TY - JOUR
T1 - International External Validation of Risk Prediction Model of 90-Day Mortality after Gastrectomy for Cancer Using Machine Learning
AU - Dal Cero, Mariagiulia
AU - Gibert Fernandez, Joan
AU - Grande, L
AU - Gimeno, Marta
AU - Osorio, Javier
AU - Bencivenga, Maria
AU - Fumagalli Romario, Uberto
AU - Rosati, Riccardo
AU - Morgagni, Paolo
AU - Gisbertz, Suzanne
AU - Polkowski, Wojciech P.
AU - Lara Santos, Lucio
AU - Kołodziejczyk, Piotr
AU - Kielan, Wojciech
AU - Reddavid, Rossella
AU - van Sandick, Johanna W.
AU - Baiocchi, Gian Luca
AU - Gockel, Ines
AU - Davies, Andrew
AU - Wijnhoven, Bas P. L.
AU - Reim, Daniel
AU - Costa, Paulo
AU - Allum, William H.
AU - Piessen, Guillaume
AU - Reynolds, John V.
AU - Mönig, Stefan P.
AU - Schneider, Paul M.
AU - Garsot Savall, Elisenda
AU - Eizaguirre, Emma
AU - Miró, Mònica
AU - Castro, Sandra
AU - Miranda, Coro
AU - Monzonis-Hernández, Xavier
AU - Pera Román, Manuel
PY - 2024
Y1 - 2024
N2 - Background: 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. Methods: 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. Results: 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. Conclusion: 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.
AB - Background: 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. Methods: 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. Results: 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. Conclusion: 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.
KW - Gastric cancer
KW - Gastrectomy
KW - Mortality
KW - Prediction
KW - Machine learning
KW - Validation
U2 - 10.3390/cancers16132463
DO - 10.3390/cancers16132463
M3 - Article
C2 - 39001525
SN - 2072-6694
VL - 16
JO - Cancers
JF - Cancers
ER -
