A grid-based HIV expert system

ABSTRACT. 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 data...

• Type: Conference
• Year: 2005
• Where: CCGRID
• Authors: Peter M. A. Sloot, Alexander Boukhanovsky, Wilco Keulen, Charles A. Boucher
• Keywords: Artificial Intelligence, CCGRID 2005, Cellular Automata-based Simulations, Cluster Computing, In-vivo Pharmaceutical Data