神经影像模型对短暂症状伴梗死患者预后的预测作用研究

The Predictive Value of Neuroimaging-based Risk Evaluation Model on the Prognosis of Cerebral Infarction Patients with Transient Symptoms

目的 评估基于神经影像特征的综合卒中复发模型(comprehensive stroke recurrence model,CSR)在短暂症状伴梗死(transient symptoms with infarction,TSI)人群中预测短期和长期卒中风险的能力,并与基于临床危险因素的卒中风险预测评分进行比较。方法 本研究数据来源于郑州大学第一附属医院的TIA数据库。收集数据库中TSI(MRIDWI序列显示弥散受限)患者的基线特征,评定ABCD^(2)评分和Essen卒中风险评分(Essenstrokeriskscore,ESRS),根据患者入院后头颅MRI结果进行CSR评分。于TSI后7 d、1年进行随访,终点事件为缺血性卒中。绘制ABCD^(2)、ESRS和CSR评分预测缺血性卒中的ROC曲线,计算不同评分的AUC并进行比较。结果 研究共纳入符合入组和排除标准的TSI患者441例,平均57.5±11.9岁,女性153例(34.7%)。CSR评分(AUC 0.688,95%CI 0.642~0.731)对TSI后1年卒中风险的预测价值高于ABCD^(2)评分(AUC0.579,95%CI 0.531~0.625,P=0.014)和ESRS(AUC 0.580,95%CI 0.532~0.626,P=0.011)。结论 与基于临床危险因素的评分如ABCD^(2)、ESRS相比,CSR评分对TSI患者的长期缺血性卒中风险具有更好的预测价值。

Objective To assess the predictive value of the comprehensive stroke recurrence(CSR) model,an imaging-based risk score,for short-term and long-term stroke risk in cerebral infarction patients with transient symptoms,and the predictive ability between this model and clinical scores was compared.Methods This study enrolled the cerebral infarction patients with transient symptoms from the TIA database of the First Affiliated Hospital of Zhengzhou University.The baseline information were collected and ABCD^(2) score,Essen Stroke Risk Score(ESRS) and CSR score(based on head MRI)were calculated in the patients.The outcome was ischemic stroke at 7 days and 1 year.The ROC curve was performed to compare the predictive value of the three scores.Results A total of 441 eligible patients were enrolled in this study,with an average age of 57.5±11.9 years and 153 females(34.7%).The CSR score(AUC 0.688,95%CI 0.642-0.731) was superior in predicting 1-year stroke risk than ABCD^(2) score(AUC 0.579,95%CI 0.531-0.625,P=0.014) and ESRS(AUC 0.580,95%CI 0.532-0.626,P=0.011).Conclusions CSR score had a higher predictive value for predicting the long-term risk of ischemic stroke,compared with the clinical risk factor-based scores such as ESRS and ABCD^(2) score.