Displaying results 1 - 8 of 13
-
Fast and Flexible Outbreak Detection by Linear-Time Subset Scanning
Content Type: Abstract
The spatial scan statistic [1] detects significant spatial clusters of disease by maximizing a likelihood ratio statistic over a large set of spatial regions. Typical spatial scan approaches either constrain the search regions to… read more… to constrain our search by penalizing or excluding un- likely subsets (e.g. disconnected or highly irregular … spatial scans, with and without LTSS, on 281 days of ED visit data from 88 Allegheny County zip codes. Various scan … -
Scalable Detection of Irregular Disease Clusters Using Soft Compactness Constraints
Content Type: Abstract
The spatial scan statistic [1] detects significant spatial clusters of disease by maximizing a likelihood ratio statistic F(S) over a large set of spatial regions, typically constrained by shape. The fast localized scan [2] enables scalable… read more… J R Stat Soc (Ser B). 2011;to appear. *Skyler Speakman E-mail: skylerspeakman@gmail.com (page number not for citation purpose) Fig. 1. … -
A Robust Expectation-Based Spatial Scan Statistic
Content Type: Abstract
This paper describes a new expectation-based scan statistic that is robust to outliers (individual anomalies at the store level that are not indicative of outbreaks). We apply this method to prospective monitoring of over-the-counter (OTC) drug… read more… to the product of the (known) expectation bi and an (un- known) relative risk qi. The robust statistic compares … -
Fast Graph Structure Learning from Unlabeled Data for Outbreak Detection
Content Type: Abstract
Disease surveillance data often has an underlying network structure (e.g. for outbreaks which spread by person-to-person contact). If the underlying graph structure is known, detection methods such as GraphScan (1) can be used to identify an… read more… the time series of observed counts (e.g. daily hospital visits for each zip code). Objective Our goal is to learn … the time series of observed counts (e.g., daily hospital visits for each zip code). Methods Our solution builds on … J R Stat Soc (Ser B). 2011, to appear. *Sriram Somanchi E-mail: somanchi@cmu.edu page number not for citation purpose … -
Monitoring Pharmacy Retail Data for Anomalous Space-Time Clusters
Content Type: Abstract
Bio-surveillance systems monitor multiple data streams (over-the-counter (OTC) sales, Emergency Department visits, etc.) to detect both natural disease outbreaks (e.g. influenza) and bio-terrorist attacks (e.g. anthrax re-lease). Many detection… read more… (over-the-counter (OTC) sales, Emergency Department visits, etc.) to detect both natural disease outbreaks (e.g. … multiple data streams (OTC sales, Emergency Department visits, etc.) to detect both natural disease outbreaks (e.g. … the system involved sending alert reports to users via e-mail. To improve users’ ability to evaluate outbreaks, alert … -
Identifying Emerging Novel Outbreaks In Textual Emergency Department Data
Content Type: Abstract
Typical approaches to monitoring ED data classify cases into pre-defined syndromes and then monitor syndrome counts for anomalies. However, syndromes cannot be created to identify every possible cluster of cases of relevance to public health. To… read more… The NC DPH dataset describes 198,511 de-identified ED visits over one year at 3 North Carolina hospitals. The data … The NC DPH dataset describes 198,511 de-identified ED visits over one year at 3 North Carolina hospitals. The data … -
Learning Outbreak Regions for Bayesian Spatial Biosurveillance
Content Type: Abstract
This work incorporates model learning into a Bayesian framework for outbreak detection. Our method learns the spatial characteristics of each outbreak type from a small number of labeled training examples, assuming a generative outbreak model with… read more… outbreaks injected into real-world Emergency Department visit data from Allegheny County, PA. In the simulations … -
Virtual Speed Networking with the Analytic Solutions Committee (ASC)
Content Type: Webinar
Presented January 11, 2018. The purpose of the event was to stimulate and facilitate constructive communication and collaboration among analytic method developers and practitioners charged with routine public health surveillance, ranging from… read more… Methods: natural language processing, machine learning Email: al.park@Utah.edu My background is in My research is … Pattern Detection Laboratory Carnegie Mellon University E-mail: neill@cs.cmu.edu Visiting Professor of Urban Analytics New York University E-mail: daniel.neill@nyu.edu Personal Website: …