一种基于-5，-7前列腺特异性抗原（proPSA）的人工神经网络用于检测前列腺癌。
A (-5, -7) proPSA based artificial neural network to detect prostate cancer.
作者信息
Stephan Carsten, Meyer Hellmuth-Alexander, Kwiatkowski Maciej, Recker Franz, Cammann Henning, Loening Stefan A, Jung Klaus, Lein Michael
机构信息
Department of Urology, Universitätsmedizin Charité Berlin, CCM, Germany.
出版信息
Eur Urol. 2006 Nov;50(5):1014-20. doi: 10.1016/j.eururo.2006.04.011. Epub 2006 May 2.
OBJECTIVE
The pro-forms of prostate specific antigen (-2,-5,-7 proPSA) and also %free PSA based artificial neural networks (ANN) have been suggested to enhance the discrimination between prostate cancer (PCa) and no evidence of malignancy (NEM). This study reports on the combined use of proPSA within a %free PSA based ANN to enhance specificity of PCa.
METHODS
Serum samples from 898 patients with PCa (n=384) or NEM (n=514) within the PSA range 1-10 microg/l were analyzed for PSA, free PSA and (-5,-7) proPSA (Roche assays). Patient data from two centers - taken first from the Swiss site of the ERSPC (Aarau) and from a referral population (Berlin) have been analyzed. Leave-one-out ANN models with the variables PSA, %fPSA, proPSA, prostate volume and status of digital rectal examination (DRE) were constructed and compared by receiver-operating characteristic (ROC) curve analysis.
RESULTS
(-5,-7) proPSA was only significantly different between NEM and PCa in the PSA range 4-10 microg/l. Within the PSA range 4-10 microg/l (Berlin group) the ANN including only the two variables %fPSA and proPSA could reach the same performance like the conventional ANN with PSA, %fPSA, age, prostate volume and DRE (both AUCs: 0.84) However, at 95% sensitivity all ANN could not improve specificity compared to %fPSA.
CONCLUSIONS
ProPSA as single parameter did not improve specificity over %fPSA whereas proPSA and %fPSA within an ANN in the PSA range 4-10 microg/l substituted prostate volume and DRE. At 95% sensitivity only ANN with prostate volume and DRE perform significantly better than %fPSA.
目的
前列腺特异性抗原的前体形式（-2、-5、-7 前列腺特异性抗原）以及基于游离前列腺特异性抗原百分比的人工神经网络（ANN）已被建议用于增强前列腺癌（PCa）与无恶性证据（NEM）之间的鉴别能力。本研究报告了在基于游离前列腺特异性抗原百分比的人工神经网络中联合使用前列腺特异性抗原前体以提高前列腺癌的特异性。
方法
对 898 例 PSA 范围在 1 - 10μg/L 的 PCa 患者（n = 384）或 NEM 患者（n = 514）的血清样本进行 PSA、游离 PSA 和（-5、-7）前列腺特异性抗原前体（罗氏检测法）分析。来自两个中心的患者数据——首先取自欧洲前列腺癌筛查随机对照试验（ERSPC）瑞士站点（阿劳）以及一个转诊人群（柏林）的数据进行了分析。构建了包含 PSA、游离 PSA 百分比、前列腺特异性抗原前体、前列腺体积和直肠指检（DRE）状态等变量的留一法人工神经网络模型，并通过受试者操作特征（ROC）曲线分析进行比较。
结果
在 PSA 范围 4 - 10μg/L 时，NEM 与 PCa 之间仅（-5、-7）前列腺特异性抗原前体存在显著差异。在 PSA 范围 4 - 10μg/L（柏林组）内，仅包含游离 PSA 百分比和前列腺特异性抗原前体这两个变量的人工神经网络能够达到与包含 PSA、游离 PSA 百分比、年龄、前列腺体积和 DRE 的传统人工神经网络相同的性能（两者 AUC 均为 0.84）。然而，在 95%敏感性时，与游离 PSA 百分比相比，所有人工神经网络均未提高特异性。
结论
前列腺特异性抗原前体作为单一参数在特异性方面并未优于游离 PSA 百分比，而在 PSA 范围 4 - 10μg/L 内，人工神经网络中的前列腺特异性抗原前体和游离 PSA 百分比可替代前列腺体积和 DRE。在 95%敏感性时，仅包含前列腺体积和 DRE 的人工神经网络的表现明显优于游离 PSA 百分比。
Zotero 插件