Predictive Analytics

The burden of asthma is a major public health issue, and of a wider interest particularly to public health practitioners, health care providers and policy makers, as well as researchers. The literature on forecasting of adverse respiratory health events like asthma attacks is limited. It is an unclear field; and there is a need for more research on the forecasting of the demand for hospital respiratory services.

Objective

This paper describes a framework for creating a time series data set with daily asthma admissions, weather and air quality factors; and then generating suitable lags for predictive multivariate quantile regression models (QRMs). It also demonstrates the use of root mean square error (RMSE) and receiver operating characteristic (ROC) error measures in selecting suitable predictive models.

Cryptosporidiosis is a gastrointestinal illness due to a protozoan parasite that is highly contagious, and resistant to multiple disinfectants. Utah experienced a large, community-wide outbreak of cryptosporidiosis between June and December of 2007. During this time period, the Utah Department of Health received reports of 1,902 laboratory confirmed cryptosporidiosis cases across the state.2 Nearly 40% of these cases occurred in Salt Lake County (SL County), Utah. In past years, SL County averaged fewer than five cases annually; however, the incidence rate in the county for this entire outbreak was 125.9 per 100,000 person–years.

Objective

The objective of this study was to investigate if prospectively applied space-time surveillance could have detected significant, emerging clusters as cryptosporidiosis, cases were reported to the Salt Lake Valley Health Department during the 2007 outbreak.

Reporting notifiable conditions to public health authorities by health-care providers and laboratories is fundamental to the prevention, control, and monitoring of population-based disease. To successfully develop community centered health, public health strives to understand and to manage the diseases in its community. Public health surveillance systems provide the mechanisms for public health professionals to ascertain the true disease burden of the population in their community. The information

necessary to determine the disease burden is primarily found in the data generated during clinical care processes.

Objective

This poster will present a predictive model to describe the actual number of confirmed cases for an outbreak (H1N1) based on the current number of confirmed cases reported to public health. The model describes the methods used to calculate the number of cases expected in a community based on the lag time in the diagnosis and reporting of these cases to public health departments.