The broad project objective is to establish a robust technical link in the process of automated outbreak? detection to complement and backup the traditional sentinel surveillance system. Means to this objective? include development and efficient combination of data-driven statistical alerting algorithms and? implementation of higher level decision-support tools for fusing algorithmic results with external information? and epidemiologist judgment.
Specific aims are to establish and exercise a context-sensitive testbed for? standardized algorithm development and evaluation, to develop an information-sharing methodology for? jurisdictional situations that preclude data-sharing, and to create decision-support tools by combining? heuristic methods used by experience health monitors with Bayesian Belief Net representation. Research? within the testbed will advance the state of the art in detection algorithms, stressing the adaptations required? to make them relevant and effective for monitoring on a daily or, depending on input data rates, a near-realtime? basis. Algorithms will broadly include univariate, multivariate hypothesis tests and data mining? techniques more general automated learning and we will seek to determine the appropriate niche for each? approach found useful. For univariate data, hypothesis test research will investigate means of combining? data modeling and process control for optimal detection performance depending on the data background.? Multivariate algorithm research will include both fully multivariate methods and multiple univariate methods? and will blend the two for optimal monitoring capability. Structured testbed design and development will? establish standards for algorithm evaluation and comparison based on health monitoring effectiveness,? measured by sensitivity, specificity, and timeliness of event detection. These standards will make this public? health research area more accessible and relevant to local heath department users. Potentially, the? decision-support tools may make complex data scenarios understandable to users of these systems.? Acceptance of potential of automated surveillance systems will stimulate increased cooperation of health? departments, data providers, and policymakers, further improving public health monitoring capability.
| Peter, William; Najmi, Amir H; Burkom, Howard S (2011) Reducing false alarms in syndromic surveillance. Stat Med 30:1665-77 |
| Elbert, Yevgeniy; Burkom, Howard S (2009) Development and evaluation of a data-adaptive alerting algorithm for univariate temporal biosurveillance data. Stat Med 28:3226-48 |
| Najmi, Amir-Homayoon; Burkom, Howard (2009) Recursive least squares background prediction of univariate syndromic surveillance data. BMC Med Inform Decis Mak 9:4 |
