Department of Urology, University of Rennes 1, Rennes, France; LTSI, Inserm U1099, Université de Rennes 1, Rennes, France.
Department of Urology, University of Angers, Angers, France.
Eur Urol Oncol. 2023 Jun;6(3):323-330. doi: 10.1016/j.euo.2022.07.007. Epub 2022 Aug 18.
Predictive tools can be useful for adapting surveillance or including patients in adjuvant trials after surgical resection of nonmetastatic renal cell carcinoma (RCC). Current models have been built using traditional statistical modelling and prespecified variables, which limits their performance.
To investigate the performance of machine learning (ML) framework to predict recurrence after RCC surgery and compare them with current validated models.
DESIGN, SETTING, AND PARTICIPANTS: In this observational study, we derived and tested several ML-based models (Random Survival Forests [RSF], Survival Support Vector Machines [S-SVM], and Extreme Gradient Boosting [XG boost]) to predict recurrence of patients who underwent radical or partial nephrectomy for a nonmetastatic RCC, between 2013 and 2020, at 21 French medical centres.
The primary end point was disease-free survival. Model discrimination was assessed using the concordance index (c-index), and calibration was assessed using the Brier score. ML models were compared with four conventional prognostic models, using decision curve analysis (DCA).
A total of 4067 patients were included in this study (3253 in the development cohort and 814 in the validation cohort). Most tumours (69%) were clear cell RCC, 40% were of high grade (nuclear International Society of Urological Pathology grade 3 or 4), and 24% had necrosis. Of the patients, 4% had nodal involvement. After a median follow-up of 57 mo (interquartile range 29-76), 523 (13%) patients recurred. ML models obtained higher c-index values than conventional models. The RSF yielded the highest c-index values (0.794), followed by S-SVM (c-index 0.784) and XG boost (c-index 0.782). In addition, all models showed good calibration with low integrated Brier scores (all integrated brier scores <0.1). However, we found calibration drift over time for all models, albeit with a smaller magnitude for ML models. Finally, DCA showed an incremental net benefit from all ML models compared with conventional models currently used in practice.
Applying ML approaches to predict recurrence following surgical resection of RCC resulted in better prediction than that of current validated models available in clinical practice. However, there is still room for improvement, which may come from the integration of novel biological and/or imaging biomarkers.
We found that artificial intelligence algorithms could better predict the risk of recurrence after surgery for a localised kidney cancer. These algorithms may help better select patients who will benefit from medical treatment after surgery.
预测工具对于适应非转移性肾细胞癌（RCC）手术后的监测或将患者纳入辅助试验可能很有用。目前的模型是使用传统的统计建模和预设变量构建的，这限制了它们的性能。
研究机器学习（ML）框架预测 RCC 手术后复发的性能，并将其与当前验证的模型进行比较。
设计、设置和参与者：在这项观察性研究中，我们从 2013 年至 2020 年在 21 家法国医疗中心，为接受根治性或部分肾切除术治疗非转移性 RCC 的患者，开发和测试了几种基于 ML 的模型（随机生存森林[RSF]、生存支持向量机[S-SVM]和极端梯度增强[XG boost]）来预测患者的复发情况。
主要终点是无病生存率。使用一致性指数（c-index）评估模型的判别能力，并使用 Brier 评分评估校准。使用决策曲线分析（DCA）比较 ML 模型与四种传统预后模型。
本研究共纳入 4067 例患者（开发队列 3253 例，验证队列 814 例）。大多数肿瘤（69%）为透明细胞 RCC，40%为高级别（核国际泌尿病理学会 3 级或 4 级），24%有坏死。患者中有 4%有淋巴结受累。中位随访 57 个月（四分位距 29-76）后，523 例（13%）患者复发。ML 模型获得的 c-index 值高于传统模型。RSF 获得的 c-index 值最高（0.794），其次是 S-SVM（c-index 0.784）和 XG boost（c-index 0.782）。此外，所有模型的集成 Brier 评分均较低（均<0.1），表明校准良好。然而，我们发现所有模型都存在随时间推移的校准漂移，尽管 ML 模型的幅度较小。最后，DCA 显示与目前临床实践中使用的传统模型相比，所有 ML 模型均具有增量净获益。
应用 ML 方法预测 RCC 手术后的复发，其预测效果优于目前临床实践中可用的验证模型。然而，仍有改进的空间，这可能来自于新型生物学和/或影像学生物标志物的整合。
我们发现人工智能算法可以更好地预测局部肾细胞癌手术后的复发风险。这些算法可能有助于更好地选择术后将从治疗中受益的患者。
