Development and validation of a nomogram incorporating OSA, age, and BMI to predict cognitive impairment after acute mild ischemic stroke

This study used a nomogram to predict cognitive impairment in acute mild ischemic stroke patients. This study retrospectively included 248 patients with acute mild ischemic stroke admitted to the Department of Neurology, Liaocheng People's Hospital, between October 31, 2022, and September 10, 2023. Cognitive impairment was defined using the Mini-Mental State Examination. The total sample was divided using a split-sample approach into a training set (n = 174) and a validation set (n = 74). We examined clinical and general data to identify cognitive dysfunction risk factors. Multivariate logistic regression identified obstructive sleep apnea (OSA), age, and body mass index (BMI) as independent risk factors for cognitive impairment. These factors were integrated to develop the nomogram as an early warning model. The predictive model was validated internally (training set) and externally (validation set). Its discriminative ability was assessed using receiver operating characteristic curves and its accuracy using calibration curves. The model demonstrated robust predictive performance in both the training set (area under the curve (AUC) = 0.808) and the validation set (AUC = 0.733). The calibration curves indicated good agreement between the predicted probability and the observed outcomes. Overall, the developed nomogram, which integrates OSA, age, and BMI, serves as a simple and effective early warning tool for predicting cognitive impairment in patients with acute mild ischemic stroke, offering valuable guidance for clinical intervention.