Department of Radiation Oncology, University of California-San Francisco, San Francisco, CA, USA.
Department of Urology, University of California-San Francisco, San Francisco, CA, USA; Department of Epidemiology and Biostatistics, University of California-San Francisco, San Francisco, CA, USA.
Eur Urol Oncol. 2023 Oct;6(5):501-507. doi: 10.1016/j.euo.2023.02.006. Epub 2023 Mar 1.
Pelvic lymph node dissection (PLND) is the gold standard for diagnosis of lymph node involvement (LNI) in patients with prostate cancer. The Roach formula, Memorial Sloan Kettering Cancer Center (MSKCC) calculator, and Briganti 2012 nomogram are elegant and simple traditional tools used to estimate the risk of LNI and select patients for PLND.
To determine whether machine learning (ML) can improve patient selection and outperform currently available tools for predicting LNI using similar readily available clinicopathologic variables.
DESIGN, SETTING, AND PARTICIPANTS: Retrospective data for patients treated with surgery and PLND between 1990 and 2020 in two academic institutions were used.
We trained three models (two logistic regression models and one gradient-boosted trees-based model [XGBoost]) on data provided from one institution (n = 20267) with age, prostate-specific antigen (PSA) levels, clinical T stage, percentage positive cores, and Gleason scores as inputs. We externally validated these models using data from another institution (n = 1322) and compared their performance to that of the traditional models using the area under the receiver operating characteristic curve (AUC), calibration, and decision curve analysis (DCA).
LNI was present in 2563 patients (11.9%) overall, and in 119 patients (9%) in the validation data set. XGBoost had the best performance among all the models. On external validation, its AUC outperformed that of the Roach formula by 0.08 (95% confidence interval [CI] 0.042-0.12), the MSKCC nomogram by 0.05 (95% CI 0.016-0.070), and the Briganti nomogram by 0.03 (95% CI 0.0092-0.051; all p < 0.05). It also had better calibration and clinical utility in terms of net benefit on DCA across relevant clinical thresholds. The main limitation of the study is its retrospective design.
Taking all measures of performance together, ML using standard clinicopathologic variables outperforms traditional tools in predicting LNI.
Determining the risk of cancer spread to the lymph nodes in patients with prostate cancer allows surgeons to perform lymph node dissection only in patients who need it and avoid the side effects of the procedure in those who do not. In this study, we used machine learning to develop a new calculator to predict the risk of lymph node involvement that outperformed traditional tools currently used by oncologists.
盆腔淋巴结清扫术（PLND）是诊断前列腺癌患者淋巴结受累（LNI）的金标准。Roach 公式、纪念斯隆凯特琳癌症中心（MSKCC）计算器和 Briganti 2012 列线图是用于估计 LNI 风险和选择 PLND 患者的优雅而简单的传统工具。
确定机器学习（ML）是否可以通过使用类似的现成临床病理变量来改善患者选择，并优于目前可用的预测 LNI 的工具。
设计、设置和参与者：使用 1990 年至 2020 年间在两个学术机构接受手术和 PLND 治疗的患者的回顾性数据。
我们使用来自一个机构（n=20267）的数据训练了三个模型（两个逻辑回归模型和一个基于梯度增强树的模型 [XGBoost]），输入为年龄、前列腺特异性抗原（PSA）水平、临床 T 期、阳性核心百分比和 Gleason 评分。我们使用另一个机构（n=1322）的数据对这些模型进行了外部验证，并使用受试者工作特征曲线下面积（AUC）、校准和决策曲线分析（DCA）来比较它们与传统模型的性能。
总体而言，2563 名患者（11.9%）存在 LNI，验证数据集中有 119 名患者（9%）。XGBoost 在所有模型中表现最好。在外部验证中，其 AUC 比 Roach 公式高 0.08（95%置信区间 [CI] 0.042-0.12），比 MSKCC 列线图高 0.05（95% CI 0.016-0.070），比 Briganti 列线图高 0.03（95% CI 0.0092-0.051；所有 p<0.05）。它在 DCA 方面也具有更好的校准和临床实用性，在相关临床阈值方面具有净收益。研究的主要限制是其回顾性设计。
综合所有性能指标，使用标准临床病理变量的机器学习在预测 LNI 方面优于传统工具。
确定前列腺癌患者癌症扩散到淋巴结的风险可以使外科医生仅在需要的患者中进行淋巴结清扫，并避免在不需要的患者中进行该手术的副作用。在这项研究中，我们使用机器学习开发了一种新的计算器来预测淋巴结受累的风险，该计算器优于肿瘤学家目前使用的传统工具。
