机器学习预测胆囊癌手术后早期复发。

Machine learning prediction of early recurrence after surgery for gallbladder cancer.

作者信息

Catalano Giovanni, Alaimo Laura, Chatzipanagiotou Odysseas P, Ruzzenente Andrea, Aucejo Federico, Marques Hugo P, Lam Vincent, Hugh Tom, Bhimani Nazim, Maithel Shishir K, Kitago Minoru, Endo Itaru, Pawlik Timothy M

机构信息

Department of Surgery, Ohio State University Wexner Medical Center and James Comprehensive Cancer Center, Columbus, Ohio, USA.

Department of Surgery, University of Verona, Verona, Italy.

出版信息

Br J Surg. 2024 Oct 30;111(11). doi: 10.1093/bjs/znae297.

DOI:10.1093/bjs/znae297

PMID:39569737

Abstract

BACKGROUND

Gallbladder cancer is often associated with poor prognosis, especially when patients experience early recurrence after surgery. Machine learning may improve prediction accuracy by analysing complex non-linear relationships. The aim of this study was to develop and evaluate a machine learning model to predict early recurrence risk after resection of gallbladder cancer.

METHODS

In this cross-sectional study, patients who underwent resection of gallbladder cancer with curative intent between 2001 and 2022 were identified using an international database. Patients were assigned randomly to a development and an evaluation cohort. Four machine learning models were trained to predict early recurrence (within 12 months) and compared using the area under the receiver operating curve (AUC).

RESULTS

Among 374 patients, 56 (15.0%) experienced early recurrence; most patients had T1 (51, 13.6%) or T2 (180, 48.1%) disease, and a subset had lymph node metastasis (120, 32.1%). In multivariable Cox analysis, resection margins (HR 2.34, 95% c.i. 1.55 to 3.80; P < 0.001), and greater AJCC T (HR 2.14, 1.41 to 3.25; P < 0.001) and N (HR 1.59, 1.05 to 2.42; P = 0.029) categories were independent predictors of early recurrence. The random forest model demonstrated the highest discrimination in the evaluation cohort (AUC 76.4, 95% c.i. 66.3 to 86.5), compared with XGBoost (AUC 74.4, 53.4 to 85.3), support vector machine (AUC 67.2, 54.4 to 80.0), and logistic regression (AUC 73.1, 60.6 to 85.7), as well as good accuracy after bootstrapping validation (AUC 75.3, 75.0 to 75.6). Patients classified as being at high versus low risk of early recurrence had much worse overall survival (36.1 versus 63.8% respectively; P < 0.001). An easy-to-use calculator was made available (https://catalano-giovanni.shinyapps.io/GallbladderER).

CONCLUSION

Machine learning-based prediction of early recurrence after resection of gallbladder cancer may help stratify patients, as well as help inform postoperative adjuvant therapy and surveillance strategies.

摘要

背景

胆囊癌常预后不良，尤其是在患者术后早期复发时。机器学习通过分析复杂的非线性关系可以提高预测准确性。本研究旨在开发和评估一种机器学习模型，以预测胆囊癌切除术后的早期复发风险。

方法

本回顾性研究使用国际数据库确定了 2001 年至 2022 年间接受胆囊癌根治性切除术的患者。将患者随机分配到开发队列和评估队列。使用接受者操作特征曲线下面积（AUC）比较了四种机器学习模型对早期复发（12 个月内）的预测效果。

结果

374 例患者中，56 例（15.0%）发生早期复发；大多数患者为 T1（51 例，13.6%）或 T2 期（180 例，48.1%），部分患者有淋巴结转移（120 例，32.1%）。多变量 Cox 分析显示，切缘（HR 2.34，95%CI 1.55 至 3.80；P < 0.001）和 AJCC 分期更高的 T 期（HR 2.14，1.41 至 3.25；P < 0.001）和 N 期（HR 1.59，1.05 至 2.42；P = 0.029）是早期复发的独立预测因素。随机森林模型在评估队列中的鉴别能力最高（AUC 76.4，95%CI 66.3 至 86.5），优于 XGBoost（AUC 74.4，53.4 至 85.3）、支持向量机（AUC 67.2，54.4 至 80.0）和逻辑回归（AUC 73.1，60.6 至 85.7），Bootstrap 验证后的准确性也较好（AUC 75.3，75.0 至 75.6）。高风险和低风险的早期复发患者的总体生存率差异很大（分别为 36.1%和 63.8%；P < 0.001）。我们还开发了一个易于使用的计算器（https://catalano-giovanni.shinyapps.io/GallbladderER）。