In this study, elderly patients with gastric cancer who underwent radical gastrectomy in Union Hospital Affiliated to Fujian Medical University from 2012 to 2018 were included as a derived cohort, and the training set and internal validation set were randomly divided by 4:1. Machine learning strategies of random forest, decision tree and support vector machine are used to construct survival prediction model. Each model was tested in an internal validation set and an external validation set consisting of patients from two other large medical centers.

This is a retrospective, supervised learning, data mining study.

Inclusion Criteria:

• (1) GC diagnosis confirmed by abdominal computed tomography (CT) or biopsy; (2) age ≥65 years at diagnosis; (3) underwent radical surgical resection without evidence of distant metastasis; and (4) availability of complete clinical and pathological data.

Exclusion Criteria:

• (1) postoperative pathology confirming non-gastric primary tumors; (2) distant metastasis; (3) incomplete clinical data; and (4) other concurrent malignancies within five years.

This retrospective prognostic study encompassed patients aged 65 or older who underwent radical gastrectomy for GC from January 2012 to April 2018. The study involved a derivation cohort and an external validation cohort.