Chen Sunmeng, Jian Tengteng, Chi Changliang, Liang Yi, Liang Xiao, Yu Ying, Jiang Fengming, Lu Ji
Department of Urology, The First Hospital of Jilin University, Changchun, China.
School of Business and Management, Jilin University, Changchun, China.
Front Oncol. 2022 Jul 6;12:941349. doi: 10.3389/fonc.2022.941349. eCollection 2022.
PSA is currently the most commonly used screening indicator for prostate cancer. However, it has limited specificity for the diagnosis of prostate cancer. We aim to construct machine learning-based models and enhance the prediction of prostate cancer.
The data of 551 patients who underwent prostate biopsy were retrospectively retrieved and divided into training and test datasets in a 3:1 ratio. We constructed five PCa prediction models with four supervised machine learning algorithms, including tPSA univariate logistic regression (LR), multivariate LR, decision tree (DT), random forest (RF), and support vector machine (SVM). The five prediction models were compared based on model performance metrics, such as the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, specificity, calibration curve, and clinical decision curve analysis (DCA).
All five models had good calibration in the training dataset. In the training dataset, the RF, DT, and multivariate LR models showed better discrimination, with AUCs of 1.0, 0.922 and 0.91, respectively, than the tPSA univariate LR and SVM models. In the test dataset, the multivariate LR model exhibited the best discrimination (AUC=0.918). The multivariate LR model and SVM model had better extrapolation and generalizability, with little change in performance between the training and test datasets. Compared with the DCA curves of the tPSA LR model, the other four models exhibited better net clinical benefits.
The results of the current retrospective study suggest that machine learning techniques can predict prostate cancer with significantly better AUC, accuracy, and net clinical benefits.
前列腺特异性抗原（PSA）是目前前列腺癌最常用的筛查指标。然而，其对前列腺癌诊断的特异性有限。我们旨在构建基于机器学习的模型，提高前列腺癌的预测能力。
回顾性收集551例接受前列腺活检患者的数据，并按3:1的比例分为训练集和测试集。我们使用四种监督式机器学习算法构建了五个前列腺癌预测模型，包括总PSA（tPSA）单变量逻辑回归（LR）、多变量LR、决策树（DT）、随机森林（RF）和支持向量机（SVM）。基于受试者工作特征曲线下面积（AUC）、准确率、灵敏度、特异性、校准曲线和临床决策曲线分析（DCA）等模型性能指标对这五个预测模型进行比较。
所有五个模型在训练集中均具有良好的校准。在训练集中，RF、DT和多变量LR模型显示出更好的区分能力，AUC分别为1.0、0.922和0.91，优于tPSA单变量LR和SVM模型。在测试集中，多变量LR模型表现出最佳的区分能力（AUC = 0.918）。多变量LR模型和SVM模型具有更好的外推性和泛化能力，训练集和测试集之间的性能变化很小。与tPSA LR模型的DCA曲线相比，其他四个模型表现出更好的净临床效益。
当前回顾性研究结果表明，机器学习技术能够以显著更好的AUC、准确率和净临床效益来预测前列腺癌。
