Objective:To develop and validate a risk prediction model for cognitive frailty in elderly patients with type 2 diabetes.Methods:A total of 483 elderly patients with type 2 diabetes who visited Tianjin First Central Hospital from June to December 2022 were selected using convenience sampling. They were randomly divided into a modeling group ( n=338) and a validation group ( n=145). Data were collected using a self-designed general information questionnaire, the Short-Form Mini Nutritional Assessment (MNA-SF), the Geriatric Depression Scale-15 (GDS-15), the Frailty Phenotype (FP), the Montreal Cognitive Assessment (MoCA), and the Clinical Dementia Rating (CDR). Logistic regression analysis was performed to identify the influencing factors. A cognitive frailty risk prediction nomogram model was constructed based on the results. The model was validated in the validation group, and its predictive performance and clinical applicability were evaluated using the area under the receiver operating characteristic curve ( AUC), calibration curve, and clinical decision curve analysis. A total of 483 questionnaires were distributed and all were returned as valid, resulting in a 100.0% response rate. Results:The prevalence of cognitive frailty in the 483 elderly patients with type 2 diabetes was 20.3% (98/483). Age, regular exercise, duration of diabetes, HbA1c levels, depression and nutritional status were identified as predictive factors in the model. The AUC of the model was 0.886, and the Hosmer-Lemeshow test showed a χ 2 value of 8.004 ( P=0.433). The optimal cutoff value was 0.335, and the accuracy was 89.0%. Conclusions:The prediction model demonstrates good fit and strong predictive performance, and can intuitively and easily identify elderly patients with type 2 diabetes who are at high risk of cognitive frailty, providing a reference for early screening and intervention.