Department of Urology, The First Affiliated Hospital of Zhengzhou University, No. 1 Jianshe East Road, Zhengzhou, 450052, China.
Key Laboratory of Precision Diagnosis and Treatment for Chronic Kidney Disease in Henan Province, Zhengzhou, 450052, China.
BMC Urol. 2021 May 16;21(1):80. doi: 10.1186/s12894-021-00849-w.
Machine learning has many attractive theoretic properties, specifically, the ability to handle non predefined relations. Additionally, studies have validated the clinical utility of mpMRI for the detection and localization of CSPCa (Gleason score ≥ 3 + 4). In this study, we sought to develop and compare machine-learning models incorporating mpMRI parameters with traditional logistic regression analysis for prediction of PCa (Gleason score ≥ 3 + 3) and CSPCa on initial biopsy.
A total of 688 patients with no prior prostate cancer diagnosis and tPSA ≤ 50 ng/ml, who underwent mpMRI and prostate biopsy were included between 2016 and 2020. We used four supervised machine-learning algorithms in a hypothesis-free manner to build models to predict PCa and CSPCa. The machine-learning models were compared to the logistic regression analysis using AUC, calibration plot, and decision curve analysis.
The artificial neural network (ANN), support vector machine (SVM), and random forest (RF) yielded similar diagnostic accuracy with logistic regression, while classification and regression tree (CART, AUC = 0.834 and 0.867) had significantly lower diagnostic accuracy than logistic regression (AUC = 0.894 and 0.917) in prediction of PCa and CSPCa (all P < 0.05). However, the CART illustrated best calibration for PCa (SSR = 0.027) and CSPCa (SSR = 0.033). The ANN, SVM, RF, and LR for PCa had higher net benefit than CART across the threshold probabilities above 5%, and the five models for CSPCa displayed similar net benefit across the threshold probabilities below 40%. The RF (53% and 57%, respectively) and SVM (52% and 55%, respectively) for PCa and CSPCa spared more unnecessary biopsies than logistic regression (35% and 47%, respectively) at 95% sensitivity for detection of CSPCa.
Machine-learning models (SVM and RF) yielded similar diagnostic accuracy and net benefit, while spared more biopsies at 95% sensitivity for detection of CSPCa, compared with logistic regression. However, no method achieved desired performance. All methods should continue to be explored and used in complementary ways.
机器学习具有许多吸引人的理论特性，特别是处理非预定义关系的能力。此外，研究已经验证了 mpMRI 在检测和定位 CSPCa（Gleason 评分≥3+4）方面的临床实用性。在这项研究中，我们试图开发并比较结合 mpMRI 参数的机器学习模型与传统逻辑回归分析，用于预测初始活检中的 PCa（Gleason 评分≥3+3）和 CSPCa。
共有 688 名无前列腺癌既往诊断且 tPSA≤50ng/ml 的患者于 2016 年至 2020 年间接受了 mpMRI 和前列腺活检。我们使用四种无假设的监督机器学习算法来建立预测 PCa 和 CSPCa 的模型。使用 AUC、校准图和决策曲线分析比较机器学习模型与逻辑回归分析。
人工神经网络（ANN）、支持向量机（SVM）和随机森林（RF）与逻辑回归的诊断准确性相似，而分类和回归树（CART，AUC=0.834 和 0.867）在预测 PCa 和 CSPCa 方面的诊断准确性明显低于逻辑回归（AUC=0.894 和 0.917）（均 P<0.05）。然而，CART 对 PCa（SSR=0.027）和 CSPCa（SSR=0.033）的校准效果最好。ANN、SVM、RF 和 LR 对 PCa 的净收益高于 CART 在阈值概率高于 5%的情况下，而五个 CSPCa 模型在阈值概率低于 40%的情况下具有相似的净收益。RF（分别为 53%和 57%）和 SVM（分别为 52%和 55%）对 PCa 和 CSPCa 而言，比逻辑回归（分别为 35%和 47%）具有更高的净收益，以 95%的 CSPCa 检测敏感性避免了更多不必要的活检。
与逻辑回归相比，机器学习模型（SVM 和 RF）在保持相似诊断准确性和净收益的同时，以 95%的 CSPCa 检测敏感性避免了更多不必要的活检。然而，没有一种方法达到了理想的性能。所有方法都应继续探索并以互补的方式使用。
