Artificial neural networks analysis of surface-enhanced laser desorption/ionization mass spectra of serum protein pattern distinguishes colorectal cancer from healthy population

Purpose: The low specificity and sensitivity of the carcinoembryonic antigen test makes it not an ideal biomarker for the detection of colorectal cancer. We developed and evaluated a proteomic approach for the simultaneous detection and analysis of multiple proteins for distinguishing individuals with colorectal cancer from healthy individuals. Experimental Design: We subjected serum samples (including 55 colorectal cancer patients and 92 age- and sex-matched healthy individuals) from 147 individuals, for analysis by surface-enhanced laser desorption/ionization (SELDI) mass spectrometry. Peaks were detected with Ciphergen SELDI software version 3.0. Using a multilayer artificial neural network with a back propagation algorithm, we developed a classifier for separating the colorectal cancer groups from the healthy groups. Results: The artificial neural network classifier separated the colorectal cancer from the healthy samples, with a sensitivity of 91% and specificity of 93%. Four top-scored peaks, at m/z of 5,911, 8,930, 8,817, and 4,476, were finally selected as the potential "fingerprints" for detection of colorectal cancer. Conclusions: The combination of SELDI-TOF mass spectrometry with the artificial neural networks in the analysis of serum protein yields significantly higher sensitivity and specificity values for the detection and diagnosis of colorectal cancer.