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

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

Research output: Contribution to conferencePaper

6 Citations (Scopus)

Abstract

Based on the fuzzy discrete event system theory we originally created, we recently reported the development of an innovative Regimen Selection System for the first round of highly active antiretroviral therapy of HIV/AIDS patients. The core of the System consisted of Fuzzy Finite State Machine Models for Treatment Regimens and a Genetic-Algorithm-Based Optimizer. In the present paper, we studied the inherent self-learning capability of the System. We focused on four historically popular treatment regimens with 32 different associated treatment objectives involving the four most important regimen factors (potency, adherence, adverse effects, and future drug options). Depending on what is to be learned, the highest self-learning accuracy was 100% and the lowest 81% with the average and standard deviation being 93% and 6.3%, respectively. These results establish our approach as a novel supervised learning mechanism. One major advantage of it over the popular neural network learning is that a reasoning chain between input and output of the System is always readily available for humans to understand its decisions. Our approach proves it to be feasible to quantitatively estimate clinical utility of a regimen and compare it with other regimens even before it is available, all with minimal involvement of AIDS experts.

Original languageEnglish (US)
Pages820-824
Number of pages5
DOIs
StatePublished - Dec 1 2005
Externally publishedYes
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

Self-learning
Discrete Event Systems
Supervised learning
Discrete event simulation
System theory
Finite automata
Genetic algorithms
Neural networks
Supervised Learning
State Machine
Systems Theory
Standard deviation
Therapy
Lowest
Drugs
Reasoning
Genetic Algorithm
Neural Networks
Output
Estimate

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

Cite this

Ying, H., Lin, F., Luan, X., MacArthur, R. D., Cohn, J. A., Barth-Jones, D. C., & Crane, L. R. (2005). A fuzzy discrete event system with self-learning capability for HIV/AIDS treatment regimen selection. 820-824. Paper presented at NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States. https://doi.org/10.1109/NAFIPS.2005.1548646

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

2005. 820-824 Paper presented at NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States.

Research output: Contribution to conferencePaper

Ying, H, Lin, F, Luan, X, MacArthur, RD, Cohn, JA, Barth-Jones, DC & Crane, LR 2005, 'A fuzzy discrete event system with self-learning capability for HIV/AIDS treatment regimen selection' Paper presented at NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States, 6/26/05 - 6/28/05, pp. 820-824. https://doi.org/10.1109/NAFIPS.2005.1548646
Ying H, Lin F, Luan X, MacArthur RD, Cohn JA, Barth-Jones DC et al. A fuzzy discrete event system with self-learning capability for HIV/AIDS treatment regimen selection. 2005. Paper presented at NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States. https://doi.org/10.1109/NAFIPS.2005.1548646
Ying, Hao ; Lin, Feng ; Luan, Xiaodong ; MacArthur, Rodger David ; Cohn, Jonathan A. ; Barth-Jones, Daniel C. ; Crane, Lawrence R. / A fuzzy discrete event system with self-learning capability for HIV/AIDS treatment regimen selection. Paper presented at NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society, Detroit, MI, United States.5 p.
@conference{e95a0934445b4976a3285bf07bcaacc1,
title = "A fuzzy discrete event system with self-learning capability for HIV/AIDS treatment regimen selection",
abstract = "Based on the fuzzy discrete event system theory we originally created, we recently reported the development of an innovative Regimen Selection System for the first round of highly active antiretroviral therapy of HIV/AIDS patients. The core of the System consisted of Fuzzy Finite State Machine Models for Treatment Regimens and a Genetic-Algorithm-Based Optimizer. In the present paper, we studied the inherent self-learning capability of the System. We focused on four historically popular treatment regimens with 32 different associated treatment objectives involving the four most important regimen factors (potency, adherence, adverse effects, and future drug options). Depending on what is to be learned, the highest self-learning accuracy was 100{\%} and the lowest 81{\%} with the average and standard deviation being 93{\%} and 6.3{\%}, respectively. These results establish our approach as a novel supervised learning mechanism. One major advantage of it over the popular neural network learning is that a reasoning chain between input and output of the System is always readily available for humans to understand its decisions. Our approach proves it to be feasible to quantitatively estimate clinical utility of a regimen and compare it with other regimens even before it is available, all with minimal involvement of AIDS experts.",
author = "Hao Ying and Feng Lin and Xiaodong Luan and MacArthur, {Rodger David} and Cohn, {Jonathan A.} and Barth-Jones, {Daniel C.} and Crane, {Lawrence R.}",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/NAFIPS.2005.1548646",
language = "English (US)",
pages = "820--824",
note = "NAFIPS 2005 - 2005 Annual Meeting of the North American Fuzzy Information Processing Society ; Conference date: 26-06-2005 Through 28-06-2005",

}

TY - CONF

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

AU - Ying, Hao

AU - Lin, Feng

AU - Luan, Xiaodong

AU - MacArthur, Rodger David

AU - Cohn, Jonathan A.

AU - Barth-Jones, Daniel C.

AU - Crane, Lawrence R.

PY - 2005/12/1

Y1 - 2005/12/1

N2 - Based on the fuzzy discrete event system theory we originally created, we recently reported the development of an innovative Regimen Selection System for the first round of highly active antiretroviral therapy of HIV/AIDS patients. The core of the System consisted of Fuzzy Finite State Machine Models for Treatment Regimens and a Genetic-Algorithm-Based Optimizer. In the present paper, we studied the inherent self-learning capability of the System. We focused on four historically popular treatment regimens with 32 different associated treatment objectives involving the four most important regimen factors (potency, adherence, adverse effects, and future drug options). Depending on what is to be learned, the highest self-learning accuracy was 100% and the lowest 81% with the average and standard deviation being 93% and 6.3%, respectively. These results establish our approach as a novel supervised learning mechanism. One major advantage of it over the popular neural network learning is that a reasoning chain between input and output of the System is always readily available for humans to understand its decisions. Our approach proves it to be feasible to quantitatively estimate clinical utility of a regimen and compare it with other regimens even before it is available, all with minimal involvement of AIDS experts.

AB - Based on the fuzzy discrete event system theory we originally created, we recently reported the development of an innovative Regimen Selection System for the first round of highly active antiretroviral therapy of HIV/AIDS patients. The core of the System consisted of Fuzzy Finite State Machine Models for Treatment Regimens and a Genetic-Algorithm-Based Optimizer. In the present paper, we studied the inherent self-learning capability of the System. We focused on four historically popular treatment regimens with 32 different associated treatment objectives involving the four most important regimen factors (potency, adherence, adverse effects, and future drug options). Depending on what is to be learned, the highest self-learning accuracy was 100% and the lowest 81% with the average and standard deviation being 93% and 6.3%, respectively. These results establish our approach as a novel supervised learning mechanism. One major advantage of it over the popular neural network learning is that a reasoning chain between input and output of the System is always readily available for humans to understand its decisions. Our approach proves it to be feasible to quantitatively estimate clinical utility of a regimen and compare it with other regimens even before it is available, all with minimal involvement of AIDS experts.

UR - http://www.scopus.com/inward/record.url?scp=33744967975&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33744967975&partnerID=8YFLogxK

U2 - 10.1109/NAFIPS.2005.1548646

DO - 10.1109/NAFIPS.2005.1548646

M3 - Paper

AN - SCOPUS:33744967975

SP - 820

EP - 824

ER -