Towards Application of One-Class Classification Methods to Medical Data

In the problem of one-class classification (OCC) one of the classes, the target class, has to be distinguished from all other possible objects, considered as nontargets. In many biomedical problems this situation arises, for example, in diagnosis, image based tumor recognition or analysis of electrocardiogram data. In this paper an approach to OCC based on a typicality test is experimentally compared with reference state-of-the-art OCC techniques-Gaussian, mixture of Gaussians, naive Parzen, Parzen, and support vector data description-using biomedical data sets. We evaluate the ability of the procedures using twelve experimental data sets with not necessarily continuous data. As there are few benchmark data sets for one-class classification, all data sets considered in the evaluation have multiple classes. Each class in turn is considered as the target class and the units in the other classes are considered as new units to be classified. The results of the comparison show the good performance of the typicality approach, which is available for high dimensional data; it is worth mentioning that it can be used for any kind of data (continuous, discrete, or nominal), whereas state-of-the-art approaches application is not straightforward when nominal variables are present.

Biochemical biomarkers in samples processed by different methods in Environmental Specimen Banks

In the last decades the creation of new Environmental Specimen Banks (ESB) is increasing due to the necessity of knowing the effects of pollutants in both the environment and human populations. ESBs analyze and store samples in order to understand the effects of chemicals, emerging substances and the environmental changes in biota. For a correct analysis of the effect induced by these variables, there is a need to add biological endpoints, such as biomarkers, to the endpoints based on chemical approaches which have being used until now. It is essential to adapt ESB´s sampling strategies in order to enable scientists to apply new biological methods. The present study was performed to obtain biochemical endpoints from samples stored in the BBEBB (Biscay Bay Environmental Biospecimen Bank) of the Marine Station of Plentzia (PIE - UPV/EHU). The main objective of the present work was to study the variability caused in biochemical biomarkers by different processing methods in mussels (Mytilus galloprovincialis) from two localities (Plentzia and Arriluze) with different pollution history. It can be concluded that the selected biomarkers (glutathione S-transferase and acetylcholinesterase) can be accurately measured in samples stored for years in the ESBs. The results also allowed the discrimination of both sampling sites. However, in a further step, the threshold levels and baseline values should be characterized for a correct interpretation of the results in relation to the assessment of the ecosystem health status.

Monte Carlo methods for TMD analyses

4th International Workshop on Transverse Polisarization Phenomena in Hard Processes (TRANSVERSITY 2014)