Knowledge-Based Avoidance of Drug-Resistant HIV Mutants
Lathrop, Richard H., Steffen, Nicholas R., Raphael, Miriam P., Deeds-Rubin, Sophia, et al., AI Magazine
We describe an AI system (CSHIV) that connects the scientific AIDS literature describing specific human immunodeficiency virus (HIV) drug resistances directly to the customized treatment strategy of a specific HIV patient. Rules in the CTSHIV knowledge base encode knowledge about sequence mutations in the HIV genome that have been found to result in drug resistance to the HIV virus. Rules are applied to the actual HIV sequences of the virus strains infecting the specific patient undergoing clinical treatment to infer current drug resistance. A rule-directed search through mutation sequence space identifies nearby drug-resistant mutant strains that might arise. The possible combination drug-treatment regimens currently approved by the U.S. Food and Drug Administration are considered and ranked by their estimated ability to avoid identified current and nearby drug-resistant mutants. The highest-ranked treatments are recommended to the attending physician. The result is more precise treatment of individual HIV patients and a decreased tendency to select for drug-resistant genes in the global HIV gene pool. Initial results from a small human clinical trial are encouraging, and further clinical trials are planned. From an Al viewpoint, the case study demonstrates the extensibility of knowledge-based systems because it illustrates how existing encoded knowledge can be used to support new knowledge-based applications that were unanticipated when the original knowledge was encoded.
Human immunodeficiency virus (HIV) causes progressive deterioration of the immune system leading almost invariably to AIDS and death from opportunistic cancers and infections. Currently in the United States, it is estimated to infect 3 to 5 million persons, is the leading cause of death in adults from 14 to 35, and is the nation's leading cause of productive years of life lost aggregated over all age groups. HIV is estimated to infect 40 to 50 million persons worldwide (CDC 1997).
The high rate of HIV viral mutation both makes development of a vaccine difficult and results in rapid positive selection for drug-resistant mutant strains. Recent multidrug combination therapies are encouraging but in most cases ultimately fail because of the development of drug resistance (O'Brian et al. 1996). A general theory of HIV drug resistance still is not in hand, but a number of specific sequence mutations in the HIV genome have been described in the scientific literature and associated with increased resistance to certain drugs.
In this article, we describe an AI system (CTSHIV) intended to improve the clinical treatment of individual HIV patients by identifying drug resistance in advance and avoiding it in treatment. The improvement is accomplished by first identifying drug-resistant HIV mutant strains that already exist in the patient, or can be selected positively for, by certain treatments and then recommending a customized treatment strategy designed to avoid selection of such mutants. The result is more precise treatment of individual HIV patients and a decreased tendency to select for drug-resistant genes in the global HIV gene pool.
The project goals are to (1) connect knowledge contained in the scientific literature about HIV drug resistance directly to the treatment of individual HIV patients, (2) enable customized treatment strategies to be based on the HIV genotype that currently infects an individual HIV patient, (3) identify the nature and extent of drug resistance currently present in an individual HIV patient, (4) identify nearby drugresistant mutant strains that could be selected positively for by some treatments, (5) rank the possible U.S. Food and Drug Administration (FDA)-approved treatments by an estimate of their ability to avoid both current and nearby drug-resistant mutants, (6) estimate the costs of the highest-ranked treatments, and (7) recommend treatments that are heuristically …
Questia, a part of Gale, Cengage Learning. www.questia.com
Publication information: Article title: Knowledge-Based Avoidance of Drug-Resistant HIV Mutants. Contributors: Lathrop, Richard H. - Author, Steffen, Nicholas R. - Author, Raphael, Miriam P. - Author, Deeds-Rubin, Sophia - Author, et al. - Author. Magazine title: AI Magazine. Volume: 20. Issue: 1 Publication date: Spring 1999. Page number: 13+. © 2009 American Association for Artificial Intelligence. Provided by ProQuest LLC. All Rights Reserved.
This material is protected by copyright and, with the exception of fair use, may not be further copied, distributed or transmitted in any form or by any means.