A distributed, collaborative intelligent agent system approach for proactive postmarketing drug safety surveillance

Yanqing Ji, Hao Ying, Margo S. Farber, John Yen, Peter Dews, Richard E. Miller, R. Michael Massanari

Research output: Contribution to journalArticle

15 Citations (Scopus)

Abstract

Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is of great importance. The current approach to postmarketing surveillance primarily relies on spontaneous reporting. It is a passive surveillance system and limited by gross underreporting (<10% reporting rate), latency, and inconsistent reporting. We propose a novel team-based intelligent agent software system approach for proactively monitoring and detecting potential ADRs of interest using electronic patient records. We designed such a system and named it ADRMonitor. The intelligent agents, operating on computers located in different places, are capable of continuously and autonomously collaborating with each other and assisting the human users (e.g., the food and drug administration (FDA), drug safety professionals, and physicians). The agents should enhance current systems and accelerate early ADR identification. To evaluate the performance of the ADRMonitor with respect to the current spontaneous reporting approach, we conducted simulation experiments on identification of ADR signal pairs (i.e., potential links between drugs and apparent adverse reactions) under various conditions. The experiments involved over 275000 simulated patients created on the basis of more than 1000 real patients treated by the drug cisapride that was on the market for seven years until its withdrawal by the FDA in 2000 due to serious ADRs. Healthcare professionals utilizing the spontaneous reporting approach and the ADRMonitor were separately simulated by decision-making models derived from a general cognitive decision model called fuzzy recognition-primed decision (RPD) model that we recently developed. The quantitative simulation results show that 1) the number of true ADR signal pairs detected by the ADRMonitor is 6.6 times higher than that by the spontaneous reporting strategy; 2) the ADR detection rate of the ADRMonitor agents with even moderate decision-making skills is five times higher than that of spontaneous reporting; and 3) as the number of patient cases increases, ADRs could be detected significantly earlier by the ADRMonitor.

Original languageEnglish (US)
Article number5352275
Pages (from-to)826-837
Number of pages12
JournalIEEE Transactions on Information Technology in Biomedicine
Volume14
Issue number3
DOIs
StatePublished - May 1 2010

Fingerprint

Postmarketing Product Surveillance
Intelligent agents
Drug-Related Side Effects and Adverse Reactions
Safety
Decision making
Experiments
United States Food and Drug Administration
Monitoring
Decision Making
Cisapride
Pharmaceutical Preparations
Software

All Science Journal Classification (ASJC) codes

  • Biotechnology
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

Ji, Yanqing ; Ying, Hao ; Farber, Margo S. ; Yen, John ; Dews, Peter ; Miller, Richard E. ; Massanari, R. Michael. / A distributed, collaborative intelligent agent system approach for proactive postmarketing drug safety surveillance. In: IEEE Transactions on Information Technology in Biomedicine. 2010 ; Vol. 14, No. 3. pp. 826-837.
@article{a81aa2fdca9a46c3b0dc952755f89707,
title = "A distributed, collaborative intelligent agent system approach for proactive postmarketing drug safety surveillance",
abstract = "Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is of great importance. The current approach to postmarketing surveillance primarily relies on spontaneous reporting. It is a passive surveillance system and limited by gross underreporting (<10{\%} reporting rate), latency, and inconsistent reporting. We propose a novel team-based intelligent agent software system approach for proactively monitoring and detecting potential ADRs of interest using electronic patient records. We designed such a system and named it ADRMonitor. The intelligent agents, operating on computers located in different places, are capable of continuously and autonomously collaborating with each other and assisting the human users (e.g., the food and drug administration (FDA), drug safety professionals, and physicians). The agents should enhance current systems and accelerate early ADR identification. To evaluate the performance of the ADRMonitor with respect to the current spontaneous reporting approach, we conducted simulation experiments on identification of ADR signal pairs (i.e., potential links between drugs and apparent adverse reactions) under various conditions. The experiments involved over 275000 simulated patients created on the basis of more than 1000 real patients treated by the drug cisapride that was on the market for seven years until its withdrawal by the FDA in 2000 due to serious ADRs. Healthcare professionals utilizing the spontaneous reporting approach and the ADRMonitor were separately simulated by decision-making models derived from a general cognitive decision model called fuzzy recognition-primed decision (RPD) model that we recently developed. The quantitative simulation results show that 1) the number of true ADR signal pairs detected by the ADRMonitor is 6.6 times higher than that by the spontaneous reporting strategy; 2) the ADR detection rate of the ADRMonitor agents with even moderate decision-making skills is five times higher than that of spontaneous reporting; and 3) as the number of patient cases increases, ADRs could be detected significantly earlier by the ADRMonitor.",
author = "Yanqing Ji and Hao Ying and Farber, {Margo S.} and John Yen and Peter Dews and Miller, {Richard E.} and Massanari, {R. Michael}",
year = "2010",
month = "5",
day = "1",
doi = "10.1109/TITB.2009.2037007",
language = "English (US)",
volume = "14",
pages = "826--837",
journal = "IEEE Journal of Biomedical and Health Informatics",
issn = "2168-2194",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

A distributed, collaborative intelligent agent system approach for proactive postmarketing drug safety surveillance. / Ji, Yanqing; Ying, Hao; Farber, Margo S.; Yen, John; Dews, Peter; Miller, Richard E.; Massanari, R. Michael.

