The search for biomarkers in biological fluids that can be used for disease diagnosis and prognosis using mass spectrometry has emerged to become a state-of-the-art methodology for clinical proteomics. Poor cross platform comparison of the findings, however, makes the need for comparison studies probably as urgent as the need for new ones. It is now increasingly recognized that standardized statistical and bioinformatics approaches during data processing are of utmost importance for such comparisons. This paper reviews two of the currently most promising methods, namely LC-MS and CE-MS techniques, and software tools used to analyze the huge amount of data they generate. We further review the statistical issues of feature selection and sample classification.