Time Series

Viral hepatitis is a global public health problem affecting millions of people every year, causing disability and death [1].The hepatitis B virus (HBV) is transmitted through the contact with the blood or other body fluids of an infected person. For formulating evidence-based policy of Public Health and data for action we should know about main ways of transmission HBV and population group with high risk of infection.

Objective

To develop model to study risk factors for hepatitis B (HB) and to identify the main causes affecting the incidence of HB.

Surveillance of individual data streams is a well-accepted approach to monitor community incidence of infectious diseases such as influenza, and to enable timely detection of outbreaks so that control measures can be applied. However the performance of alerts may be improved by simultaneously monitor a variety of data sources, or multiple streams (eg from different geographic locations) of the same type, rather than monitoring only aggregate data. Rates of influenza-like illness in subtropical settings typically show greater variability than in temperate regions.

Objective

This paper describes the use of time series models for simultaneous monitoring of multiple streams of influenza surveillance data.

Analysis of time series data requires accurate calculation of a predicted value. Non-regression methods such as the Early Aberration Reporting System CuSum are computationally simple, but most do not adjust for day of week or holiday. Alternately, regression methods require larger counts, more computer resources, and possibly longer baseline periods of data. As increasing volumes of data are reported and analyzed, the predictive accuracy of simpler methods should be assessed and optimized.

Objective

To compare the predictive accuracy of three non-regression methods in analysis of time series count data.

In 2004, the NSW Public Health Real-time Emergency Department Surveillance System operating in and around Sydney, Australia signalled a large-scale increase in Emergency Department (ED) visits for gastrointestinal illness (GI). A subsequent alarming state-wide rise in institutional gastroenteritis outbreaks was also seen through conventional outbreak surveillance.

Objectives

To examine the association between short-term variation in ED visits for GI with short-term variation in institutional gastroenteritis outbreaks and thus to evaluate whether syndromic surveillance of GI through EDs provides early warning for institutional gastroenteritis outbreaks.

Crude mortality could be valuable for infectious disease surveillance if available in a complete and timely fashion. Such data can be of used for detecting, and tracking the impact of unusual health events (e.g. pandemic influenza) or other unexpected or unknown events of infectious nature.

To evaluate whether these goals can be achieved with crude mortality monitoring in the Netherlands, a pilot study was set up in 2008 in which death counts were received from Statistics Netherlands. 

The aims of this pilot are: 1) Setting up communication and data transmission. 2) Calculating expected mortality counts (depending on the season) and a prediction interval. 3) Detecting deviations in mortality counts above the threshold. 4) Comparing such deviations (and lags hereof) with other public health information (such as sentinel influenza-like-illness surveillance, and web-based selfreported ILI). 4) Evaluating the additional value of such a system for infectious disease public health.

Objective

To evaluate the potential use of mortality data in the Netherlands for real-time surveillance of infectious disease events through a pilot study.

Numerous methods have been applied to the problem of modeling temporal properties of disease surveillance data; the ESSENCE system contains a widely used approach (1). STL (2) is a flexible, wellproven method for temporal modeling that decomposes the series into frequency components. A periodic component like DW can be exactly periodic or evolve through time. STL is based on loess (3), which can model a numeric response as a function of any explanatory variables. After the STL modeling of the counts, we will add patient address and produce a timespace modeling using both STL and more general loess methods.

Objective

Use the STL local-regression (loess) decomposition procedure and transformation to model the univariate time-series characteristics of chief-complaint daily counts as a first step in a time and spatial modeling. Develop visualization tools for model display and checking.

It has been noted since the era of Hippocrates that weather conditions at a specific location can influence the incidence of various infectious and noninfectious diseases. It has also been implied that variations in weather conditions influence the number of cases of infectious respiratory conditions. Syndromic surveillance was introduced in Athens, Greece, for the first time in July 2002 in the framework of increased preparedness for the Olympic Games of 2004. Our experience showed that the incidence of some syndromes parallels that of diseases surveyed by the mandatory notification system of the Hellenic Center for Diseases Control and Prevention that are known to have a strong seasonal pattern in their incidence e.g. influenza. Influenza incidence peaks at the same time with the “respiratory infection with fever” syndrome during spring. This study aimed at investigating possible relationships between the incidence of the “respiratory infection with fever” syndrome and meteorological parameters.

Objective

This study explores the possible impact of meteorological conditions on the incidence of clinical syndromes with an interest for public health in the basin of Athens, Greece.

Objective: To investigate seasonal patterns of gastrointestinal (GI) illness among children and adults.

Time series analysis is very common in syndromic surveillance. Large scale biosurveillance systems typically perform thousands of time series queries per day: for example, monitoring of nationwide over-thecounter (OTC) sales data may require separate time series analyses on tens of thousands of zip codes. More complex query types (e.g. queries over various combinations of patient age, gender, and other characteristics, or spatial scans performed over all potential disease clusters) may require millions of distinct queries. Commercial OLAP databases provide data cubes to handle such ad hoc queries, but these methods typically suffer from long build times (typically hours), huge memory requirements (requiring the purchase of high-end database servers), and high maintenance costs. Additionally, data cubes typically require 1 second or more to respond to each complex query. This delay is an inconvenience to users who want to perform multiple queries in an online fashion; additionally, data cubes are far too slow for statistical analyses requiring millions of complex queries, which would require days of processing time.

Objective

We present T-Cube, a new tool for very fast retrieval and analysis of time series data. Using a novel method of data caching, T-Cube performs time series queries approximately 1,000 times faster than standard state-of-the-art data cube technologies. This speedup has two main benefits: it enables fast anomaly detection by simultaneous statistical analysis of many thousands of time series, and it allows public health users to perform many complex, ad hoc time series queries on the fly without inconvenient delays.

Yearly epidemics of respiratory diseases occur in children. Early recognition of these and of unexpected epidemics due to new agents or as acts of biological/chemical terrorism is desirable. In this study, we evaluate the ordering of chest radiographs as a proxy for early identification of epidemics of lower respiratory tract disease. This has the potential to act as a sensitive real-time surveillance tool during such outbreaks.

Objective:

Create a tool for monitoring respiratory epidemics based on chest radiograph ordering patterns.