Division of Surgical Oncology, Department of Surgery, The Ohio State University Wexner Medical Center and James Comprehensive Cancer Center, Columbus, OH, USA.
Department of Surgery, University of Verona, Verona, Italy.
Ann Surg Oncol. 2023 Sep;30(9):5406-5415. doi: 10.1245/s10434-023-13636-8. Epub 2023 May 20.
The high incidence of early recurrence after hepatectomy for intrahepatic cholangiocarcinoma (ICC) has a detrimental effect on overall survival (OS). Machine-learning models may improve the accuracy of outcome prediction for malignancies.
Patients who underwent curative-intent hepatectomy for ICC were identified using an international database. Three machine-learning models were trained to predict early recurrence (< 12 months after hepatectomy) using 14 clinicopathologic characteristics. The area under the receiver operating curve (AUC) was used to assess their discrimination ability.
In this study, 536 patients were randomly assigned to training (n = 376, 70.1%) and testing (n = 160, 29.9%) cohorts. Overall, 270 (50.4%) patients experienced early recurrence (training: n = 150 [50.3%] vs testing: n = 81 [50.6%]), with a median tumor burden score (TBS) of 5.6 (training: 5.8 [interquartile range {IQR}, 4.1-8.1] vs testing: 5.5 [IQR, 3.7-7.9]) and metastatic/undetermined nodes (N1/NX) in the majority of the patients (training: n = 282 [75.0%] vs testing n = 118 [73.8%]). Among the three different machine-learning algorithms, random forest (RF) demonstrated the highest discrimination in the training/testing cohorts (RF [AUC, 0.904/0.779] vs support vector machine [AUC, 0.671/0.746] vs logistic regression [AUC, 0.668/0.745]). The five most influential variables in the final model were TBS, perineural invasion, microvascular invasion, CA 19-9 lower than 200 U/mL, and N1/NX disease. The RF model successfully stratified OS relative to the risk of early recurrence.
Machine-learning prediction of early recurrence after ICC resection may inform tailored counseling, treatment, and recommendations. An easy-to-use calculator based on the RF model was developed and made available online.
肝内胆管癌（ICC）患者行肝切除术后早期复发的发生率较高，这对总体生存（OS）有不利影响。机器学习模型可能会提高恶性肿瘤预后预测的准确性。
使用国际数据库确定接受根治性肝切除术治疗 ICC 的患者。使用 14 种临床病理特征，训练三种机器学习模型来预测早期复发（肝切除术后<12 个月）。使用接受者操作特征曲线下的面积（AUC）评估其鉴别能力。
本研究中，536 名患者被随机分配到训练（n=376，70.1%）和测试（n=160，29.9%）队列。总体而言，270 名（50.4%）患者发生早期复发（训练：n=150[50.3%] vs 测试：n=81[50.6%]），肿瘤负担评分（TBS）中位数为 5.6（训练：5.8 [四分位距 {IQR}，4.1-8.1] vs 测试：5.5 [IQR，3.7-7.9]），且大多数患者存在转移性/不确定的淋巴结（N1/NX）（训练：n=282[75.0%] vs 测试：n=118[73.8%]）。在三种不同的机器学习算法中，随机森林（RF）在训练/测试队列中的鉴别能力最高（RF[AUC，0.904/0.779] vs 支持向量机[AUC，0.671/0.746] vs 逻辑回归[AUC，0.668/0.745]）。最终模型中五个最具影响力的变量是 TBS、神经周围侵犯、微血管侵犯、CA19-9 低于 200 U/mL 和 N1/NX 疾病。RF 模型成功地根据早期复发的风险对 OS 进行了分层。
ICC 切除术后早期复发的机器学习预测可能有助于提供有针对性的咨询、治疗和建议。基于 RF 模型开发了一个易于使用的计算器，并在网上提供。
