A dynamic neural network model for predicting risk of Zika in real time

被引:61
作者
Akhtar, Mahmood [1 ,2 ]
Kraemer, Moritz U. G. [3 ,4 ,5 ]
Gardner, Lauren M. [1 ,6 ]
机构
[1] UNSW Sydney, Sch Civil & Environm Engn, Sydney, NSW, Australia
[2] UNSW Sydney, Sch Womens & Childrens Hlth, Sydney, NSW, Australia
[3] Univ Oxford, Dept Zool, Oxford, England
[4] Boston Childrens Hosp, Computat Epidemiol Grp, Boston, MA USA
[5] Harvard Med Sch, Boston, MA 02115 USA
[6] Johns Hopkins Univ, Dept Civil Engn, Baltimore, MD 21218 USA
关键词
Zika; Epidemic risk prediction; Dynamic neural network; VIRUS OUTBREAK; DENGUE SURVEILLANCE; SOUTH-PACIFIC; TRANSMISSION; FORECAST; SYSTEM; IMPACT; SPREAD; ISLAND;
D O I
10.1186/s12916-019-1389-3
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background In 2015, the Zika virus spread from Brazil throughout the Americas, posing an unprecedented challenge to the public health community. During the epidemic, international public health officials lacked reliable predictions of the outbreak's expected geographic scale and prevalence of cases, and were therefore unable to plan and allocate surveillance resources in a timely and effective manner. Methods In this work, we present a dynamic neural network model to predict the geographic spread of outbreaks in real time. The modeling framework is flexible in three main dimensions (i) selection of the chosen risk indicator, i.e., case counts or incidence rate; (ii) risk classification scheme, which defines the high-risk group based on a relative or absolute threshold; and (iii) prediction forecast window (1 up to 12 weeks). The proposed model can be applied dynamically throughout the course of an outbreak to identify the regions expected to be at greatest risk in the future. Results The model is applied to the recent Zika epidemic in the Americas at a weekly temporal resolution and country spatial resolution, using epidemiological data, passenger air travel volumes, and vector habitat suitability, socioeconomic, and population data for all affected countries and territories in the Americas. The model performance is quantitatively evaluated based on the predictive accuracy of the model. We show that the model can accurately predict the geographic expansion of Zika in the Americas with the overall average accuracy remaining above 85% even for prediction windows of up to 12 weeks. Conclusions Sensitivity analysis illustrated the model performance to be robust across a range of features. Critically, the model performed consistently well at various stages throughout the course of the outbreak, indicating its potential value at any time during an epidemic. The predictive capability was superior for shorter forecast windows and geographically isolated locations that are predominantly connected via air travel. The highly flexible nature of the proposed modeling framework enables policy makers to develop and plan vector control programs and case surveillance strategies which can be tailored to a range of objectives and resource constraints.
引用
收藏
页数:16
相关论文
共 83 条
[1]   Dengue confirmed-cases prediction: A neural network model [J].
Aburas, Hani M. ;
Cetiner, B. Gultekin ;
Sari, Murat .
EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (06) :4256-4260
[2]   A Critical Assessment of Vector Control for Dengue Prevention [J].
Achee, Nicole L. ;
Gould, Fred ;
Perkins, T. Alex ;
Reiner, Robert C., Jr. ;
Morrison, Amy C. ;
Ritchie, Scott A. ;
Gubler, Duane J. ;
Teyssou, Remy ;
Scott, Thomas W. .
PLOS NEGLECTED TROPICAL DISEASES, 2015, 9 (05)
[3]   Bayesian dynamic modeling of time series of dengue disease case counts [J].
Adyro Martinez-Bello, Daniel ;
Lopez-Quilez, Antonio ;
Torres-Prieto, Alexander .
PLOS NEGLECTED TROPICAL DISEASES, 2017, 11 (07)
[4]  
Ahmadi S., 2018, J PUBLIC HLTH EMERG, V2, P20, DOI [10.21037/jphe.2018.05.02, DOI 10.21037/JPHE.2018.05.02]
[5]   Prediction of Dengue Incidence Using Search Query Surveillance [J].
Althouse, Benjamin M. ;
Ng, Yih Yng ;
Cummings, Derek A. T. .
PLOS NEGLECTED TROPICAL DISEASES, 2011, 5 (08)
[6]  
Anggraeni W, 2016, 2016 INT C INF COMM
[7]  
[Anonymous], 2016, Population density by Population Census
[8]   Dengue forecasting in Sao Paulo city with generalized additive models, artificial neural networks and seasonal autoregressive integrated moving average models [J].
Baquero, Oswaldo Santos ;
Reis Santana, Lidia Maria ;
Chiaravalloti-Neto, Francisco .
PLOS ONE, 2018, 13 (04)
[9]   ZIKA: A New System to Empower Health Workers and Local Communities to Improve Surveillance Protocols by E-learning and to Forecast Zika Virus in Real Time in Brazil [J].
Beltran, Juan D. ;
Boscor, Andrei ;
dos Santos, Wellington P. ;
Massoni, Tiago ;
Kostkova, Patty .
DH '18: PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE ON DIGITAL HEALTH, 2018, :90-94
[10]   Anticipating the international spread of Zika virus from Brazil [J].
Bogoch, Isaac I. ;
Brady, Oliver J. ;
Kraemer, Moritz U. G. ;
German, Matthew ;
Creatore, Marisa I. ;
Kulkarni, Manisha A. ;
Brownstein, John S. ;
Mekaru, Sumiko R. ;
Hay, Simon I. ;
Groot, Emily ;
Watts, Alexander ;
Khan, Kamran .
LANCET, 2016, 387 (10016) :335-336