Biomedical subjects

Bostjan Brumen

Publications and source records attributed to Bostjan Brumen.

3 recordsLinked to original sources

PubMed2005

Agent oriented approach to handling medical data.

Medical treatment of a patient could be represented as a circle of the following actions: examination, diagnostics, and therapy. The aims of the actions are to find out the patient's state of health and consequently to conclude about possible diseases and finally to choose a suitable therapy. In long term, the circle of actions repeat as long as the patient is not healthy. Efficiency of this treatment depends on the knowledge and the experiences of the physicians involved. Information technology offers many possibilities to help the physicians increase the efficiency and the quality of this work. In the article, we present an agent-oriented computer-based health care service, which uses information from different data sources that are physically distributed across several sites. Such a decentralized approach mirrors the organizational structure of a health service and it is very similar to an agent-oriented view of the world.

Artificial Intelligence↗

PubMed2005

Diagnostic process from the data quality point of view.

The spread of electronic use of data in various areas has put importance of data quality to higher level. Data quality has syntactic and semantic component; the syntactic component is relatively easy to achieve if supported by tools (either off-the-shelf or our own), while semantic component requires more research. In many cases such data come from different sources, are distributed across enterprise and are at different quality levels. Special attention needs to be paid to data upon which critical decisions are met, such as medical data for example. The starting point for research is in our case the risk of the medical area. In the paper we will focus on the semantic component of medical data quality.

Computer Security↗

PubMed2005

Protecting medical data for decision-making analyses.

In this paper, we present a procedure for data protection, which can be applied before any model building based analyses are performed. In medical environments, abundant data exist, but because of the lack of knowledge, they are rarely analyzed, although they hide valuable and often life-saving knowledge. To be able to analyze the data, the analyst needs to have a full access to the relevant sources, but this may be in the direct contradiction with the demand that data remain secure, and more importantly in medical area, private. This is especially the case if the data analyst is outsourced and not directly affiliated with the data owner. We address this issue and propose a solution where the model-building process is still possible while data are better protected. We consider the case where the distributions of original data values are preserved while the values themselves change, so that the resulting model is equivalent to the one built with original data.

Algorithms↗