Machine Learning Risk Prediction Model of 90-day Mortality After Gastrectomy for Cancer.

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.

Textbook outcome and survival after gastric cancer resection with curative intent: A population-based analysis.

BACKGROUND: The concept of textbook outcome (TO) has been proposed for analyzing quality of surgical care. This study assessed the incidence of TO among patients undergoing curative gastric cancer resection, predictors for TO achievement, and the association of TO with survival. METHOD: All patients with gastric and gastroesophageal junction cancers undergoing curative gastrectomy between January 2014-December 2017 were identified from a population-based database (Spanish EURECCA Registry). TO included: macroscopically complete resection at the time of operation, R0 resection, ≥15 lymph nodes removed and examined, no serious postoperative complications (Clavien-Dindo ≥II), no re-intervention, hospital stay ≤14 days, no 30-day readmissions and no 90-day mortality. Logistic regression was used to assess the adjusted achievement of TO. Cox survival regression was used to compare conditional adjusted survival across groups. RESULTS: In total, 1293 patients were included, and TO was achieved in 541 patients (41.1%). Among the criteria, "macroscopically complete resection" had the highest compliance (96.5%) while "no serious complications" had the lowest compliance (63.7%). Age (OR 0.53 for the 65-74 years and OR 0.34 for the ≥75 years age group), Charlson comorbidity index ≥3 (OR 0.53, 95%CI 0.34-0.82), neoadjuvant chemoradiotherapy (OR 0.24, 95%CI 0.08-0.70), multivisceral resection (OR 0.55, 95%CI 0.33-0.91), and surgery performed in a community hospital (OR 0.65, CI95% 0.46-0.91) were independently associated with not achieving TO. TO was independently associated with conditional survival (HR 0.67, 95%CI 0.55-0.83). CONCLUSION: TO was achieved in 41.1% of patients who underwent gastric cancer resection with curative intent and was associated with longer survival.

Resección de lipoma submucoso en región prepilórica mediante cirugía robótica / Resection of submucosal lipoma in the prepyloric region by roboti surgery

No disponible