摘要目的探索 IBD 血清差异蛋白指纹图谱的诊断模型及其临床应用价值。方法应用弱阳离子磁珠联合基质辅助激光解吸电离飞行时间质谱（MALDI‐TOF‐MS）技术对72例 IBD 患者（其中CD 54例、UC 18例）和44名健康对照者的血清蛋白质谱进行分析，将3组两两对比，采用 Wilcoxon 秩和检验筛选出 P＜0．05的差异蛋白质峰，通过遗传算法结合支持向量机模型的方法筛选出最佳诊断模型，用留一法评估模型的预测效果。结果 CD 组与健康对照组，UC 组与健康对照组，CD 组与 UC 组中分别筛选出差异最大的10个蛋白质峰。质量／电荷比（M ／Z）值为3275．29，4963．91，4980．53，5336．90的4个蛋白质峰组合所建立的诊断模型能很好地区分 CD 组与健康对照组，其诊断 CD 的特异度为97．7％，敏感度为92．6％。 M ／Z 值为2272．41，2660．42，3029．77，5002．78的4个蛋白质峰组合所建立的诊断模型能很好地区分 UC 组与健康对照组，其诊断 UC 的特异度为100．0％，敏感度为94．4％。M ／Z 值为2082．63，2210．64，4039．02，4298．30，4978．03，5002．22的6个蛋白质峰组合模型，诊断 CD 的特异度为50．0％，敏感度为88．9％。结论 MALDI‐TOF‐MS 技术联合遗传算法结合支持向量机模型所建立的 CD 与 UC 血清差异蛋白的诊断模型，对 IBD 具有较高的诊断价值。

abstractsObjective To explore the diagnostic model and clinical application value of serum proteomic fingerprint in inflammatory bowel disease (IBD) .Methods Serum proteome profiles of 72 IBD patients (54 Crohn′s disease (CD) and 18 ulcerative colitis (UC) and 44 healthy controls were analyzed by the weak cation exchange (WCX) beads combined matrix‐assisted laser desorption/ionization time of flight mass spectrometry (MALDI‐TOF‐MS ) technique . Among three groups , every two groups were compared .Wilcoxon rank sum test was used to screen out the peaks of difference expressed protein (P<0 .05) .Genetic algorithm combining with support vector machine (SVM ) was utilized to select the best diagnostic model .The predictive effects of this model was evaluated by leave one out method (LOO ) . Results The 10 most discriminating protein peaks were screened out between CD group and healthy control group , between UC group and healthy control group , between CD group and UC group . A diagnostic model established with four protein peaks ,the mass‐to‐charge ratio (M /Z ) of them was 3 275 .29 ,4 963 .91 ,4 980 .53 and 5 336 .90 ,could better distinguish CD and healthy controls .The specificity was 97 .7% ,and the sensitivity was 92 .6% in CD diagnosis .A diagnostic model established with four protein peaks ,the M /Z of them was 2 272 .41 ,2 660 .42 ,3 029 .77 and 5 002 .78 ,could better distinguish UC and healthy controls .The specificity was 100 .0% ,and the sensitivity was 94 .4% .A&nbsp;specificity was 50 .0% and sensitivity was 88 .9% in CD diagnosis with the diagnostic model of six protein peaks and the M /Z of them was 2 082 .63 ,2 210 .64 ,4 039 .02 ,4 298 .30 ,4 978 .03 ,5 002 .22 .Conclusion The diagnostic model of serum difference expressed protein in CD and UC is established by MALDI‐TOF‐MS technique and genetic algorithm combining with SVM ,which has high diagnostic value in IBD .