Objective: 

To develop and validate a risk prediction model of 90-day mortality (90DM) using machine learning in a large multicenter cohort of patients undergoing gastric cancer resection with curative intent.

Background: 

The 90DM rate after gastrectomy for cancer is a quality of care indicator in surgical oncology. There is a lack of well-validated instruments for personalized prognosis of gastric cancer.

Methods: 

Consecutive patients with gastric adenocarcinoma who underwent potentially curative gastrectomy between 2014 and 2021 registered in the Spanish EURECCA Esophagogastric Cancer Registry database were included. The 90DM for all causes was the study outcome. Preoperative clinical characteristics were tested in four 90DM predictive models: Cross Validated Elastic regularized logistic regression method (cv-Enet), boosting linear regression (glmboost), random forest, and an ensemble model. Performance was evaluated using the area under the curve by 10-fold cross-validation.

Results: 

A total of 3182 and 260 patients from 39 institutions in 6 regions were included in the development and validation cohorts, respectively. The 90DM rate was 5.6% and 6.2%, respectively. The random forest model showed the best discrimination capacity with a validated area under the curve of 0.844 [95% confidence interval (CI): 0.841–0.848] as compared with cv-Enet (0.796, 95% CI: 0.784–0.808), glmboost (0.797, 95% CI: 0.785–0.809), and ensemble model (0.847, 95% CI: 0.836–0.858) in the development cohort. Similar discriminative capacity was observed in the validation cohort.

Conclusions: 

A robust clinical model for predicting the risk of 90DM after surgery of gastric cancer was developed. Its use may aid patients and surgeons in making informed decisions.

中文翻译：

---

癌症胃切除术后 90 天死亡率的机器学习风险预测模型

客观的： 

使用机器学习在一个大型多中心队列患者中开发和验证 90 天死亡率 (90DM) 的风险预测模型，该队列包括以治愈为目的的胃癌切除术。

背景： 

癌症胃切除术后的 90DM 率是外科肿瘤学的护理质量指标。缺乏经过充分验证的胃癌个体化预后工具。

方法： 

包括在西班牙 EURECCA 食管胃癌登记数据库中登记的 2014 年至 2021 年间连续接受潜在治愈性胃切除术的胃腺癌患者。所有原因的 90DM 是研究结果。在四个 90DM 预测模型中测试了术前临床特征：交叉验证弹性正则化逻辑回归方法 (cv-Enet)、增强线性回归 (glmboost)、随机森林和集成模型。通过 10 倍交叉验证使用曲线下面积评估性能。

结果： 

来自 6 个地区 39 个机构的 3182 名和 260 名患者分别被纳入开发和验证队列。90DM 率分别为 5.6% 和 6.2%。与 cv-Enet (0.796, 95% CI: 0.784–0.808)、glmboost 相比，随机森林模型显示出最佳的辨别能力，曲线下的验证面积为 0.844 [95% 置信区间 (CI)：0.841–0.848] (0.797, 95% CI: 0.785–0.809) 和开发队列中的集成模型 (0.847, 95% CI: 0.836–0.858)。在验证队列中观察到类似的辨别能力。

结论： 

开发了一种用于预测胃癌手术后 90DM 风险的稳健临床模型。它的使用可以帮助患者和外科医生做出明智的决定。