The Applied Research Of Serum Protein Spectrum Of Esophageal Cancer Combined With Artificial Neural Network Diagnosis System

Objective: Esophageal cancer are malignant tumors of digestive system with a high disease incidence in our country, Only early diagnosis can effectively improve of 5-year survival rate.Protein spectrum technology is a wide range of disease markers analysis platform based on protein chip and mass spectrometry technology,it helps filter out associated molecular changes of esophageal cancer.Now,According to the serum protein spectrum specific expression to establishment the artificial neural network diagnostic system of esophageal cancer,and to research the significance at the early diagnosis of esophageal cancer。Methods:Collection of the serum of the experimental group (59 cases of esophageal cancer patients),the first control group (60 cases of non-esophageal cancer patients with malignant tumors of the digestive system),the second control group(27 cases of benign disease patients),the third control group(30 cases of normal people),amount to 176 cases of the serum samples.all serum samples were detected using surface-enhanced laser desorption ionization time of flight mass spectrometry (SELDI-TOF-MS)combined with gold chips, using Ciphergen Proteinehip software and Biomarker Wizard 3.1 software to obtain mixed patterns of all serum for statistical analysis and calculate their differences in order to filter out the specific expression of protein; using specific expression of M/Z combined with artificial neural network software establish the diagnosis system of esophageal cancer。Results:After experimental detected, we found eight differences protein peaks (4218.8,4238.4,4478.2,4966.1,5336.6,5357.1,5919.8,5940.1,M/Z) (P <0.001)from 176 cases of the serum samples,and to establishment the artificial neural network diagnostic system of esophageal cancer. Then, using double-blind method to detected the artificial neural network diagnosis system of esophageal cancer,to verify the diagnosis system of sensitivity and specificity. Statistical analysis showed that We establishment the diagnostic system of esophageal cancer in the cut-off of 0.3, the detection of esophageal cancer patients with a sensitivity of 88.1% and specificity was 85.5%, diagnose accordance rate 86.4%。Conclusion: 1.Eight differences M/Z with specific expression in serum of esophageal cancer were found successfully; 2. Successfully established a artificial neural network diagnosis system of esophageal cancer, and be verified with double-blind method, and obtain to satisfactory sensitivity and specificity from the objective indicators; 3. The value of diagnostic efficiency analysis of ANN system tell us, When the cut-off value of 0.1, ANN system can achieve 98.3% sensitivity, but the specificity was only 57.3%, it could be applied to a large number of medical examinations or screening in a large area; when the cut-off value of 0.5,ANN system can achieve a specificity of 95.7%, but the sensitivity was only 62.7 %, it could be applied to patients with early diagnosis; 4.Combination with serum protein spectrum and artificial neural network diagnosis system for small samples of patients with esophageal cancer has a higher diagnostic sensitivity and specificity, High-risk groups can be used for early screening or early diagnosis,Samples could be expanded to conduct in-depth applied research.