Construction and evaluation of the risk prediction model of cognitive dysfunction after acute ischemic stroke

Objective To establish a prediction model of post-stroke cognitive impairment(PSCI) in patients with acute ischemic stroke, in order to effectively identify the high-risk group of PSCI and reduce the risk of PSCI.

Methods A total of 143 new acute ischemic stroke patients admitted to The First Affiliated Hospital of Bengbu Medical University from March to November 2023 were selected.After 3-6 months of follow-up, patients were divided into the cognitive impairment group and cognitive normal group according to MMSE score.The predictive model was constructed by logistic regression analysis, the influencing factors of PSCI were analyzed, and the effectiveness of model was evaluated by ROC analysis.

Results The results of logistic regression analysis showed that history of coronary heart disease, high NIHSS score, high mRS score on admission, D-dimer levels were the risk factors of cognitive dysfunction in patients with acute ischemic stroke, and the differences of which were statistically significant(P < 0.05 to P < 0.01).The results of ROC analysis, the areas under the curve of NIHSS, D-dimer, mRS, history of coronary heart disease and combined predicted cognitive dysfunction in patients with acute ischemic stroke were 0.728, 0.641, 0.700, 0.583 and 0.733, respectively.

Conclusions The prediction model of PSCI is constructed by logistic regression analysis.The NIHSS, D-dimer, history of coronary heart disease and mRS on admission may be the independent risk factors of PSCI in patients with acute ischemic stroke.They have certain prediction ability for PSCI, and the combined prediction efficiency is better.