Fast Bayesian scan statistics for multivariate event detection and visualization

Research output: Contribution to journalArticle

Abstract

The multivariate Bayesian scan statistic (MBSS) is a recently proposed, general framework for event detection and characterization in multivariate space-time data. MBSS integrates prior information and observations from multiple data streams in a Bayesian framework, computing the posterior probability of each type of event in each space-time region. MBSS has been shown to have many advantages over previous event detection approaches, including improved timeliness and accuracy of detection, easy interpretation and visualization of results, and the ability to model and accurately differentiate between multiple event types. This work extends the MBSS framework to enable detection and visualization of irregularly shaped clusters in multivariate data, by defining a hierarchical prior over all subsets of locations. While a naive search over the exponentially many subsets would be computationally infeasible, we demonstrate that the total posterior probability that each location has been affected can be efficiently computed, enabling rapid detection and visualization of irregular clusters. We compare the run time and detection power of this 'Fast Subset Sums' method to our original MBSS approach (assuming a uniform prior over circular regions) on semi-synthetic outbreaks injected into real-world Emergency Department data from Allegheny County, Pennsylvania. We demonstrate substantial improvements in spatial accuracy and timeliness of detection, while maintaining the scalability and fast run time of the original MBSS method.

Original languageEnglish (US)
Pages (from-to)455-469
Number of pages15
JournalStatistics in Medicine
Volume30
Issue number5
DOIs
StatePublished - Feb 28 2011

Fingerprint

Scan Statistic
Event Detection
Visualization
Posterior Probability
Space-time
Hierarchical Prior
Subset Sum
Subset
Multivariate Data
Prior Information
Disease Outbreaks
Hospital Emergency Service
Differentiate
Data Streams
Emergency
Demonstrate
Irregular
Scalability
Integrate
Computing

Keywords

  • Disease surveillance
  • Event detection
  • Scan statistics

ASJC Scopus subject areas

  • Epidemiology
  • Statistics and Probability

Cite this

Fast Bayesian scan statistics for multivariate event detection and visualization. / Neill, Daniel.

In: Statistics in Medicine, Vol. 30, No. 5, 28.02.2011, p. 455-469.

Research output: Contribution to journalArticle

@article{5577f092d0254e77bde5d3acace97a87,
title = "Fast Bayesian scan statistics for multivariate event detection and visualization",
abstract = "The multivariate Bayesian scan statistic (MBSS) is a recently proposed, general framework for event detection and characterization in multivariate space-time data. MBSS integrates prior information and observations from multiple data streams in a Bayesian framework, computing the posterior probability of each type of event in each space-time region. MBSS has been shown to have many advantages over previous event detection approaches, including improved timeliness and accuracy of detection, easy interpretation and visualization of results, and the ability to model and accurately differentiate between multiple event types. This work extends the MBSS framework to enable detection and visualization of irregularly shaped clusters in multivariate data, by defining a hierarchical prior over all subsets of locations. While a naive search over the exponentially many subsets would be computationally infeasible, we demonstrate that the total posterior probability that each location has been affected can be efficiently computed, enabling rapid detection and visualization of irregular clusters. We compare the run time and detection power of this 'Fast Subset Sums' method to our original MBSS approach (assuming a uniform prior over circular regions) on semi-synthetic outbreaks injected into real-world Emergency Department data from Allegheny County, Pennsylvania. We demonstrate substantial improvements in spatial accuracy and timeliness of detection, while maintaining the scalability and fast run time of the original MBSS method.",
keywords = "Disease surveillance, Event detection, Scan statistics",
author = "Daniel Neill",
year = "2011",
month = "2",
day = "28",
doi = "10.1002/sim.3881",
language = "English (US)",
volume = "30",
pages = "455--469",
journal = "Statistics in Medicine",
issn = "0277-6715",
publisher = "John Wiley and Sons Ltd",
number = "5",

}

TY - JOUR

T1 - Fast Bayesian scan statistics for multivariate event detection and visualization

AU - Neill, Daniel

PY - 2011/2/28

Y1 - 2011/2/28

N2 - The multivariate Bayesian scan statistic (MBSS) is a recently proposed, general framework for event detection and characterization in multivariate space-time data. MBSS integrates prior information and observations from multiple data streams in a Bayesian framework, computing the posterior probability of each type of event in each space-time region. MBSS has been shown to have many advantages over previous event detection approaches, including improved timeliness and accuracy of detection, easy interpretation and visualization of results, and the ability to model and accurately differentiate between multiple event types. This work extends the MBSS framework to enable detection and visualization of irregularly shaped clusters in multivariate data, by defining a hierarchical prior over all subsets of locations. While a naive search over the exponentially many subsets would be computationally infeasible, we demonstrate that the total posterior probability that each location has been affected can be efficiently computed, enabling rapid detection and visualization of irregular clusters. We compare the run time and detection power of this 'Fast Subset Sums' method to our original MBSS approach (assuming a uniform prior over circular regions) on semi-synthetic outbreaks injected into real-world Emergency Department data from Allegheny County, Pennsylvania. We demonstrate substantial improvements in spatial accuracy and timeliness of detection, while maintaining the scalability and fast run time of the original MBSS method.

AB - The multivariate Bayesian scan statistic (MBSS) is a recently proposed, general framework for event detection and characterization in multivariate space-time data. MBSS integrates prior information and observations from multiple data streams in a Bayesian framework, computing the posterior probability of each type of event in each space-time region. MBSS has been shown to have many advantages over previous event detection approaches, including improved timeliness and accuracy of detection, easy interpretation and visualization of results, and the ability to model and accurately differentiate between multiple event types. This work extends the MBSS framework to enable detection and visualization of irregularly shaped clusters in multivariate data, by defining a hierarchical prior over all subsets of locations. While a naive search over the exponentially many subsets would be computationally infeasible, we demonstrate that the total posterior probability that each location has been affected can be efficiently computed, enabling rapid detection and visualization of irregular clusters. We compare the run time and detection power of this 'Fast Subset Sums' method to our original MBSS approach (assuming a uniform prior over circular regions) on semi-synthetic outbreaks injected into real-world Emergency Department data from Allegheny County, Pennsylvania. We demonstrate substantial improvements in spatial accuracy and timeliness of detection, while maintaining the scalability and fast run time of the original MBSS method.

KW - Disease surveillance

KW - Event detection

KW - Scan statistics

UR - http://www.scopus.com/inward/record.url?scp=79851488592&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79851488592&partnerID=8YFLogxK

U2 - 10.1002/sim.3881

DO - 10.1002/sim.3881

M3 - Article

C2 - 21312215

AN - SCOPUS:79851488592

VL - 30

SP - 455

EP - 469

JO - Statistics in Medicine

JF - Statistics in Medicine

SN - 0277-6715

IS - 5

ER -