Displaying results 1 - 5 of 5
-
A System for Simulation: Introducing Outbreaks into Time Series Data
Content Type: Abstract
Objective Several authors have described ways to introduce artificial outbreaks into time series for the purpose of developing, testing, and evaluating the effectiveness and timeliness of anomaly detection algorithms, and more… read more… 1.5 and 2.0 (middle panels) and otherwise 1.75. These are all challenging choices. We added artificial outbreaks at spacing 57 days (top panels), 39 days (middle panels), and 57 and 22 days … -
HWR at the Contest: A Holt-Winters-Based Method Applied to Simulated Outbreaks
Content Type: Abstract
Objective: Ideal anomaly detection algorithms should detect both sudden and gradual changes, while keeping the background false positive alert rate at a tolerable level. Our objective was to develop an anomaly detection algorithm that adapts to the… read more… tolerable level. Our objective was to develop an anomaly de- tection algorithm that adapts to the time series being … and some quantities based on the ξ(t) / σ^(ξ(t) which are de- rived from statistical quality control (SQC)-type … is the sum sumres + c0 + c1 + c2 + c3 + c4 + c5, where all c(i) are zero, except c0 = p_pos5 * 1.862 if pos=5 c1 = … -
Sensitivity and Specificity of an Ngram Method for Classifying Emergency Department Visits into the Respiratory Syndrome in the Turkish Language
Content Type: Abstract
Previously we developed an “Ngram” classifier for syndromic surveillance of emergency department (ED) chief complaints (CC) in Turkish for bioterrorism. The classifier is developed from a set of ED visits for which both the ICD… read more… Setting: University hospital ED in Turkey. Participants: All ED visits for 2002. Protocol: We developed a respiratory … dichotomize the visits in or out of the RESP syndrome. We did the ROC analysis both with the original Turkish … -
Performance of an Adaptive Anomaly Detection Algorithm for a Low Incidence Syndrome Before and After a Major Outbreak
Content Type: Abstract
Ideal anomaly detection algorithms should detect both sudden and gradual changes, while keeping the background false positive alert rate at a tolerable level. Further, the algorithm needs to perform well when the need is to detect… read more… injected at 30 different starting dates in October, with all injected outbreaks ending before the flu season. We … and 41-60 days. In the calculation of specifici- ties all alerts outside of the simulated outbreak and the flu … -
The Performance of a NGram Classifier for Patients' Chief Complaint Based on a Computerized Pick List Entry and Free Text in an Italian Emergency Department
Content Type: Abstract
Syndromic surveillance of emergency department (ED) visit data is often based on computer algorithms which assign patient chief complaints (CC) and ICD code data to syndromes. The triage nurse note (NN) has also been used for… read more… Hospital Residency in Emergency Medicine, 5 Dipartimento di Emergenza e Accettazione e Medicina d'Urgenza. Azienda …