Abstract
One of recent advances in biotechnology offers high-throughput mass-spectrometry data, for disease detection, prevention, and biomarker discovery. In fact proteomics has recently become an attractive topic of research in biomedicine. Signal processing and pattern classification techniques are inherently essential for analyzing proteomic data. In this paper the estimation method of block kriging is utilized to derive an error marching strategy for classifying proteomic signals with a particular application to the prediction of cardiovascular events using clinical mass spectrometry data. The proposed block kriging based classification technique has been found to be superior to other recently developed methods.