Trigonometric Regression for Analysis of Public Health Surveillance Data

Steven E Rigdon,Ehsan Jahanpour,George Turabelidze

doi:10.1155/2014/673293

Abstract

Statistical challenges in monitoring modern biosurveillance data are well described in the literature. Even though assumptions of normality, independence, and stationarity are typically violated in the biosurveillance data, statistical process control (SPC) charts adopted from industry have been widely used in public health for communicable disease monitoring. But, blind usage of SPC charts in public health that ignores the characteristics of disease surveillance data may result in poor detection of disease outbreaks and/or excessive false-positive alarms. Thus, improved biosurveillance systems are clearly needed, and participation of statisticians knowledgeable in SPC alongside epidemiologists in the design and evaluation of such systems can be more productive. We describe and study a method for monitoring reportable disease counts using a Poisson distribution whose mean is allowed to vary depending on the week of the year. The seasonality is modeled by a trigonometric function whose parameters can be estimated by some baseline set of data. We study the ability of such a model to detect an outbreak. Specifically, we estimate the probability of detection (POD), the average number of weeks to signal given that a signal has occurred (conditional expected delay, or CED), and the false-positive rate (FPR, the average number of false-alarms per year).

Highlights

Homeland Security Presidential Directive 21 of October 18, 2007, defined biosurveillance as “. . . the process of active datagathering with appropriate analysis and interpretation of biosphere data that might relate to disease activity and threats to human or animal health—whether infectious, toxic, metabolic, or otherwise, and regardless of intentional or natural origin—in order to achieve early warning of health threats, early detection of health events, and overall situational awareness of disease activity. . ..” This suggests two distinct goals: situational awareness and early event detection
While situational awareness is certainly an important characteristic of a disease surveillance system, we focus on the problem of early event detection (EED)
We describe a simple method for early outbreak detection, DESTEM (Disease Electronic Surveillance with Trigonometric Models), and we apply it to the reportable communicable diseases data in Missouri, USA

Summary

Introduction

Homeland Security Presidential Directive 21 of October 18, 2007, defined biosurveillance as “. . . the process of active datagathering with appropriate analysis and interpretation of biosphere data that might relate to disease activity and threats to human or animal health—whether infectious, toxic, metabolic, or otherwise, and regardless of intentional or natural origin—in order to achieve early warning of health threats, early detection of health events, and overall situational awareness of disease activity. . ..” This suggests two distinct goals: situational awareness and early event detection. While situational awareness is certainly an important characteristic of a disease surveillance system, we focus on the problem of early event detection (EED). A surveillance system for diseases whose occurrence rate is seasonal cannot have a constant control limit since there would be frequent signal limits in the peak season and practically no signals in the off-season. A control chart is used in industry to identify when the output differs from what would be expected by chance. The primary tool for disease surveillance could be a control chart, similar to what is used in industry. This technique is called statistical process control (SPC).

The Trigonometric Model

A Simulation Study of DESTEM Performance

Discussion and Conclusion