Background <p>Carbohydrate antigen 199 (CA199) is a well-established glycoprotein biomarker traditionally utilized for the diagnosis and prognosis of pancreatic and gastrointestinal malignancies. Recent research has demonstrated a significant association between CA199 and benign metabolic disorders, with notably elevated serum CA199 levels detected in individuals with type 2 diabetes mellitus (T2DM). Diabetic kidney disease (DKD) represents a severe microvascular complication of T2DM, with its prevalence in Northwest China being substantially higher than in other regions of the country. Nonetheless, the relationship between serum CA199 levels and DKD in T2DM patients remains contentious, and there is limited research specifically focusing on this specific regional population. This study aims to examine the association between serum CA199 levels and the prevalence of DKD in hospitalized T2DM patients in Northwest China.</p> Methods <p>A retrospective cross-sectional analysis was conducted on the clinical data of 647 patients diagnosed with T2DM who were admitted to the Department of Endocrinology at the Second Affiliated Hospital of Xi’an Jiaotong University between January 2022 and May 2024. DKD was operationally defined by a urinary albumin-to-creatinine ratio (ACR) exceeding 30&#xa0;mg/g or an estimated glomerular filtration rate (eGFR) below 60 mL/(min·1.73&#xa0;m²). To investigate the association between serum CA199 levels and DKD, multivariable logistic regression models were employed, incorporating CA199 both as a continuous variable (per one standard deviation increase) and as a categorical variable stratified by quartiles. Additionally, restricted cubic spline (RCS) analysis was conducted to assess the dose-response relationship. The incremental predictive value of CA199 beyond a baseline risk model was evaluated through the C-statistic, net reclassification improvement (NRI), and integrated discrimination improvement (IDI). Subgroup analyses with interaction tests were performed, and the Benjamini-Hochberg method was used to control the false discovery rate. Furthermore, sensitivity analyses were conducted to ascertain the robustness of the findings.</p> Results <p>Logistic regression analysis identified a significant positive association between CA199 levels and DKD among the 647 study participants (per SD increase: OR = 1.704, 95% CI: 1.37–2.12, <i>P</i> &lt; 0.001). RCS analysis further corroborated a clear positive dose-response relationship. Stratification of CA199 into quartiles showed a progressive increase in DKD risk across quartiles (P for trend &lt; 0.001); patients in the highest quartile had a 2.57-fold higher risk than those in the lowest quartile (OR = 2.57, 95% CI: 1.56–4.27, <i>P</i> &lt; 0.001). Adding CA199 to a baseline risk model significantly improved predictive performance (C-statistic: 0.674 to 0.711; NRI = 0.115; IDI = 0.044; all <i>P</i> &lt; 0.01). Subgroup analyses revealed significant interactions with drinking status and HbA1c level (P for interaction = 0.016 and 0.035, respectively), but no significant interactions with sex, age, smoking, or hypertension (all <i>P</i> &gt; 0.05). Sensitivity analyses (trimming 5% extremes, log-transformation, multiple imputation) consistently confirmed the robustness of the association.</p> Conclusions <p>This cross-sectional study revealed a significant positive association between serum CA199 levels and DKD in adults with T2DM from Northwest China. Future prospective studies are needed to validate this finding.</p> Clinical trial number <p>Not applicable.</p>