Department of Colorectal Surgery, National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital, Chinese Academy of Medical Sciences and Peking Union Medical College, Beijing.
Department of Colorectal Surgery, Changhai Hospital, Naval Medical University, Shanghai.
Int J Surg. 2023 Mar 1;109(3):255-265. doi: 10.1097/JS9.0000000000000067.
Although the surgical treatment strategy for rectal cancer (RC) is usually based on the preoperative diagnosis of lymph node metastasis (LNM), the accurate diagnosis of LNM has been a clinical challenge. In this study, we developed machine learning (ML) models to predict the LNM status before surgery based on a privacy-preserving computing platform (PPCP) and created a web tool to help clinicians with treatment-based decision-making in RC patients.
A total of 6578 RC patients were enrolled in this study. ML models, including logistic regression, support vector machine, extreme gradient boosting (XGB), and random forest, were used to establish the prediction models. The areas under the receiver operating characteristic curves (AUCs) were calculated to compare the accuracy of the ML models with the US guidelines and clinical diagnosis of LNM. Last, model establishment and validation were performed in the PPCP without the exchange of raw data among different institutions.
LNM was detected in 1006 (35.3%), 252 (35.3%), 581 (32.9%), and 342 (27.4%) RC patients in the training, test, and external validation sets 1 and 2, respectively. The XGB model identified the optimal model with an AUC of 0.84 [95% confidence interval (CI), 0.83-0.86] compared with the logistic regression model (AUC, 0.76; 95% CI, 0.74-0.78), random forest model (AUC, 0.82; 95% CI, 0.81-0.84), and support vector machine model (AUC, 0.79; 95% CI, 0.78-0.81). Furthermore, the XGB model showed higher accuracy than the predictive factors of the US guidelines and clinical diagnosis. The predictive XGB model was embedded in a web tool (named LN-MASTER) to predict the LNM status for RC.
The proposed easy-to-use model showed good performance for LNM prediction, and the web tool can help clinicians make treatment-based decisions for patients with RC. Furthermore, PPCP enables state-of-the-art model development despite the limited local data availability.
尽管直肠癌（RC）的手术治疗策略通常基于术前淋巴结转移（LNM）的诊断，但准确诊断 LNM 一直是临床挑战。在这项研究中，我们开发了机器学习（ML）模型，基于隐私保护计算平台（PPCP）预测术前 LNM 状态，并创建了一个网络工具，以帮助 RC 患者的临床医生进行基于治疗的决策。
共纳入 6578 例 RC 患者。使用逻辑回归、支持向量机、极端梯度增强（XGB）和随机森林等 ML 模型建立预测模型。计算受试者工作特征曲线下的面积（AUC），以比较 ML 模型与美国指南和 LNM 临床诊断的准确性。最后，在没有不同机构之间原始数据交换的 PPCP 中进行模型建立和验证。
在训练集、测试集和外部验证集 1 和 2 中，分别有 1006（35.3%）、252（35.3%）、581（32.9%）和 342（27.4%）例 RC 患者检测到 LNM。XGB 模型的 AUC 为 0.84[95%置信区间（CI）：0.83-0.86]，优于逻辑回归模型（AUC：0.76；95%CI：0.74-0.78）、随机森林模型（AUC：0.82；95%CI：0.81-0.84）和支持向量机模型（AUC：0.79；95%CI：0.78-0.81）。此外，XGB 模型的准确性高于美国指南的预测因素和临床诊断。预测 XGB 模型被嵌入到一个网络工具（命名为 LN-MASTER）中，用于预测 RC 的 LNM 状态。
所提出的易于使用的模型在 LNM 预测方面表现出良好的性能，该网络工具可以帮助临床医生为 RC 患者做出基于治疗的决策。此外，尽管局部数据有限，PPCP 仍可实现最先进的模型开发。
