To identify independent discriminative factors that distinguish the gastrointestinal (GI) subtype of Immunoglobulin G4-related disease (IgG4-RD) from gastrointestinal cancer (GIC), and to develop and validate a non‑invasive predictive nomogram for early differential diagnosis, thereby reducing the risk of misdiagnosis and unnecessary invasive procedures.

A retrospective case‑control study was conducted at the Affiliated Hospital of Xuzhou Medical University between January 2012 and October 2025. A total of 56 treatment‑naïve patients were enrolled, including 18 with the GI subtype of IgG4-RD and 38 with GIC. Ninety‑four clinical parameters, comprising demographic characteristics, laboratory indices, involved organs, and initial symptoms, were collected within 24 hours of admission. Univariate analysis was performed using independent-sample t‑tests, Mann‑Whitney U test, χ² test, or Fisher’s exact test, as appropriate. Statistically significant variables were subsequently entered into multivariate logistic regression to identify independent predictors and construct a nomogram. Model performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

Multivariate logistic regression identified three independent predictors for differentiating GI‑subtype IgG4-RD from GIC: activated clotting time (ACT) (odds ratio [OR] = 0.93, 95% confidence interval [CI]: 0.88–0.99, P = 0.022), serum total protein (OR = 1.26, 95% CI: 1.05–1.51, P = 0.014), and glomerular filtration rate (GFR) (OR = 0.94, 95% CI: 0.89–0.98, P = 0.010). The nomogram derived from these three variables demonstrated excellent discriminative ability, with an area under the ROC curve (AUC) of 0.91 (95% CI: 0.83–0.99). The calibration curve yielded a mean absolute error of 0.07, indicating good agreement between predicted and observed probabilities. Decision curve analysis showed that the model provided superior net clinical benefit compared with both treat‑all and treat‑none strategies across a wide threshold probability range (0–0.95).

A novel, non‑invasive predictive nomogram incorporating serum total protein, GFR, and ACT was successfully developed and internally validated. This tool effectively distinguishes the GI subtype of IgG4-RD from gastrointestinal cancer with high accuracy and clinical utility. It holds promise for early risk stratification, facilitating timely differential diagnosis and potentially reducing unnecessary invasive procedures in routine clinical practice.