Displaying results 1 - 3 of 3
-
Syndromic Prediction Power: Comparing Covariates and Baselines
Content Type: Abstract
The eleven syndrome classifications for clinical data records monitored by BioSense include rare events such as death or lymphadenitis and also common occurrences such as respiratory infections. BioSense currently uses two statistical methods for… read more… data for this paper consisted of daily military clinical visit count data from the Department of Defense (DoD) for … of 28, 56, and 112 days were used to make one-day-ahead visit count predictions. For each forecast, the baseline … -
Data-Adapted Temporal Alerting Algorithms for Routine Health Monitoring
Content Type: Abstract
This paper discusses selection of temporal alerting algorithms for syndromic surveillance to achieve reliable detection performance based on statistical properties and the epidemiological context of the input data. We used quantities calculated from… read more… alerting algorithms involve four steps: preconditioning, com- putation of expected values, computation of test sta- … signals. Sensitivity values were recorded for practical back- ground alert rates to compare algorithm detection … -
Synthesizing the American Health Information Community’s Minimum Data Set
Content Type: Abstract
One of the challenges facing developers and users of automated disease surveillance systems is being able to accurately evaluate the performance of their systems for the wide variety of public health threats that are possible. A… read more… represent- ing various types of outbreaks on top of that back- ground [3],[4]. With the introduction of the AHIC …