Cancer Sciences Unit, University of Southampton, Southampton, UK.
Department of Surgery, University Medical Centre, Utrecht, the Netherlands.
Br J Surg. 2020 Jul;107(8):1042-1052. doi: 10.1002/bjs.11461. Epub 2020 Jan 30.
Early cancer recurrence after oesophagectomy is a common problem, with an incidence of 20-30 per cent despite the widespread use of neoadjuvant treatment. Quantification of this risk is difficult and existing models perform poorly. This study aimed to develop a predictive model for early recurrence after surgery for oesophageal adenocarcinoma using a large multinational cohort and machine learning approaches.
Consecutive patients who underwent oesophagectomy for adenocarcinoma and had neoadjuvant treatment in one Dutch and six UK oesophagogastric units were analysed. Using clinical characteristics and postoperative histopathology, models were generated using elastic net regression (ELR) and the machine learning methods random forest (RF) and extreme gradient boosting (XGB). Finally, a combined (ensemble) model of these was generated. The relative importance of factors to outcome was calculated as a percentage contribution to the model.
A total of 812 patients were included. The recurrence rate at less than 1 year was 29·1 per cent. All of the models demonstrated good discrimination. Internally validated areas under the receiver operating characteristic (ROC) curve (AUCs) were similar, with the ensemble model performing best (AUC 0·791 for ELR, 0·801 for RF, 0·804 for XGB, 0·805 for ensemble). Performance was similar when internal-external validation was used (validation across sites, AUC 0·804 for ensemble). In the final model, the most important variables were number of positive lymph nodes (25·7 per cent) and lymphovascular invasion (16·9 per cent).
The model derived using machine learning approaches and an international data set provided excellent performance in quantifying the risk of early recurrence after surgery, and will be useful in prognostication for clinicians and patients.
尽管新辅助治疗已广泛应用，但食管癌手术后早期复发仍是一个常见问题，其发生率为 20%-30%。这种风险的量化较为困难，且现有模型的表现不佳。本研究旨在使用大型跨国队列和机器学习方法，为食管腺癌手术后早期复发开发一种预测模型。
对在荷兰的一个和英国的六个胃肠病学单位接受新辅助治疗并接受食管癌切除术的连续患者进行了分析。使用临床特征和术后组织病理学，使用弹性网络回归（ELR）和机器学习方法随机森林（RF）和极端梯度提升（XGB）生成模型。最后，生成这些模型的组合（集成）模型。通过对模型的百分比贡献来计算结果的因素相对重要性。
共纳入 812 例患者。不到 1 年的复发率为 29.1%。所有模型均表现出良好的判别力。内部验证的接收者操作特征曲线下面积（AUCs）相似，集成模型表现最佳（ELR 的 AUC 为 0.791，RF 为 0.801，XGB 为 0.804，集成模型为 0.805）。当使用内部-外部验证时（跨站点验证，集成模型的 AUC 为 0.804），性能也相似。在最终模型中，最重要的变量是阳性淋巴结数量（占 25.7%）和脉管侵犯（占 16.9%）。
使用机器学习方法和国际数据集得出的模型在量化手术后早期复发风险方面表现出色，这将对临床医生和患者的预后具有重要意义。
