A Grid-Based Hiv Expert System

Objectives.This paper addresses Grid-based integration and access of distributed data from infectious disease patient databases, literature on in-vitro and in-vivo pharmaceutical data, mutation databases, clinical trials, simulations and medical expert knowledge. Methods. Multivariate analyses combined with rule-based fuzzy logic are applied to the integrated data to provide ranking of patient-specific drugs. In addition, cellular automata-based simulations are used to predict the drug behaviour over time. Access to and integration of data is done through existing Internet servers and emerging Grid-based frameworks like Globus. Data presentation is done by standalone PC based software, Web-access and PDA roaming WAP access. The experiments were carried out on the DAS2, a Dutch Grid testbed. Results. The output of the problem-solving environment (PSE) consists of a prediction of the drug sensitivity of the virus, generated by comparing the viral genotype to a relational database which contains a large number of phenotype-genotype pairs.Conclusions. Artificial Intelligence and Grid technology are effectively used to abstract knowledge from the data and provide the physicians with adaptive interactive advice on treatment applied to drug resistant HIV. An important aspect of our research is to use a variety of statistical and numerical methods to identify relationships between HIV genetic sequences and antiviral resistance to investigate consistency of results.

[1]  J. Schapiro,et al.  Methods for investigation of the relationship between drug-susceptibility phenotype and human immunodeficiency virus type 1 genotype with applications to AIDS clinical trials group 333. , 2000, The Journal of infectious diseases.

[2]  Elizabeth Connick,et al.  Antiretroviral-drug resistance among patients recently infected with HIV. , 2002, The New England journal of medicine.

[3]  R. M. Zorzenon dos Santos,et al.  Dynamics of HIV infection: a cellular automata approach. , 2001, Physical review letters.

[4]  Samuel Karlin.  COMPOUNDING STOCHASTIC PROCESSES , 1968 .

[5]  M. Waterman.  Mathematical Methods for DNA Sequences , 1989 .

[6]  Peter M. A. Sloot,et al.  A grid-based problem-solving environment for biomedicine , 2003 .

[7]  Peter M. A. Sloot,et al.  Cellular Automata Model of Drug Therapy for HIV Infection , 2002, ACRI.

[8]  Peter M. A. Sloot,et al.  Stochastic Modeling of Temporal Variability of HIV-1 Population , 2003, International Conference on Computational Science.

[9]  J. Schapiro,et al.  Drug-resistance genotyping in HIV-1 therapy: the VIRAD APT randomi sed controlled trial , 1999, The Lancet.

[10]  Peter M. A. Sloot,et al.  AG-IVE: An Agent Based Solution to Constructing Interactive Simulation Systems , 2002, International Conference on Computational Science.

[11]  Samuel Karlin,et al.  A First Course on Stochastic Processes , 1968 .

[12]  J. Church,et al.  ANTIRETROVIRAL-DRUG RESISTANCE AMONG PATIENTS RECENTLY INFECTED WITH HIV , 2003, Pediatrics.