Advancing Traditional Prostate-specific Antigen Kinetics in the Detection of Prostate Cancer: A Machine Learning Model.
Advancing Traditional Prostate-specific Antigen Kinetics in the Detection of Prostate Cancer: A Machine Learning Model.
复制标题
DOI：
10.1016/j.euf.2021.11.009
复制
发表时间：
2022-09
影响因子：
5.4
通讯作者：
Smith, Elliot
中科院分区：
文献类型：
--
作者：
Perera, Marlon;Smith, Lewis;Thompson, Ian;Breemer, Geoff;Papa, Nathan;Patel, Manish I.;Swindle, Peter;Smith, Elliot
前列腺特异性抗原（PSA）动力学，定义为PSA随时间的变化，可用作前列腺癌的预测因子。PSA动力学可以被评估为PSA速度，其传统上被二分地评估并且如果大于0.35或0.75 ng/ml/yr则被分类为异常。机器学习模型可以在使用PSA动力学而不是PSA速度评估风险方面提供额外的益处。通过构建可推广的通用机器学习模型来提高PSA动力学的实用性。数据来自PLCO和PCPT试验以及当代澳大利亚队列。PSA数据使用修改的高斯过程进行内插。设计了一种基于双头方法的机器学习模型，其中多变量输入被馈送到一维ResNet 18模型中。根据受试者工作特征曲线下面积（AUC），评估模型性能与PSA水平和PSA速度的比较。共有10719例患者纳入分析。在对诊断分级组≥2的完整数据库的验证集进行的测试中，机器学习模型的AUC为0.886（95%置信区间[CI] 0.870-0.902），而PSA为0.807（95% CI 0.796-0.819），PSA速度为0.627（95% CI 0.607-0.648）。机器学习模型可用于增强PSA动力学在前列腺癌诊断中的诊断效用。与传统的PSA速度和PSA阈值方法相比，我们证明了准确性的显著提高。前列腺癌的诊断受到前列腺特异性抗原（PSA）血液测试的诊断准确性的限制。机器学习算法等技术的进步可以大大提高前列腺癌筛查的诊断准确性，而无需额外的成本或测试。
Prostate-specific antigen (PSA) kinetics, defined as the change in PSA over time, may be of use as a predictor of prostate cancer. PSA kinetics can be assessed as the PSA velocity, which is traditionally evaluated dichotomously and classified as abnormal if greater than either 0.35 or 0.75 ng/ml/yr. Machine learning models may provide additional benefit in assessing risk using PSA kinetics instead of PSA velocity. To improve the utility of PSA kinetics by constructing a generalizable, universal machine learning model. Data were obtained from the PLCO and PCPT trials and from a contemporary Australian cohort. PSA data were interpolated using a modified Gaussian process. A machine learning model based on a two-headed approach was designed, in which the multivariable input was fed into a one-dimensional ResNet18 model. The model performance was assessed compared to PSA levels and PSA velocity in terms of area under the receiver operator characteristic curve (AUC). A total of 10 719 patients were included in the analysis. In tests on a validation set of the complete database to diagnose grade group ≥2, the AUC was 0.886 (95% confidence interval [CI] 0.870–0.902) for the machine learning model, compared to 0.807 (95% CI 0.796–0.819) for PSA and 0.627 (95% CI 0.607–0.648) for PSA velocity. Machine learning models can be used to augment the diagnostic utility of PSA kinetics in the diagnosis of prostate cancer. We demonstrated significant improvements in accuracy compared to the traditional approaches of PSA velocity and PSA thresholds. Prostate cancer diagnosis is limited by the diagnostic accuracy of the prostate-specific antigen (PSA) blood test. Advances in techniques such as machine learning algorithms can greatly improve the diagnostic accuracy of prostate cancer screening without additional costs or tests.
登录
查看更多内容
影响因子：
6.2
作者：
Pinsky, Paul F.;Prorok, Philip C.;Andriole, Gerald L.
通讯作者：
Andriole, Gerald L.
影响因子：
2.8
作者：
Bruun, L;Becker, C;Christensson, A
通讯作者：
Christensson, A
影响因子：
4.5
作者：
Loeb, Stacy;Roehl, Kimberly A.;Nadler, Robert B.
通讯作者：
Nadler, Robert B.
影响因子：
4.8
作者：
Nixon, RG;Wener, MH;Brawer, MK
通讯作者：
Brawer, MK
影响因子：
3.4
作者：
Perera, Marlon;Mirchandani, Rohan;Smith, Elliot
通讯作者：
Smith, Elliot