This study aimed to identify independent risk factors for colorectal adenomatous polyps in patients with type 2 diabetes mellitus (T2DM) and to develop a predictive model to facilitate early and targeted screening. A total of 521 T2DM patients undergoing colonoscopy at Gansu Provincial People's Hospital (January 2022-May 2025) were retrospectively analyzed. Patients were randomly divided into a training set (n = 366) and a validation set (n = 155). The training set was further categorized into polyp and non-polyp groups. Logistic regression was used to identify independent risk factors and construct a predictive model, which was evaluated by ROC curve, calibration plot and decision curve analysis. Age, homocysteine level, body mass index, fecal occult blood test positivity, diabetic peripheral neuropathy and diarrhea were identified as independent risk factors for colorectal adenomatous polyps in patients with T2DM. The predictive model demonstrated strong discrimination, with an area under the ROC curve of 0.878. At the optimal Youden index of 0.526, the model achieved a sensitivity of 0.749 and a specificity of 0.864. Calibration analysis showed good agreement between predicted and observed outcomes (χ2 = 6.173, p = 0.628). This predictive model, based on key clinical risk factors, provides an effective tool for assessing the risk of colorectal adenomatous polyps in T2DM patients, and may support early detection and targeted prevention strategies in clinical practice.
Mu et al. (Thu,) studied this question.