Pilot Study On Serum Protein Finger Printing Coupled With ANN To Eestablish Diagnostic Pattern Of Laryngeal Cancer

Objective: To study Serum Protein of patients with Laryngeal cancer and contrasting persons using surface enhanced laser desorption ionization time of-flight mass spectrometry ( SELDI-TOF-MS ) and to screen different expressed protein.To find molecule diagnostic SELDI model and new method with superiority in sensitivity and specificity for early detection of Laryngeal cancer using ANN (artificial neural network).Methods: The study includes 110 sera,31 patients diagnosed as laryngeal cancer and 79 patients as contrast persons : 23 cases with polyp of vocal cord ; 11 cases with premalignant laryngeal lesions (including keratosis of the larynx, has a serious smoking history of chronic hypertrophic laryngitis, papilloma of larynx); 45 cases healthy people. The SELDI-TOF-MS and gold protein chip were performed to detect mass spectrogram for serum protein signature analysis. Spectra of the protein will be useful with Ciphergen ProteinChip 3.0 software for data correction and analysis.Then , the different expressed markers were screened from the maps by Biomarker Wizard 3.1 software and further to build ANN model .Results: Total of 79 different expressed protein peaks were detected between the group of laryngeal cancer and contrast group(P<0.05) . Of which there are significant differences in the protein peak (t test, the molecular weight 2000～20000 Da, P <0.01) a total of 24.Laryngeal cancer patients with high expression group of proteins have 15 peaks, and low expression of the protein has 9 peaks. After training, the selection from nine significant differences in the expression of protein (M/Z as 9258,3153,2776,2114,2424,5927,2650,2872,2537Da) setting up the artificial neural network model can be diagnosed with the controlled group and patients with laryngeal cancer accurately. When the cut-off value of 0.25 the sensitivity (SEN) was 87.1%, specificity (SPE) 84.8%, diagnostic index for 171.9℅, and the distinction between laryngeal cancer and premalignant laryngeal lesions with an accuracy of 100℅.Conclusion: The technique of SELDI-TOF-MS is high throughput research method in proteomics with superiorities of automation,rapidness,paucity of samples,sensitivity and specificity.Combination of nine markers (M/Z 9258,3153,2776,2114,2424,5927,2650,2872,2537Da) may be hopeful biomarkers which can be help to diagnose Laryngeal cancer, especially to distinguish between premalignant laryngeal lesions and laryngeal cancer has reached 100℅.It is useful for SELDI-TOF-MS technology to diagnose laryngeal cancer and select tumor-specific serum protein biomarker, people are worthy of further study of the deep.