Medical School of Chinese PLA, Beijing, China.
Department of Otolaryngology Head and Neck Surgery, The First Medical Centre of Chinese PLA General Hospital, Beijing, China.
Front Endocrinol (Lausanne). 2022 Oct 10;13:1019037. doi: 10.3389/fendo.2022.1019037. eCollection 2022.
To develop a web-based machine learning server to predict lateral lymph node metastasis (LLNM) in papillary thyroid cancer (PTC) patients.
Clinical data for PTC patients who underwent primary thyroidectomy at our hospital between January 2015 and December 2020, with pathologically confirmed presence or absence of any LLNM finding, were retrospectively reviewed. We built all models from a training set (80%) and assessed them in a test set (20%), using algorithms including decision tree, XGBoost, random forest, support vector machine, neural network, and K-nearest neighbor algorithm. Their performance was measured against a previously established nomogram using area under the receiver operating characteristic curve (AUC), decision curve analysis (DCA), precision, recall, accuracy, F1 score, specificity, and sensitivity. Interpretable machine learning was used for identifying potential relationships between variables and LLNM, and a web-based tool was created for use by clinicians.
A total of 1135 (62.53%) out of 1815 PTC patients enrolled in this study experienced LLNM episodes. In predicting LLNM, the best algorithm was random forest. In determining feature importance, the AUC reached 0.80, with an accuracy of 0.74, sensitivity of 0.89, and F1 score of 0.81. In addition, DCA showed that random forest held a higher clinical net benefit. Random forest identified tumor size, lymph node microcalcification, age, lymph node size, and tumor location as the most influentials in predicting LLNM. And the website tool is freely accessible at http://43.138.62.202/.
The results showed that machine learning can be used to enable accurate prediction for LLNM in PTC patients, and that the web tool allowed for LLNM risk assessment at the individual level.
开发一个基于网络的机器学习服务器，以预测甲状腺乳头状癌（PTC）患者的侧颈部淋巴结转移（LLNM）。
回顾性分析 2015 年 1 月至 2020 年 12 月在我院接受原发性甲状腺切除术的 PTC 患者的临床资料，病理证实有或无任何 LLNM 发现。我们使用决策树、XGBoost、随机森林、支持向量机、神经网络和 K 最近邻算法等算法，从训练集（80%）中构建所有模型，并在测试集（20%）中进行评估。我们使用受试者工作特征曲线下面积（AUC）、决策曲线分析（DCA）、精确率、召回率、准确率、F1 评分、特异性和敏感性等指标来衡量它们与之前建立的列线图的性能。我们还使用可解释的机器学习来识别变量与 LLNM 之间的潜在关系，并创建了一个基于网络的工具供临床医生使用。
本研究共纳入 1815 例 PTC 患者，其中 1135 例（62.53%）发生了 LLNM。在预测 LLNM 方面，最好的算法是随机森林。在确定特征重要性方面，AUC 达到 0.80，准确率为 0.74，敏感度为 0.89，F1 得分为 0.81。此外，DCA 显示随机森林具有更高的临床净收益。随机森林确定肿瘤大小、淋巴结微钙化、年龄、淋巴结大小和肿瘤位置是预测 LLNM 的最主要因素。该网站工具可在 http://43.138.62.202/ 免费访问。
研究结果表明，机器学习可用于准确预测 PTC 患者的 LLNM，该网站工具可用于个体水平的 LLNM 风险评估。
