Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance

Yanqing Ji, Hao Ying, John Yen, Shizhuo Zhu, R. Michael Massanari, Daniel C. Barth-Jones

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is highly desirable. In the U.S., the Food and Drug Administration (FDA) has provided Web-based forms for spontaneous reporting of possible ADRs. Nevertheless, the process of analyzing and interpreting the reports, collecting additional relevant information, and drawing reliable conclusions requires collaboration between experts with different and complimentary skills (e.g., epidemiologists, biostatisticians, pharmacists and physicians). Multi-agent systems have been shown to be a promising approach for tackling distributed problem solving, especially when data sources and knowledge are distributed, and coordination and collaboration are required. Hence, we propose a team-based multi-agent framework for early detection of ADRs. In this framework, intelligent agents assist a team of experts based on a human decision making model called Recognition-Primed Decision (RPD). Fuzzy logic is used to determine the degree of similarity for retrieving experience in the RPD model. We describe our preliminary system design and illustrate its potential benefits for assisting FDA expert teams in early detection of previously unknown ADRs.

Original languageEnglish (US)
Title of host publicationNAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society
Pages644-649
Number of pages6
Volume2005
DOIs
StatePublished - 2005
EventNAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society - Detroit, MI, United States
Duration: Jun 26 2005Jun 28 2005

Other

OtherNAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society
CountryUnited States
CityDetroit, MI
Period6/26/056/28/05

Fingerprint

Multi agent systems
Intelligent agents
Fuzzy logic
Decision making
Systems analysis

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Media Technology

Cite this

Ji, Y., Ying, H., Yen, J., Zhu, S., Massanari, R. M., & Barth-Jones, D. C. (2005). Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance. In NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society (Vol. 2005, pp. 644-649). [1548613] https://doi.org/10.1109/NAFIPS.2005.1548613
Ji, Yanqing ; Ying, Hao ; Yen, John ; Zhu, Shizhuo ; Massanari, R. Michael ; Barth-Jones, Daniel C. / Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance. NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society. Vol. 2005 2005. pp. 644-649
@inproceedings{8fc9d624e17943389f354c32e38b0b9f,
title = "Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance",
abstract = "Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is highly desirable. In the U.S., the Food and Drug Administration (FDA) has provided Web-based forms for spontaneous reporting of possible ADRs. Nevertheless, the process of analyzing and interpreting the reports, collecting additional relevant information, and drawing reliable conclusions requires collaboration between experts with different and complimentary skills (e.g., epidemiologists, biostatisticians, pharmacists and physicians). Multi-agent systems have been shown to be a promising approach for tackling distributed problem solving, especially when data sources and knowledge are distributed, and coordination and collaboration are required. Hence, we propose a team-based multi-agent framework for early detection of ADRs. In this framework, intelligent agents assist a team of experts based on a human decision making model called Recognition-Primed Decision (RPD). Fuzzy logic is used to determine the degree of similarity for retrieving experience in the RPD model. We describe our preliminary system design and illustrate its potential benefits for assisting FDA expert teams in early detection of previously unknown ADRs.",
author = "Yanqing Ji and Hao Ying and John Yen and Shizhuo Zhu and Massanari, {R. Michael} and Barth-Jones, {Daniel C.}",
year = "2005",
doi = "10.1109/NAFIPS.2005.1548613",
language = "English (US)",
volume = "2005",
pages = "644--649",
booktitle = "NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society",

}

Ji, Y, Ying, H, Yen, J, Zhu, S, Massanari, RM & Barth-Jones, DC 2005, Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance. in NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society. vol. 2005, 1548613, pp. 644-649, NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States, 6/26/05. https://doi.org/10.1109/NAFIPS.2005.1548613

Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance. / Ji, Yanqing; Ying, Hao; Yen, John; Zhu, Shizhuo; Massanari, R. Michael; Barth-Jones, Daniel C.

NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society. Vol. 2005 2005. p. 644-649 1548613.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance

AU - Ji, Yanqing

AU - Ying, Hao

AU - Yen, John

AU - Zhu, Shizhuo

AU - Massanari, R. Michael

AU - Barth-Jones, Daniel C.

PY - 2005

Y1 - 2005

N2 - Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is highly desirable. In the U.S., the Food and Drug Administration (FDA) has provided Web-based forms for spontaneous reporting of possible ADRs. Nevertheless, the process of analyzing and interpreting the reports, collecting additional relevant information, and drawing reliable conclusions requires collaboration between experts with different and complimentary skills (e.g., epidemiologists, biostatisticians, pharmacists and physicians). Multi-agent systems have been shown to be a promising approach for tackling distributed problem solving, especially when data sources and knowledge are distributed, and coordination and collaboration are required. Hence, we propose a team-based multi-agent framework for early detection of ADRs. In this framework, intelligent agents assist a team of experts based on a human decision making model called Recognition-Primed Decision (RPD). Fuzzy logic is used to determine the degree of similarity for retrieving experience in the RPD model. We describe our preliminary system design and illustrate its potential benefits for assisting FDA expert teams in early detection of previously unknown ADRs.

AB - Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is highly desirable. In the U.S., the Food and Drug Administration (FDA) has provided Web-based forms for spontaneous reporting of possible ADRs. Nevertheless, the process of analyzing and interpreting the reports, collecting additional relevant information, and drawing reliable conclusions requires collaboration between experts with different and complimentary skills (e.g., epidemiologists, biostatisticians, pharmacists and physicians). Multi-agent systems have been shown to be a promising approach for tackling distributed problem solving, especially when data sources and knowledge are distributed, and coordination and collaboration are required. Hence, we propose a team-based multi-agent framework for early detection of ADRs. In this framework, intelligent agents assist a team of experts based on a human decision making model called Recognition-Primed Decision (RPD). Fuzzy logic is used to determine the degree of similarity for retrieving experience in the RPD model. We describe our preliminary system design and illustrate its potential benefits for assisting FDA expert teams in early detection of previously unknown ADRs.

UR - http://www.scopus.com/inward/record.url?scp=33744992233&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744992233&partnerID=8YFLogxK

U2 - 10.1109/NAFIPS.2005.1548613

DO - 10.1109/NAFIPS.2005.1548613

M3 - Conference contribution

AN - SCOPUS:33744992233

VL - 2005

SP - 644

EP - 649

BT - NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society

ER -

Ji Y, Ying H, Yen J, Zhu S, Massanari RM, Barth-Jones DC. Team-based multi-agent system for early detection of adverse drug reactions in postmarketing surveillance. In NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society. Vol. 2005. 2005. p. 644-649. 1548613 https://doi.org/10.1109/NAFIPS.2005.1548613