Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer

Taxiarchis Botsis; John Scott; Ravi Goud; Pamela Toman; Andrea Sutherland; Robert Ball

doi:10.3233/978-1-61499-432-9-1178

Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer

Taxiarchis Botsis, John Scott, Ravi Goud, Pamela Toman, Andrea Sutherland, Robert Ball

Bloomberg School of Public Health

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Scopus citations

Abstract

The medical review of adverse event reports for medical products requires the processing of 'big data' stored in spontaneous reporting systems, such as the US Vaccine Adverse Event Reporting System (VAERS). VAERS data are not well suited to traditional statistical analyses so we developed the FDA Adverse Event Network Analyzer (AENA) and three novel network analysis approaches to extract information from these data. Our new approaches include a weighting scheme based on co-occurring triplets in reports, a visualization layout inspired by the islands algorithm, and a network growth methodology for the detection of outliers. We explored and verified these approaches by analysing the historical signal of Intussusception (IS) after the administration of RotaShield vaccine (RV) in 1999. We believe that our study supports the use of AENA for pattern recognition in medical product safety and other clinical data.

Original language	English (US)
Title of host publication	e-Health - For Continuity of Care - Proceedings of MIE 2014
Editors	Louise Pape-Haugaard, Brigitte Seroussi Brigitte, Osman Saka, Christian Lovis, Arie Hasman, Stig Kjaer Andersen
Publisher	IOS Press
Pages	1178-1182
Number of pages	5
ISBN (Electronic)	9781614994312
DOIs	https://doi.org/10.3233/978-1-61499-432-9-1178
State	Published - 2014
Event	25th European Medical Informatics Conference, MIE 2014 - Istanbul, Turkey Duration: Aug 31 2014 → Sep 3 2014

Publication series

Name	Studies in Health Technology and Informatics
Volume	205
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Other

Other	25th European Medical Informatics Conference, MIE 2014
Country/Territory	Turkey
City	Istanbul
Period	8/31/14 → 9/3/14

Keywords

Big Data
Network Analysis
Pattern Recognition
Safety Surveillance

ASJC Scopus subject areas

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/978-1-61499-432-9-1178

Cite this

Botsis, T., Scott, J., Goud, R., Toman, P., Sutherland, A., & Ball, R. (2014). Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer. In L. Pape-Haugaard, B. Seroussi Brigitte, O. Saka, C. Lovis, A. Hasman, & S. K. Andersen (Eds.), e-Health - For Continuity of Care - Proceedings of MIE 2014 (pp. 1178-1182). (Studies in Health Technology and Informatics; Vol. 205). IOS Press. https://doi.org/10.3233/978-1-61499-432-9-1178

Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer. / Botsis, Taxiarchis; Scott, John; Goud, Ravi et al.
e-Health - For Continuity of Care - Proceedings of MIE 2014. ed. / Louise Pape-Haugaard; Brigitte Seroussi Brigitte; Osman Saka; Christian Lovis; Arie Hasman; Stig Kjaer Andersen. IOS Press, 2014. p. 1178-1182 (Studies in Health Technology and Informatics; Vol. 205).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Botsis, T, Scott, J, Goud, R, Toman, P, Sutherland, A & Ball, R 2014, Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer. in L Pape-Haugaard, B Seroussi Brigitte, O Saka, C Lovis, A Hasman & SK Andersen (eds), e-Health - For Continuity of Care - Proceedings of MIE 2014. Studies in Health Technology and Informatics, vol. 205, IOS Press, pp. 1178-1182, 25th European Medical Informatics Conference, MIE 2014, Istanbul, Turkey, 8/31/14. https://doi.org/10.3233/978-1-61499-432-9-1178

Botsis T, Scott J, Goud R, Toman P, Sutherland A, Ball R. Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer. In Pape-Haugaard L, Seroussi Brigitte B, Saka O, Lovis C, Hasman A, Andersen SK, editors, e-Health - For Continuity of Care - Proceedings of MIE 2014. IOS Press. 2014. p. 1178-1182. (Studies in Health Technology and Informatics). doi: 10.3233/978-1-61499-432-9-1178

Botsis, Taxiarchis ; Scott, John ; Goud, Ravi et al. / Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer. e-Health - For Continuity of Care - Proceedings of MIE 2014. editor / Louise Pape-Haugaard ; Brigitte Seroussi Brigitte ; Osman Saka ; Christian Lovis ; Arie Hasman ; Stig Kjaer Andersen. IOS Press, 2014. pp. 1178-1182 (Studies in Health Technology and Informatics).

