Sidransky David, Irizarry Rafael, Califano Joseph A, Li Xianbin, Ren Hening, Benoit Nicole, Mao Li
Department of Otolaryngology-Head and Neck Surgery, Head and Neck Cancer Research Division, The Johns Hopkins University School of Medicine, Baltimore, MD 21205-2196, USA.
J Natl Cancer Inst. 2003 Nov 19;95(22):1711-7. doi: 10.1093/jnci/djg099.
There are no reliable blood markers for the early detection and monitoring of aerodigestive tract tumors. Recent studies have suggested that serum protein patterns may be able to distinguish cancer patients from control subjects.
We used matrix-assisted laser desorption and ionization (MALDI) mass spectroscopy to obtain serum protein patterns from patients with head and neck cancer (n = 99) or lung cancer (n = 92) and from control subjects (n = 143) at risk for the development of these cancers. From the mass spectra, we predicted the cancer status of patients using a simple classification procedure based on a t test feature selection and linear discriminant analysis (LDA). We cross-validated the data with 200 random data simulations to establish a range of the LDA tuning parameter, which was used to construct receiver operating characteristic (ROC) curves.
Average total protein levels were higher in case patients than in control subjects, although the differences were not statistically significant. Ten individual m/z peaks, from 5 to 111 kd, appeared frequently in head and neck cancer patients but not in control subjects. Using the 45 top predictors, selected by spectral mass and LDA, we observed that ROC curves differed from those expected under the null hypothesis, suggesting that spectral profiles from the sera of patients with head and neck cancer statistically significantly differed from the sera of control subjects. The model developed on head and neck cancer patients could also be used to identify patients with lung cancer.
The pattern of protein spectra in total serum reliably distinguished cancer case patients from control subjects. Incorporation of MALDI assays into prospective longitudinal trials to assess the true predictive values of protein spectra in cancer detection is needed.
