Application of serum surface-enhanced laser desorption/ionization proteomic patterns in distinguishing non-small cell lung cancer patients from healthy people

OBJECTIVE: To explore the application of serum surface-enhanced laser desorption/ionization (SELDI) marker patterns in distinguishing non-small cell lung cancer patients from healthy people by protein chip technology. METHODS: One hundred and sixty-three serum samples (123 patients with lung cancer and 40 healthy persons), were randomly divided into a training set [94 cases, 53 non-small cell lung cancer (NSCLC), 21 small cell lung cancer and 20 healthy persons] and a blinded test set (69 cases), were included for analysis by surface-enhanced laser desorption/ionization time-of-flight mass spectrometry (SELDI-TOF-MS). Five protein peaks at 11,493, 6,429, 8,245, 5,336 and 2,536 were automatically chosen for the system training and the development of a decision classification tree model (marker pattern). The accuracy of the model was tested with the blinded test set (an independent set of masked serum samples from 49 patients with NSCLC and 20 healthy persons). RESULTS: The model differentiated the patients with NSCLC from the healthy people with a sensitivity of 95.9% (71/74) and a specificity of 90.0% (18/20) in the training set and a sensitivity of 83.7%, and a specificity of 80.0% in the blinded set respectively. CONCLUSION: SELDI-TOF-MS technique can correctly distinguish NSCLC patients from healthy people, and it has the potential for the development of a screening test for the detection of NSCLC.