@inproceedings{222bc83ab3df44299602ae98ff5fe466,

title = "Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer",

abstract = "The medical review of adverse event reports for medical products requires the processing of 'big data' stored in spontaneous reporting systems, such as the US Vaccine Adverse Event Reporting System (VAERS). VAERS data are not well suited to traditional statistical analyses so we developed the FDA Adverse Event Network Analyzer (AENA) and three novel network analysis approaches to extract information from these data. Our new approaches include a weighting scheme based on co-occurring triplets in reports, a visualization layout inspired by the islands algorithm, and a network growth methodology for the detection of outliers. We explored and verified these approaches by analysing the historical signal of Intussusception (IS) after the administration of RotaShield vaccine (RV) in 1999. We believe that our study supports the use of AENA for pattern recognition in medical product safety and other clinical data.",

keywords = "Big Data, Network Analysis, Pattern Recognition, Safety Surveillance",

author = "Taxiarchis Botsis and John Scott and Ravi Goud and Pamela Toman and Andrea Sutherland and Robert Ball",

year = "2014",

doi = "10.3233/978-1-61499-432-9-1178",

language = "English (US)",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "1178--1182",

editor = "Louise Pape-Haugaard and {Seroussi Brigitte}, Brigitte and Osman Saka and Christian Lovis and Arie Hasman and Andersen, {Stig Kjaer}",

booktitle = "e-Health - For Continuity of Care - Proceedings of MIE 2014",

note = "25th European Medical Informatics Conference, MIE 2014 ; Conference date: 31-08-2014 Through 03-09-2014",

}

TY - GEN

T1 - Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer

AU - Botsis, Taxiarchis

AU - Scott, John

AU - Goud, Ravi

AU - Toman, Pamela

AU - Sutherland, Andrea

AU - Ball, Robert

PY - 2014

Y1 - 2014

N2 - The medical review of adverse event reports for medical products requires the processing of 'big data' stored in spontaneous reporting systems, such as the US Vaccine Adverse Event Reporting System (VAERS). VAERS data are not well suited to traditional statistical analyses so we developed the FDA Adverse Event Network Analyzer (AENA) and three novel network analysis approaches to extract information from these data. Our new approaches include a weighting scheme based on co-occurring triplets in reports, a visualization layout inspired by the islands algorithm, and a network growth methodology for the detection of outliers. We explored and verified these approaches by analysing the historical signal of Intussusception (IS) after the administration of RotaShield vaccine (RV) in 1999. We believe that our study supports the use of AENA for pattern recognition in medical product safety and other clinical data.

AB - The medical review of adverse event reports for medical products requires the processing of 'big data' stored in spontaneous reporting systems, such as the US Vaccine Adverse Event Reporting System (VAERS). VAERS data are not well suited to traditional statistical analyses so we developed the FDA Adverse Event Network Analyzer (AENA) and three novel network analysis approaches to extract information from these data. Our new approaches include a weighting scheme based on co-occurring triplets in reports, a visualization layout inspired by the islands algorithm, and a network growth methodology for the detection of outliers. We explored and verified these approaches by analysing the historical signal of Intussusception (IS) after the administration of RotaShield vaccine (RV) in 1999. We believe that our study supports the use of AENA for pattern recognition in medical product safety and other clinical data.

KW - Big Data

KW - Network Analysis

KW - Pattern Recognition

KW - Safety Surveillance

UR - http://www.scopus.com/inward/record.url?scp=84929515750&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84929515750&partnerID=8YFLogxK

U2 - 10.3233/978-1-61499-432-9-1178

DO - 10.3233/978-1-61499-432-9-1178

M3 - Conference contribution

C2 - 25160375

AN - SCOPUS:84929515750

T3 - Studies in Health Technology and Informatics

SP - 1178

EP - 1182

BT - e-Health - For Continuity of Care - Proceedings of MIE 2014

A2 - Pape-Haugaard, Louise

A2 - Seroussi Brigitte, Brigitte

A2 - Saka, Osman

A2 - Lovis, Christian

A2 - Hasman, Arie

A2 - Andersen, Stig Kjaer

PB - IOS Press

T2 - 25th European Medical Informatics Conference, MIE 2014

Y2 - 31 August 2014 through 3 September 2014

ER -

Novel Algorithms for Improved Pattern Recognition Using the US FDA Adverse Event Network Analyzer

Abstract

Publication series

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this