CAJ | 학술논문

目的建立胰腺癌血清学诊断模型,探讨评估胰腺癌分期和治疗疗效的生物学标志物.方法采用强阴离子交换(SAX2)芯片和表面增强激光解吸电离飞行时间质谱仪(SELDI-TOF-MS)技术,测定58例胰腺癌患者和51例正常对照者的血清蛋白质指纹图谱;应用Biomarker Wizard统计软件以及决策树算法、Logistic回归和ROC曲线,建立决策树和二分类回归诊断模型.结果在质荷比(M/Z)值为2000～30 000范围内,建立10个决策树诊断模型,其预测胰腺癌的正确率为92.9%(13/14),诊断胰腺癌的敏感性为83.3%,特异性为100%.应用Logistic回归联合多种差异蛋白峰诊断胰腺癌的曲线下面积(AUC)为0.976±0.011(P<0.001),敏感性为77.6%～91.4%,特异性为92.2%～100%.联合6个差异蛋白峰诊断胰腺癌Ⅰ与Ⅱ期、Ⅱ与Ⅲ期以及Ⅲ与Ⅳ期的AUC值分别为0.897±0.054、0.978±0.021和0.792±0.107(P<0.05).胰腺癌组中高表达的差异蛋白峰(M/Z 4016)在手术前后有下调趋势(P<0.05).结论应用SELDI-TOF-MS技术进行胰腺癌血清蛋白质指纹图谱分析,采用统计学方法建立胰腺癌决策树和二分类回归诊断模型,对胰腺癌的诊断和鉴别诊断有一定的价值;筛选出的差异蛋白峰对胰腺癌的预后和疗效评估有一定的应用价值.
목적 건립이선암혈청학진단모형,탐토평고이선암분기화치료료효적생물학표지물.방법 채용강음리자교환(SAX2)심편화표면증강격광해흡전리비행시간질보의(SELDI-TOF-MS)기술,측정58례이선암환자화51례정상대조자적혈청단백질지문도보;응용Biomarker Wizard통계연건이급결책수산법、Logistic회귀화ROC곡선,건립결책수화이분류회귀진단모형.결과 재질하비(M/Z)치위2000～30 000범위내,건립10개결책수진단모형,기예측이선암적정학솔위92.9%(13/14),진단이선암적민감성위83.3%,특이성위100%.응용Logistic회귀연합다충차이단백봉진단이선암적곡선하면적(AUC)위0.976±0.011(P<0.001),민감성위77.6%～91.4%,특이성위92.2%～100%.연합6개차이단백봉진단이선암Ⅰ여Ⅱ기、Ⅱ여Ⅲ기이급Ⅲ여Ⅳ기적AUC치분별위0.897±0.054、0.978±0.021화0.792±0.107(P<0.05).이선암조중고표체적차이단백봉(M/Z 4016)재수술전후유하조추세(P<0.05).결론 응용SELDI-TOF-MS기술진행이선암혈청단백질지문도보분석,채용통계학방법건립이선암결책수화이분류회귀진단모형,대이선암적진단화감별진단유일정적개치;사선출적차이단백봉대이선암적예후화료효평고유일정적응용개치.
Objective To establish decision tree and logistic regression classification models for diagnosing pancreatic adenocarcinoma (PaCa) and for screening serum biomarkers related to evaluation of different stages and curative effects. Methods Serum samples obtained from subjects with pancreatic adenocarcinoma (n =58) and normal pancreas (n =51) were applied to strong anion exchange chromatography (SAX2) chips for protein profiling by SELDI-TOF-MS to screen multiple serum biomarkers.Biomarker Wizard software and several statistical methods including algorithm of decision tree, logistic regression and ROC curves were used to construct the decision tree or logistic regression classification models. Results Average of 61 mass peaks were detected at the molecular range of 2000-30 000, ten decision trees with the highest cross validation rate were chosen to construct the classification models, which can differentiate PaCa from normal pancreas with a sensitivity of 83.3% and a specificity of 100%. Logistic regression was used to achieve the AUC (0.976 ±0. 011 ,P <0.001) with a sensitivity of 77. 6%-91. 4%and a specificity of 92.2% -100%. Six mass peaks were combined by logistic regression to achieve the AUC 0.897 ±0.054, 0.978 ±0.021 and 0. 792 ± 0. 107 (P < 0. 05 ) in the three groups (patients at stage Ⅰ and Ⅱ , stage 1 and Ⅲ, stage Ⅲ and Ⅳ ). One mass peak (M/Z 4 016) was screened (P < 0. 05)significantly between the preoperative and postoperative PaCa samples and the intensity decreased weeks after operation. Conclusion Decision tree and logistic regression classification models of the mass peaks screened by SELDI-TOF-MS serum profiling can be used to differentiate pancreatic adenocarcinoma from normal pancreas, and is superior to CA 199. The detected mass peaks are helpful for the evaluation of curative effect and prognosis of pancreatic adenocarcinoma.