In: IEEE Transactions on Information Technology in Biomedicine, Vol. 14, No. 3, 5352275, 01.05.2010, p. 826-837.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A distributed, collaborative intelligent agent system approach for proactive postmarketing drug safety surveillance

AU - Ji, Yanqing

AU - Ying, Hao

AU - Farber, Margo S.

AU - Yen, John

AU - Dews, Peter

AU - Miller, Richard E.

AU - Massanari, R. Michael

PY - 2010/5/1

Y1 - 2010/5/1

N2 - Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is of great importance. The current approach to postmarketing surveillance primarily relies on spontaneous reporting. It is a passive surveillance system and limited by gross underreporting (<10% reporting rate), latency, and inconsistent reporting. We propose a novel team-based intelligent agent software system approach for proactively monitoring and detecting potential ADRs of interest using electronic patient records. We designed such a system and named it ADRMonitor. The intelligent agents, operating on computers located in different places, are capable of continuously and autonomously collaborating with each other and assisting the human users (e.g., the food and drug administration (FDA), drug safety professionals, and physicians). The agents should enhance current systems and accelerate early ADR identification. To evaluate the performance of the ADRMonitor with respect to the current spontaneous reporting approach, we conducted simulation experiments on identification of ADR signal pairs (i.e., potential links between drugs and apparent adverse reactions) under various conditions. The experiments involved over 275000 simulated patients created on the basis of more than 1000 real patients treated by the drug cisapride that was on the market for seven years until its withdrawal by the FDA in 2000 due to serious ADRs. Healthcare professionals utilizing the spontaneous reporting approach and the ADRMonitor were separately simulated by decision-making models derived from a general cognitive decision model called fuzzy recognition-primed decision (RPD) model that we recently developed. The quantitative simulation results show that 1) the number of true ADR signal pairs detected by the ADRMonitor is 6.6 times higher than that by the spontaneous reporting strategy; 2) the ADR detection rate of the ADRMonitor agents with even moderate decision-making skills is five times higher than that of spontaneous reporting; and 3) as the number of patient cases increases, ADRs could be detected significantly earlier by the ADRMonitor.

AB - Discovering unknown adverse drug reactions (ADRs) in postmarketing surveillance as early as possible is of great importance. The current approach to postmarketing surveillance primarily relies on spontaneous reporting. It is a passive surveillance system and limited by gross underreporting (<10% reporting rate), latency, and inconsistent reporting. We propose a novel team-based intelligent agent software system approach for proactively monitoring and detecting potential ADRs of interest using electronic patient records. We designed such a system and named it ADRMonitor. The intelligent agents, operating on computers located in different places, are capable of continuously and autonomously collaborating with each other and assisting the human users (e.g., the food and drug administration (FDA), drug safety professionals, and physicians). The agents should enhance current systems and accelerate early ADR identification. To evaluate the performance of the ADRMonitor with respect to the current spontaneous reporting approach, we conducted simulation experiments on identification of ADR signal pairs (i.e., potential links between drugs and apparent adverse reactions) under various conditions. The experiments involved over 275000 simulated patients created on the basis of more than 1000 real patients treated by the drug cisapride that was on the market for seven years until its withdrawal by the FDA in 2000 due to serious ADRs. Healthcare professionals utilizing the spontaneous reporting approach and the ADRMonitor were separately simulated by decision-making models derived from a general cognitive decision model called fuzzy recognition-primed decision (RPD) model that we recently developed. The quantitative simulation results show that 1) the number of true ADR signal pairs detected by the ADRMonitor is 6.6 times higher than that by the spontaneous reporting strategy; 2) the ADR detection rate of the ADRMonitor agents with even moderate decision-making skills is five times higher than that of spontaneous reporting; and 3) as the number of patient cases increases, ADRs could be detected significantly earlier by the ADRMonitor.

UR - http://www.scopus.com/inward/record.url?scp=77953142866&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953142866&partnerID=8YFLogxK

U2 - 10.1109/TITB.2009.2037007

DO - 10.1109/TITB.2009.2037007

M3 - Article

VL - 14

SP - 826

EP - 837

JO - IEEE Journal of Biomedical and Health Informatics

JF - IEEE Journal of Biomedical and Health Informatics

SN - 2168-2194

IS - 3

M1 - 5352275

ER -