Kawashima Jun, Endo Yutaka, Rashid Zayed, Altaf Abdullah, Woldesenbet Selamawit, Tsilimigras Diamantis I, Guglielmi Alfredo, Marques Hugo P, Maithel Shishir K, Groot Koerkamp Bas, Pulitano Carlo, Aucejo Federico, Endo Itaru, Pawlik Timothy M
Department of Surgery, The Ohio State University Wexner Medical Center and James Comprehensive Cancer Center, Columbus, OH, USA.
Department of Gastroenterological Surgery, Yokohama City University School of Medicine, Yokohama, Japan.
Hepatobiliary Surg Nutr. 2025 Feb 1;14(1):3-15. doi: 10.21037/hbsn-24-385. Epub 2025 Jan 16.
Although offering the best chance of potential cure for patients with localized perihilar cholangiocarcinoma (pCCA), resection has been associated with high morbidity and sometimes poor long-term outcomes due to recurrence. We sought to develop a predictive model to identify individuals at high risk for very early recurrence (VER) after curative-intent surgery for pCCA.
Patients who underwent curative-intent surgery for pCCA between 2000-2023 were identified from a multi-institutional database. An eXtreme Gradient Boosting (XGBoost) model was developed to estimate the risk of VER, defined as recurrence within 6 months after resection. The relative importance of clinicopathologic factors was determined using SHapley Additive exPlanations (SHAP) values.
Among 434 patients undergoing curative-intent resection for pCCA, 65 (15.0%) patients developed VER. Median overall survival (OS) among patients with and without VER was 8.4 [interquartile range (IQR) 6.6-11.3] versus 38.5 (IQR 31.9-45.7) months (P<0.001). An XGBoost model was able to stratify patients relative to the risk of VER [low-risk: 6-month recurrence-free survival (RFS) 94.6% intermediate-risk: 6-month RFS 88.3% high-risk: 6-month RFS 40.0%; P<0.001]. Similarly, 3-year OS incrementally worsened based on VER risk (low-risk: 75.3% intermediate-risk: 19.5% high-risk: 4.6%; P<0.001). The SHAP algorithm identified age, preoperative carbohydrate antigen 19-9 (CA19-9) levels, tumor size and differentiation/grade, as well as lymph node metastasis as the five most important predictors of VER. The predictive accuracy of the model was good in the training [c-index: 0.74, 95% confidence interval (CI): 0.67-0.81] and internal validation (c-index: 0.77, 95% CI: 0.71-0.83) cohorts. An easy-to-use risk calculator for VER was developed and made available online at: https://junkawashima.shinyapps.io/VER_hilar/.
A novel, machine learning based model was able to predict accurately the chance of VER after curative-intent resection of pCCA. In turn, the tool may help surgeons in the selection of patients likely to benefit the most from resection, as well as counsel individuals about the anticipated risk of recurrence in the early post-operative period.
尽管手术切除为局限性肝门部胆管癌（pCCA）患者提供了潜在治愈的最佳机会，但由于复发，手术切除一直伴随着高发病率，有时长期预后也较差。我们试图开发一种预测模型，以识别pCCA根治性手术后极早期复发（VER）高危个体。
从多机构数据库中识别出2000年至2023年间接受pCCA根治性手术的患者。开发了一种极端梯度提升（XGBoost）模型来估计VER风险，定义为切除后6个月内复发。使用SHapley加性解释（SHAP）值确定临床病理因素的相对重要性。
在434例接受pCCA根治性切除的患者中，65例（15.0%）发生VER。发生VER和未发生VER的患者中位总生存期（OS）分别为8.4[四分位间距（IQR）6.6 - 11.3]个月和38.5（IQR 31.9 - 45.7）个月（P<0.001）。XGBoost模型能够根据VER风险对患者进行分层[低风险：6个月无复发生存率（RFS）94.6%；中风险：6个月RFS 88.3%；高风险：6个月RFS 40.0%；P<0.001]。同样，基于VER风险，3年OS逐渐变差（低风险：75.3%；中风险：19.5%；高风险：4.6%；P<0.001）。SHAP算法确定年龄、术前糖类抗原19 - 9（CA19 - 9）水平、肿瘤大小和分化/分级以及淋巴结转移是VER的五个最重要预测因素。该模型在训练队列[c指数：0.74，95%置信区间（CI）：0.67 - 0.81]和内部验证队列（c指数：0.77，95% CI：0.71 - 0.83）中的预测准确性良好。开发了一个易于使用的VER风险计算器，并在网上提供：https://junkawashima.shinyapps.io/VER_hilar/。
一种基于机器学习的新型模型能够准确预测pCCA根治性切除术后VER的可能性。反过来，该工具可能有助于外科医生选择最有可能从切除中获益的患者，并为个体提供术后早期预期复发风险的咨询。
