continuously collected from wearable sensors. We propose to model the behavior-related multi-source data streams with a local-global graph. We take experiments on StudentLife dataset, and extensive results demonstrate the effectiveness of our proposed model.
  arXiv  Detail & Related papers  (2021-03-23T11:10:04Z)
• Understanding the temporal evolution of COVID-19 research through machine learning and natural language processing [66.63200823918429]
  The outbreak of the novel coronavirus disease 2019 (COVID-19), caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has been continuously affecting human lives and communities around the world. We used multiple data sources, i.e., PubMed and ArXiv, and built several machine learning models to characterize the landscape of current COVID-19 research. Our findings confirm the types of research available in PubMed and ArXiv differ significantly, with the former exhibiting greater diversity in terms of COVID-19 related issues.
  arXiv  Detail & Related papers  (2020-07-22T18:02:39Z)
• Cross-lingual Transfer Learning for COVID-19 Outbreak Alignment [90.12602012910465]
  We train on Italy's early COVID-19 outbreak through Twitter and transfer to several other countries. Our experiments show strong results with up to 0.85 Spearman correlation in cross-country predictions.
  arXiv  Detail & Related papers  (2020-06-05T02:04:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.