New directions in artificial intelligence for public health surveillance

Daniel B. Neill

doi:10.1109/MIS.2012.18

New directions in artificial intelligence for public health surveillance

Research output: Contribution to journal › Article › peer-review

Abstract

The next decade of disease surveillance research will require novel methods to effectively use massive quantities of complex, high-dimensional data. We summarize two recent approaches which deal with the increasing complexity and scale of health data, including the use of rich text data to detect emerging outbreaks with novel symptom patterns, and fast subset scan methods to efficiently identify the most relevant patterns in massive datasets.

Original language	English (US)
Article number	6163563
Pages (from-to)	56-59
Number of pages	4
Journal	IEEE Intelligent Systems
Volume	27
Issue number	1
DOIs	https://doi.org/10.1109/MIS.2012.18
State	Published - Jan 2012

Keywords

disease surveillance
event detection
public health surveillance
semantic scan statistic
spatial and subset scanning

ASJC Scopus subject areas

Computer Networks and Communications
Artificial Intelligence

Access to Document

10.1109/MIS.2012.18

Cite this

@article{692c70f0cda24ecab6dfc4e47f736c68,

title = "New directions in artificial intelligence for public health surveillance",

abstract = "The next decade of disease surveillance research will require novel methods to effectively use massive quantities of complex, high-dimensional data. We summarize two recent approaches which deal with the increasing complexity and scale of health data, including the use of rich text data to detect emerging outbreaks with novel symptom patterns, and fast subset scan methods to efficiently identify the most relevant patterns in massive datasets.",

keywords = "disease surveillance, event detection, public health surveillance, semantic scan statistic, spatial and subset scanning",

author = "Neill, {Daniel B.}",

note = "Funding Information: This article is based on the author{\textquoteright}s invited talk, “Research Challenges for Biosurveil-lance,” presented at the 2010 Annual Conference of the International Society for Disease Surveillance (ISDS). The author wishes to thank the ISDS community, as well as the members of his Event and Pattern Detection Laboratory, for their comments and feedback. This work was partially supported by the National Science Foundation under grants IIS-0916345, IIS-0911032, and IIS-0953330. All views are solely those of the author, and have not been endorsed by NSF.",

year = "2012",

month = jan,

doi = "10.1109/MIS.2012.18",

language = "English (US)",

volume = "27",

pages = "56--59",

journal = "IEEE Intelligent Systems",

issn = "1541-1672",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - New directions in artificial intelligence for public health surveillance

AU - Neill, Daniel B.

N1 - Funding Information: This article is based on the author’s invited talk, “Research Challenges for Biosurveil-lance,” presented at the 2010 Annual Conference of the International Society for Disease Surveillance (ISDS). The author wishes to thank the ISDS community, as well as the members of his Event and Pattern Detection Laboratory, for their comments and feedback. This work was partially supported by the National Science Foundation under grants IIS-0916345, IIS-0911032, and IIS-0953330. All views are solely those of the author, and have not been endorsed by NSF.

PY - 2012/1

Y1 - 2012/1

N2 - The next decade of disease surveillance research will require novel methods to effectively use massive quantities of complex, high-dimensional data. We summarize two recent approaches which deal with the increasing complexity and scale of health data, including the use of rich text data to detect emerging outbreaks with novel symptom patterns, and fast subset scan methods to efficiently identify the most relevant patterns in massive datasets.

AB - The next decade of disease surveillance research will require novel methods to effectively use massive quantities of complex, high-dimensional data. We summarize two recent approaches which deal with the increasing complexity and scale of health data, including the use of rich text data to detect emerging outbreaks with novel symptom patterns, and fast subset scan methods to efficiently identify the most relevant patterns in massive datasets.

KW - disease surveillance

KW - event detection

KW - public health surveillance

KW - semantic scan statistic

KW - spatial and subset scanning

UR - http://www.scopus.com/inward/record.url?scp=84858218973&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84858218973&partnerID=8YFLogxK

U2 - 10.1109/MIS.2012.18

DO - 10.1109/MIS.2012.18

M3 - Article

AN - SCOPUS:84858218973

SN - 1541-1672

VL - 27

SP - 56

EP - 59

JO - IEEE Intelligent Systems

JF - IEEE Intelligent Systems

IS - 1

M1 - 6163563

ER -

New directions in artificial intelligence for public health surveillance

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this