Results 1 -
8 of
8
Forecasting a Moving Target: Ensemble Models for ILI Case Count Predictions
"... Modern epidemiological forecasts of common illnesses, such as the flu, rely on both traditional surveillance sources as well as digital surveillance data such as so-cial network activity and search queries. However, most published studies have been retrospective. For a real-time prediction system, w ..."
Abstract
-
Cited by 4 (2 self)
- Add to MetaCart
(Show Context)
Modern epidemiological forecasts of common illnesses, such as the flu, rely on both traditional surveillance sources as well as digital surveillance data such as so-cial network activity and search queries. However, most published studies have been retrospective. For a real-time prediction system, we posit that one of the key challenges is to effectively handle the uncertainty asso-ciated with reports of flu activity. Such reports, are in general, lagged by several weeks and typically revised for several weeks after they are first reported. In this paper, we present a detailed prospective analysis of the generation of robust quantitative predictions of tempo-ral trends of flu activity using several surrogate data sources for 15 Latin American countries. We present our findings about the limitations and advantages of correcting the uncertainty associated with official flu estimates. We also compare the prediction accuracy between model-level fusion of different surrogate data sources against data-level fusion. Finally, we present a novel matrix factorization approach using neighbor-hood embedding to predict flu case counts. Comparing our proposed ensemble method against several baseline methods helps us demarcate the importance of different data sources for the countries under consideration. 1
in viral respiratory tract infections
"... Note added March 2015: I have now written a shorter version of this paper, which I hope is argued better. It is available at ..."
Abstract
- Add to MetaCart
(Show Context)
Note added March 2015: I have now written a shorter version of this paper, which I hope is argued better. It is available at
Dynamic Poisson Autoregression for Influenza-Like-Illness Case Count Prediction
"... Influenza-like-illness (ILI) is among of the most common dis-eases worldwide, and reliable forecasting of the same can have significant public health benefits. Recently, new forms of disease surveillance based upon digital data sources have been proposed and are continuing to attract attention over ..."
Abstract
- Add to MetaCart
(Show Context)
Influenza-like-illness (ILI) is among of the most common dis-eases worldwide, and reliable forecasting of the same can have significant public health benefits. Recently, new forms of disease surveillance based upon digital data sources have been proposed and are continuing to attract attention over traditional surveillance methods. In this paper, we focus on short-term ILI case count prediction and develop a dy-namic Poisson autoregressive model with exogenous inputs variables (DPARX) for flu forecasting. In this model, we al-low the autoregressive model to change over time. In order to control the variation in the model, we construct a model similarity graph to specify the relationship between pairs of models at two time points and embed prior knowledge in terms of the structure of the graph. We formulate ILI case count forecasting as a convex optimization problem, whose objective balances the autoregressive loss and the model sim-ilarity regularization induced by the structure of the similar-ity graph. We then propose an efficient algorithm to solve this problem by block coordinate descent. We apply our model and the corresponding learning method on historical ILI records for 15 countries around the world using a va-riety of syndromic surveillance data sources. Our approach provides consistently better forecasting results than state-of-the-art models available for short-term ILI case count fore-casting.
Communication Use of the NASA Giovanni Data System for Geospatial Public Health Research: Example of Weather-Influenza Connection
, 2014
"... Abstract: The NASA Giovanni data analysis system has been recognized as a useful tool to access and analyze many different types of remote sensing data. The variety of environmental data types has allowed the use of Giovanni for different application areas, such as agriculture, hydrology, and air qu ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract: The NASA Giovanni data analysis system has been recognized as a useful tool to access and analyze many different types of remote sensing data. The variety of environmental data types has allowed the use of Giovanni for different application areas, such as agriculture, hydrology, and air quality research. The use of Giovanni for researching connections between public health issues and Earth’s environment and climate, potentially exacerbated by anthropogenic influence, has been increasingly demonstrated. In this communication, the pertinence of several different data parameters to public health will be described. This communication also provides a case study of the use of remote sensing data from Giovanni in assessing the associations between seasonal influenza and meteorological parameters. In this study, logistic regression was employed with precipitation, temperature and specific humidity as predictors. Specific humidity was found to be associated (p < 0.05)
unknown title
"... exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds and influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature ..."
Abstract
- Add to MetaCart
(Show Context)
exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds and influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature sensitivity (with less activity at higher temperatures) that prevents them from moving down the respiratory tract and infecting the lungs and internal organs of birds and mammals. This reduces the likelihood of death or immobilization of the host, which would reduce transmission of the virus. [Referees, I’m sure this is not a completely new idea; can you help me with references –
unknown title
"... exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds and influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature ..."
Abstract
- Add to MetaCart
(Show Context)
exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds and influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature sensitivity (with less activity at higher temperatures) that prevents them from moving down the respiratory tract and infecting the lungs and internal organs of birds and mammals. This reduces the likelihood of death or immobilization of the host, which would reduce transmission of the virus. [Referees, I’m sure this is not a completely new idea; can you help me with references –
unknown title
"... exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature sens ..."
Abstract
- Add to MetaCart
(Show Context)
exploration of selective trends and seasonality in viral respiratory tract infections Current explanations of the seasonality of colds influenza are incompatible with observations of the incidence of these diseases in the tropics. I suggest that most wild respiratory viruses possess temperature sensitivity (with less activity at higher temperatures) that prevents them from moving down the respiratory tract and infecting the lungs and internal organs of birds and mammals. This reduces the likelihood of death or immobilization of the host, which would reduce transmission of the virus.
unknown title
"... temperature fluctuations on the replication and transmission of respiratory viruses ..."
Abstract
- Add to MetaCart
(Show Context)
temperature fluctuations on the replication and transmission of respiratory viruses
