Reliable quantitative risk assessment requires the use of extensive statistical data, and well validated models for interpreting the data. In many fields neither of these are available in practice, but there may still be a requirement to generate a meaningful characterisation of risk. The StAR project aims to develop sound methods of qualitative risk assessment, based on a novel mathematical theory developed in the laboratory.
An early prototype computer system for the prediction of carcinogenic risk due to chemical compounds was demonstrated t the end of 1994. This has been revised to incorporate software developed at LHASA UK to search for chemical structural alerts. The revised prototype was demonstrated early in 1996, and work is now progressing to extend the knowledge base. The StAR project is currently focused on the assessment of carcinogenic risk, but the resulting technology should be applicable to a wide range of risk assessment problems in oncology and further afield.
The StAR project was funded by the UK Department of Trade and Industry and the Engineering and Physical Sciences Research Council, as part of the Intelligent Systems Integration Programme.