A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection

Hao Ying, Feng Lin, Rodger David MacArthur, Jonathan A. Cohn, Daniel C. Barth-Jones, Hong Ye, Lawrence R. Crane

Research output: Contribution to journalArticle

30 Citations (Scopus)

Abstract

The U.S. Department of Health and Human Services Human Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatment-decision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6%. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4% and 100%. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9% with the agreement for the two experts being both 100%. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.

Original languageEnglish (US)
Pages (from-to)966-979
Number of pages14
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume37
Issue number4
DOIs
StatePublished - Aug 1 2007
Externally publishedYes

Fingerprint

Discrete event simulation
Viruses
Supervised learning
System theory
Finite automata
Decision support systems
Medicine
Learning systems
Classifiers
Genetic algorithms
Health

Keywords

  • Artificial intelligence
  • Discrete event systems
  • Fuzzy discrete event systems
  • Fuzzy logic
  • HIV/AIDS treatment

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Information Systems
  • Human-Computer Interaction
  • Computer Science Applications
  • Electrical and Electronic Engineering

Cite this

A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection. / Ying, Hao; Lin, Feng; MacArthur, Rodger David; Cohn, Jonathan A.; Barth-Jones, Daniel C.; Ye, Hong; Crane, Lawrence R.

In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, Vol. 37, No. 4, 01.08.2007, p. 966-979.

Research output: Contribution to journalArticle

Ying, Hao ; Lin, Feng ; MacArthur, Rodger David ; Cohn, Jonathan A. ; Barth-Jones, Daniel C. ; Ye, Hong ; Crane, Lawrence R. / A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection. In: IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics. 2007 ; Vol. 37, No. 4. pp. 966-979.
@article{e3e7afa0bf704853a70b38ae45ea39f8,
title = "A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection",
abstract = "The U.S. Department of Health and Human Services Human Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatment-decision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6{\%}. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4{\%} and 100{\%}. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9{\%} with the agreement for the two experts being both 100{\%}. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.",
keywords = "Artificial intelligence, Discrete event systems, Fuzzy discrete event systems, Fuzzy logic, HIV/AIDS treatment",
author = "Hao Ying and Feng Lin and MacArthur, {Rodger David} and Cohn, {Jonathan A.} and Barth-Jones, {Daniel C.} and Hong Ye and Crane, {Lawrence R.}",
year = "2007",
month = "8",
day = "1",
doi = "10.1109/TSMCB.2007.895360",
language = "English (US)",
volume = "37",
pages = "966--979",
journal = "IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics",
issn = "1083-4419",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - A self-learning fuzzy discrete event system for HIV/AIDS treatment regimen selection

AU - Ying, Hao

AU - Lin, Feng

AU - MacArthur, Rodger David

AU - Cohn, Jonathan A.

AU - Barth-Jones, Daniel C.

AU - Ye, Hong

AU - Crane, Lawrence R.

PY - 2007/8/1

Y1 - 2007/8/1

N2 - The U.S. Department of Health and Human Services Human Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatment-decision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6%. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4% and 100%. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9% with the agreement for the two experts being both 100%. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.

AB - The U.S. Department of Health and Human Services Human Immunodeficiency Virus (HIV)/Acquired Immune Deficiency Syndrome (AIDS) treatment guidelines are modified several times per year to reflect the rapid evolution of the field (e.g., emergence of new antiretroviral drugs). As such, a treatment-decision support system that is capable of self-learning is highly desirable. Based on the fuzzy discrete event system (FDES) theory that we recently created, we have developed a self-learning HIV/AIDS regimen selection system for the initial round of combination antiretroviral therapy, one of the most complex therapies in medicine. The system consisted of a treatment objectives classifier, fuzzy finite state machine models for treatment regimens, and a genetic-algorithm-based optimizer. Supervised learning was achieved through automatically adjusting the parameters of the models by the optimizer. We focused on the four historically popular regimens with 32 associated treatment objectives involving the four most important clinical variables (potency, adherence, adverse effects, and future drug options). The learning targets for the objectives were produced by two expert AIDS physicians on the project, and their averaged overall agreement rate was 70.6%. The system's learning ability and new regimen suitability prediction capability were tested under various conditions of clinical importance. The prediction accuracy was found between 84.4% and 100%. Finally, we retrospectively evaluated the system using 23 patients treated by 11 experienced nonexpert faculty physicians and 12 patients treated by the two experts at our AIDS Clinical Center in 2001. The overall exact agreement between the 13 physicians' selections and the system's choices was 82.9% with the agreement for the two experts being both 100%. For the seven mismatched cases, the system actually chose more appropriate regimens in four cases and equivalent regimens in another two cases. It made a mistake in one case. These (preliminary) results show that 1) the System outperformed the nonexpert physicians and 2) it performed as well as the expert physicians did. This learning and prediction approach, as well as our original FDESs theory, is general purpose and can be applied to other medical or nonmedical problems.

KW - Artificial intelligence

KW - Discrete event systems

KW - Fuzzy discrete event systems

KW - Fuzzy logic

KW - HIV/AIDS treatment

UR - http://www.scopus.com/inward/record.url?scp=34547097512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547097512&partnerID=8YFLogxK

U2 - 10.1109/TSMCB.2007.895360

DO - 10.1109/TSMCB.2007.895360

M3 - Article

C2 - 17702293

AN - SCOPUS:34547097512

VL - 37

SP - 966

EP - 979

JO - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

JF - IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

SN - 1083-4419

IS - 4

ER -