An official website of the United States government
Abstract ObjectivesWest Nile virus (WNV) is the most common mosquito-borne disease in the United States. Predicting the location and timing of outbreaks would allow targeting of disease prevention and mosquito control activities. Our objective was to develop software (ArboMAP) for routine WNV forecasting using public health surveillance data and meteorological observations. Materials and MethodsArboMAP was implemented using an R markdown script for data processing, modeling, and report generation. A Google Earth Engine application was developed to summarize and download weather data. Generalized additive models were used to make county-level predictions of WNV cases. ResultsArboMAP minimized the number of manual steps required to make weekly forecasts, generated information that was useful for decision-makers, and has been tested and implemented in multiple public health institutions. Discussion and ConclusionRoutine prediction of mosquito-borne disease risk is feasible and can be implemented by public health departments using ArboMAP.
more »
« less
Multi-faceted analysis and prediction for the outbreak of pediatric respiratory syncytial virus
Abstract ObjectivesRespiratory syncytial virus (RSV) is a significant cause of pediatric hospitalizations. This article aims to utilize multisource data and leverage the tensor methods to uncover distinct RSV geographic clusters and develop an accurate RSV prediction model for future seasons. Materials and MethodsThis study utilizes 5-year RSV data from sources, including medical claims, CDC surveillance data, and Google search trends. We conduct spatiotemporal tensor analysis and prediction for pediatric RSV in the United States by designing (i) a nonnegative tensor factorization model for pediatric RSV diseases and location clustering; (ii) and a recurrent neural network tensor regression model for county-level trend prediction using the disease and location features. ResultsWe identify a clustering hierarchy of pediatric diseases: Three common geographic clusters of RSV outbreaks were identified from independent sources, showing an annual RSV trend shifting across different US regions, from the South and Southeast regions to the Central and Northeast regions and then to the West and Northwest regions, while precipitation and temperature were found as correlative factors with the coefficient of determination R2≈0.5, respectively. Our regression model accurately predicted the 2022-2023 RSV season at the county level, achieving R2≈0.3 mean absolute error MAE < 0.4 and a Pearson correlation greater than 0.75, which significantly outperforms the baselines with P-values <.05. ConclusionOur proposed framework provides a thorough analysis of RSV disease in the United States, which enables healthcare providers to better prepare for potential outbreaks, anticipate increased demand for services and supplies, and save more lives with timely interventions.
more »
« less
- Award ID(s):
- 2034479
- PAR ID:
- 10473065
- Publisher / Repository:
- Oxford University Press
- Date Published:
- Journal Name:
- Journal of the American Medical Informatics Association
- Volume:
- 31
- Issue:
- 1
- ISSN:
- 1067-5027
- Format(s):
- Medium: X Size: p. 198-208
- Size(s):
- p. 198-208
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Accurate prediction of the transmission of epidemic diseases such as COVID-19 is crucial for implementing effective mitigation measures. In this work, we develop a tensor method to predict the evolution of epidemic trends for many regions simultaneously. We construct a 3-way spatio-temporal tensor (location, attribute, time) of case counts and propose a nonnegative tensor factorization with latent epidemiological model regularization named STELAR. Unlike standard tensor factorization methods which cannot predict slabs ahead, STELAR enables long-term prediction by incorporating latent temporal regularization through a system of discrete time difference equations of a widely adopted epidemiological model. We use latent instead of location/attribute-level epidemiological dynamics to capture common epidemic profile sub-types and improve collaborative learning and prediction. We conduct experiments using both county- and state level COVID-19 data and show that our model can identify interesting latent patterns of the epidemic. Finally, we evaluate the predictive ability of our method and show superior performance compared to the baselines, achieving up to 21% lower root mean square error and 25% lower mean absolute error for county-level prediction.more » « less
-
Abstract BackgroundSeasonal patterns of mycobacterial infections affecting humans and animals remain a complex and understudied aspect of infectious disease dynamics. These intra-annual patterns are increasingly relevant in the context of global climate change, which may influence the timing and geographic spread of these diseases. A better understanding of such patterns could improve surveillance, prevention, and control strategies. MethodsWe conducted a mixed-methods bibliometric review combining bibliographic searches and scoping analysis to synthesize decades of research on the seasonality of mycobacterial infections in humans and animals. We systematically searched three major scientific databases—Scopus, PubMed-MEDLINE, and Web of Science—for articles published between 1971 and April 2023. From an initial dataset of 1830 unique articles, we identified and analysed 122 studies that met predefined inclusion criteria. We extracted information on pathogen type, statistical methods, geographic location, and host species. In addition, we conducted a co-citation network analysis to identify key methodological influences and research clusters. ResultsThe retained studies encompassed tuberculosis, Buruli ulcer, bovine tuberculosis, and other mycobacterial diseases such as leprosy and Johne’s disease. Most articles focused on tuberculosis in humans, followed by Buruli ulcer caused byMycobacterium ulcerans. There was a marked increase in studies on seasonal trends in tuberculosis and Buruli ulcer over time, with notable variation in geographic and methodological coverage. Research was heavily concentrated in the northern hemisphere, especially in China, while southern regions remained underrepresented. Advanced statistical tools, including generalized linear models and time-series analyses, were instrumental in detecting seasonality, particularly for tuberculosis and Buruli ulcer. ConclusionSeasonality appears to be a common yet understudied feature of many mycobacterial infections. Greater interdisciplinary collaboration and the use of appropriate analytical tools are essential to better understand these patterns, especially in underrepresented regions. Addressing methodological and geographic gaps will be crucial to improve responses to these diseases in a changing global environment.more » « less
-
Abstract MotivationPolygenic risk score (PRS) has been widely exploited for genetic risk prediction due to its accuracy and conceptual simplicity. We introduce a unified Bayesian regression framework, NeuPred, for PRS construction, which accommodates varying genetic architectures and improves overall prediction accuracy for complex diseases by allowing for a wide class of prior choices. To take full advantage of the framework, we propose a summary-statistics-based cross-validation strategy to automatically select suitable chromosome-level priors, which demonstrates a striking variability of the prior preference of each chromosome, for the same complex disease, and further significantly improves the prediction accuracy. ResultsSimulation studies and real data applications with seven disease datasets from the Wellcome Trust Case Control Consortium cohort and eight groups of large-scale genome-wide association studies demonstrate that NeuPred achieves substantial and consistent improvements in terms of predictive r2 over existing methods. In addition, NeuPred has similar or advantageous computational efficiency compared with the state-of-the-art Bayesian methods. Availability and implementationThe R package implementing NeuPred is available at https://github.com/shuangsong0110/NeuPred. Supplementary informationSupplementary data are available at Bioinformatics online.more » « less
-
Revolutionising disease detection: The emergence of non-invasive VOC breathomicsBreathomics marks a revolutionary approach to disease detection by analyzing the chemical composition of exhaled breath. As the world recovers from the recent global health crises, the detection and management of pandemic diseases like COVID-19, RSV, and flu have come to the forefront. The COVID-19 pandemic alone has affected over 96 million people in the US, with a devastating count of more than a million fatalities. Similarly, respiratory syncytial virus (RSV) and influenza (flu) collectively burden the healthcare system with millions of cases annually, leading to hundreds of thousands of hospitalizations and tens of thousands of deaths. These staggering statistics underscore an urgent need for diagnostic methods that are not only swift and accurate but also non- invasive to facilitate rapid, widespread testing. Enter Breathomics—a revolutionary approach that analyzes the chemical composition of exhaled breath to detect diseases.more » « less
