Dal Cero Mariagiulia, Gibert Joan, Grande Luis, Gimeno Marta, Osorio Javier, Bencivenga Maria, Fumagalli Romario Uberto, Rosati Riccardo, Morgagni Paolo, Gisbertz Suzanne, Polkowski Wojciech P, Lara Santos Lucio, Kołodziejczyk Piotr, Kielan Wojciech, Reddavid Rossella, van Sandick Johanna W, Baiocchi Gian Luca, Gockel Ines, Davies Andrew, Wijnhoven Bas P L, Reim Daniel, Costa Paulo, Allum William H, Piessen Guillaume, Reynolds John V, Mönig Stefan P, Schneider Paul M, Garsot Elisenda, Eizaguirre Emma, Miró Mònica, Castro Sandra, Miranda Coro, Monzonis-Hernández Xavier, Pera Manuel
Hospital del Mar Research Institute (IMIM), Section of Gastrointestinal Surgery, Hospital del Mar, Department of Surgery, Universitat Autònoma de Barcelona, 08003 Barcelona, Spain.
Department of Pathology, Hospital Universitario del Mar, Cancer Research Program, Hospital del Mar Research Institute (IMIM), 08003 Barcelona, Spain.
Cancers (Basel). 2024 Jul 5;16(13):2463. doi: 10.3390/cancers16132463.
Radical gastrectomy remains the main treatment for gastric cancer, despite its high mortality. A clinical predictive model of 90-day mortality (90DM) risk after gastric cancer surgery based on the Spanish EURECCA registry database was developed using a matching learning algorithm. We performed an external validation of this model based on data from an international multicenter cohort of patients.
A cohort of patients from the European GASTRODATA database was selected. Demographic, clinical, and treatment variables in the original and validation cohorts were compared. The performance of the model was evaluated using the area under the curve (AUC) for a random forest model.
The validation cohort included 2546 patients from 24 European hospitals. The advanced clinical T- and N-category, neoadjuvant therapy, open procedures, total gastrectomy rates, and mean volume of the centers were significantly higher in the validation cohort. The 90DM rate was also higher in the validation cohort (5.6%) vs. the original cohort (3.7%). The AUC in the validation model was 0.716.
The externally validated model for predicting the 90DM risk in gastric cancer patients undergoing gastrectomy with curative intent continues to be as useful as the original model in clinical practice.
尽管胃癌根治术死亡率较高，但仍是胃癌的主要治疗方法。基于西班牙EURECCA注册数据库，使用匹配学习算法建立了胃癌手术后90天死亡率（90DM）风险的临床预测模型。我们基于一个国际多中心患者队列的数据对该模型进行了外部验证。
选择欧洲GASTRODATA数据库中的一组患者。比较原始队列和验证队列中的人口统计学、临床和治疗变量。使用随机森林模型的曲线下面积（AUC）评估模型的性能。
验证队列包括来自24家欧洲医院的2546名患者。验证队列中晚期临床T和N分期、新辅助治疗、开放手术、全胃切除率以及中心的平均病例数显著更高。验证队列中的90DM率（5.6%）也高于原始队列（3.7%）。验证模型中的AUC为0.716。
在临床实践中，经外部验证的用于预测接受根治性胃切除术的胃癌患者90DM风险的模型，其有效性与原始模型相当。
