单侧慢性硬膜下血肿钻孔引流术后复发的临床预测模型建立与验证

Establishment and validation of a clinical prediction model of unilateral chronic subdural hematoma recurrence after burr hole irrigation and drainage

目的研究基于临床资料建立并验证单侧慢性硬膜下血肿(CSDH)钻孔引流术后复发的预测模型。方法纳入采用钻孔引流治疗的366例单侧CSDH患者。根据首次钻孔后3个月内是否CSDH复发,将患者分为复发组和非复发组;分析比较与CSDH术后复发可能相关的15项因素。采用最小绝对收缩和选择算子(LASSO)回归来降低数据维度和筛选预测因子,纳入多因素Logistic回归建立预测模型并制作列线图。受试者工作特征曲线(ROC)和校准曲线用于验证模型的区分度和拟合优度。决策曲线分析评价预测模型的临床适用性。结果LASSO回归筛选出4个预测因子(年龄、脑萎缩、术前血肿量、脑复张率),纳入Logistic回归并形成列线图。经过验证,模型的ROC曲线下面积为0.769;校准曲线显示预测概率与实际概率有很好的一致性;决策曲线分析则显示模型在一定范围内的临床适用性。结论本研究建立的CSDH术后复发的预测模型具有良好的区分度、拟合优度和临床适用性,有利于个体化治疗的调整及对复发高风险患者的针对性观察随访。

Objective To establish and verify a clinical prediction model of unilateral chronic subdural hematoma(CSDH)recurrence after burr hole irrigation and drainage based on clinical data.Methods 366 cases of unilateral CSDH patients were collected.According to the recurrence within 3 months after the first drilling,the patients were divided into recurrence group and non recurrence group,and 15 factors related to the recurrence of CSDH were analyzed.The least absolute shrinkage and selection operator(LASSO)regression was used to reduce the data dimension and filter the prediction factors.The multivariate logistic regression was used to establish the prediction model and constructe nomogram.Receiver operating characteristic(ROC)curve and calibration curve were respectively used to detect the discrimination and goodness of fit of the model.Decision curve analysis(DCA)was used to evaluate the clinical applicability of the prediction model.Results Four predictors were screened out by LASSO regression and included in logistic regression to form a nomogram.After verification,the area under the curve(AUC)of ROC was 0.769.The calibration curve showed that the predicted probability was in good agreement with the actual probability.DCA showed the clinical applicability of the model in a certain range.Conclusion The study establishes a prediction model of postoperative recurrence of CSDH,which has good differentiation,goodness of fit and clinical applicability,and is conducive to the adjustment of individualized treatment and targeted follow-up of patients with high risk of recurrence.