Objective:To evaluate the value of a nomogram model based on clinical and CT fea-tures in predicting early expansion of supratentorial parenchymal hemorrhage.Methods:The clinical data and CT signs of 291 patients with supratentorial intracerebral hemorrhage were retrospectively analyzed.According to the development of hematoma enlargement(HE),the patients were divided into the HE group(n=131)and the non-HE group(n=160).The patients were divided into the training set(n=204)and the validation set(n=87)by random stratified sampling at a ratio of 7∶3.The clini-cal data and CT signs of the two groups were compared.Univariate and multivariate Logistic regres-sion analysis were used to screen independent risk factors,and a nomogram prediction model was con-structed.The receiver operating characteristic(ROC)curve and area under the curve(AUC),calibra-tion curve and clinical impact curve(CIC)were used to evaluate the discrimination,calibration and clinical practicability of the nomogram.Results:Fasting blood glucose,black hole sign,whirl sign,and blend sign were independent risk factors for HE(all P＜0.05).The AUC of the nomogram model in the training set and validation set were 0.787(95％CI:0.723～0.851)and0.716(95％CI:0.594～0.839),respectively.The Hosmer-Lemeshow goodness of fit test showed that there was no significant difference between the predicted results of the model and the actual results(x2=9.007,P=0.342,R2=0.328).The calibration curve showed that the model fitted well.CIC showed that the nomogram had high clinical value.Conclusion:The individualized prediction model based on clinical and CT fea-tures can effectively predict the early expansion of supratentorial parenchymal hemorrhage.
维普
万方数据