AUGIS Surv-G: Prediction of long-term survival after gastrectomy using Random Survival Forests

Abstract

Background: no well validated and contemporaneous tools for personalised prognostication of gastric adenocarcinoma exist. This study aimed to derive and validate a prognostic model for overall survival after surgery for gastric adenocarcinoma using a large national dataset and a non-linear Random Survival Forest (RSF) methodology.

Patients and methods: national audit data from England and Wales were used to identify patients who underwent a potentially curative gastrectomy for adenocarcinoma of the stomach. A total of 2931 patients were included and 29 clinical and pathological variables considered for their impact on survival. A RSF was then trained and validated internally using bootstrapping with calibration and discrimination (time dependent AUC) assessed.

Results: the median survival of the cohort was 69 months, with a 5-year survival of 53.2%. Ten variables were found to significantly influence survival and included in the final model, with the most important being lymph node positivity, pT stage and achieving an R0 resection. Patient characteristics including ASA grade and age were also influential. On validation the model achieved excellent performance with a five-year tAUC of 0.80 (95%CI 0.78-0.82) and good agreement between observed and predicted survival probabilities. A wide spread of predictions for three- (14.8-98.3%, IQR 43.2-84.4%) and five-year (9.4-96.1%, IQR 31.7-73.8%) survival were seen.

Conclusions: a prognostic model for survival after a potentially curative resection for gastric adenocarcinoma was derived and exhibited excellent discrimination and calibration of predictions. After appropriate external validation, it could provide utility in both prognostication for patients and for benchmarking of treatment responses.

More information

Identifiers

ORCID for Timothy Underwood: orcid.org/0000-0001-9455-2188

Catalogue record

Export record

Altmetrics