Department of Radiology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, Jiangsu Province, China.
Department of Pathology, The First Affiliated Hospital with Nanjing Medical University, Nanjing, Jiangsu Province, China.
BJU Int. 2019 Dec;124(6):972-983. doi: 10.1111/bju.14892. Epub 2019 Aug 28.
To develop a machine learning (ML)-assisted model to identify candidates for extended pelvic lymph node dissection (ePLND) in prostate cancer by integrating clinical, biopsy, and precisely defined magnetic resonance imaging (MRI) findings.
In all, 248 patients treated with radical prostatectomy and ePLND or PLND were included. ML-assisted models were developed from 18 integrated features using logistic regression (LR), support vector machine (SVM), and random forests (RFs). The models were compared to the Memorial SloanKettering Cancer Center (MSKCC) nomogram using receiver operating characteristic-derived area under the curve (AUC) calibration plots and decision curve analysis (DCA).
A total of 59/248 (23.8%) lymph node invasions (LNIs) were identified at surgery. The predictive accuracy of the ML-based models, with (+) or without (-) MRI-reported LNI, yielded similar AUCs (RFs /RFs : 0.906/0.885; SVM /SVM : 0.891/0.868; LR /LR : 0.886/0.882) and were higher than the MSKCC nomogram (0.816; P < 0.001). The calibration of the MSKCC nomogram tended to underestimate LNI risk across the entire range of predicted probabilities compared to the ML-assisted models. The DCA showed that the ML-assisted models significantly improved risk prediction at a risk threshold of ≤80% compared to the MSKCC nomogram. If ePLNDs missed was controlled at <3%, both RFs and RFs resulted in a higher positive predictive value (51.4%/49.6% vs 40.3%), similar negative predictive value (97.2%/97.8% vs 97.2%), and higher number of ePLNDs spared (56.9%/54.4% vs 43.9%) compared to the MSKCC nomogram.
Our ML-based model, with a 5-15% cutoff, is superior to the MSKCC nomogram, sparing ≥50% of ePLNDs with a risk of missing <3% of LNIs.
通过整合临床、活检和精确定义的磁共振成像（MRI）发现，开发一种机器学习（ML）辅助模型，以识别前列腺癌扩大盆腔淋巴结清扫术（ePLND）的候选者。
共纳入 248 例接受根治性前列腺切除术和 ePLND 或 PLND 的患者。使用逻辑回归（LR）、支持向量机（SVM）和随机森林（RFs）从 18 个综合特征中开发 ML 辅助模型。使用接受者操作特征曲线（AUC）校准图和决策曲线分析（DCA）将模型与 Memorial SloanKettering Cancer Center（MSKCC）列线图进行比较。
手术中共发现 59/248（23.8%）淋巴结浸润（LNI）。基于 ML 的模型（有（+）或无（-）MRI 报告的 LNI）的预测准确性具有相似的 AUC（RFs /RFs：0.906/0.885；SVM /SVM：0.891/0.868；LR /LR：0.886/0.882），并且高于 MSKCC 列线图（0.816；P<0.001）。与 ML 辅助模型相比，MSKCC 列线图的校准倾向于低估整个预测概率范围内的 LNI 风险。DCA 表明，与 MSKCC 列线图相比，ML 辅助模型在≤80%的风险阈值下显著改善了风险预测。如果控制 ePLND 漏诊率<3%，则 RFs 和 RFs 均导致更高的阳性预测值（51.4%/49.6%比 40.3%）、相似的阴性预测值（97.2%/97.8%比 97.2%）和更高的 ePLND 节省数量（56.9%/54.4%比 43.9%）。
我们的基于 ML 的模型，使用 5-15%的截止值，优于 MSKCC 列线图，可以在 LNIs 漏诊风险<3%的情况下，节省≥50%的 ePLND。
