Displaying results 1 - 7 of 7
-
T-Cube as an Enabling Technology in Surveillance Applications
Content Type: Abstract
T-Cube is especially useful for rapidly retrieving responses to ad-hoc queries against large datasets of additive time series labeled using a set of categorical attributes. It can be used as a general tool to support any task… read more… of over-the-counter medications and emergency department visits. In this paper we present efficiencies which can be … pairs of size = 1 and 2, the total number of such com- binations exceeding 4.3 million. The involved ana- … -
Using AFDL Algorithm to Estimate Risk of Positive Outcomes of Microbial Tests at Food Establishments
Content Type: Abstract
One of the common tasks faced by the U.S. Department of Agriculture (USDA) food safety analysts is to estimate the risk of observing positive outcomes of microbial tests of food samples collected at the slaughter and food… read more… of specific test results at different establishments may be purely coincidental and our analysis does not attempt … of specific test results at different establishments may be purely co- incidental and our analysis does not … of specific test results at different establishments may be purely coincidental and our analysis does not attempt … -
Patterns of Emergency Care Utilization by Chronically Ill
Content Type: Abstract
The nature of Emergency Room services makes the patients' visits hard to predict and control and the services incur high costs. Chronic patients should not require urgent care to treat their chronic illness, if they were properly managed in… read more… The nature of Emergency Room services makes the patients' visits hard to predict and control and the services incur … in primary care. We track frequency of emergency room visits by chronically ill when the primary complaint of … The nature of Emergency Room services makes the patients' visits hard to predict and control and the services incur … -
Utility of Potential Misdiagnoses in Predicting Foodborne Outbreaks
Content Type: Abstract
Reliable detection and accurate scoping of outbreaks of foodborne illness are the keys to effective mitigation of their impacts. However, relatively small number of persons affected and underreporting, challenge the reliability of surveillance… read more… improved by including cases in which Salmonella infection may be confused2. Objective To investigate utility of using … in the analysis cases diagnosed with conditions that may have physiological appearance similar to Salmonellosis. … improved by including cases in which Salmonella infection may be confused2. Objective To investigate utility of using … -
Mining Intensive Care Vitals for Leading Indicators of Adverse Health Events
Content Type: Abstract
The status of each Intensive Care Unit (ICU) patient is routinely monitored and a number of vital signs are recorded at sub-second frequencies which results in large amounts of data. We propose an approach to transform this stream of raw vital… read more… learned from reference data. Any substantial departure may be indicative of an upcoming adverse health episode. Our … to: 1. Identify change points in vital signs which may be indicative of impending critical health events in … ehtj11115 ehtj11120 ehtj11024 ehtj11060 ehtj11110 26-50 ehtj11034 ehtj11198 ehtj11174 ehtj11048 ehtj11154 … -
Rapid Processing of Ad-Hoc Queries against Large Sets of Time Series
Content Type: Abstract
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… read more… monitoring of nationwide over-thecounter (OTC) sales data may require separate time series analyses on tens of … scans performed over all potential disease clusters) may require millions of distinct queries. Commercial OLAP … of nationwide over-the- counter (OTC) sales data may require separate time series analyses on tens of … -
Learning Stable Multivariate Baseline Models for Outbreak Detection
Content Type: Abstract
We propose a novel technique for building generative models of real-valued multivariate time series data streams. Such models are of considerable utility as baseline simulators in anomaly detection systems. The proposed algorithm, based on Linear… read more… it is important that any baseline model scales to mul- tidimensional observations. In many cases, different … A. At every time step, a higher-dimensional observation y is emit- ted according to another linear transformation. …