This retrospective study analyzed data from 2,102 patients after surgery for gastrointestinal tumors from the INSPIRE database. An increased preoperative stress hyperglycemic ratio (SHR) was independently associated with an increased risk of intensive care unit (ICU) admission. Each 0.1 unit increase in SHR was associated with an odds ratio (OR) of 1.08 (95% CI: 1.04–1.13, p < 0.001). Patients with the highest tertile of SHR (≥1.04) had an OR of 1.43 (95% CI: 1.04–1.97, p = 0.03) versus the lowest tertile. The relationship between SHR and risk was linear (P for non-linearity > 0.05). The predictive model with SHR achieved an AUC of 0.895 and a mean absolute error of 0.009. Subgroup analyzes showed interaction effects for age and sex. Integrating SHR into preoperative assessment may improve risk stratification and patient management.