基于临床-影像组学列线图预测轻中度创伤性损伤患者进展性实质内出血
该研究回顾性分析2018年1月至2021年12月166例伴实质内出血的轻中度创伤性脑损伤患者,按6:4分为训练集和测试集,构建结合影像组学特征与临床因素的联合模型预测实质内出血进展。联合模型训练集AUC为0.81(95%CI 0.72-0.90),测试集AUC为0.88(95%CI 0.79-0.96),优于单纯临床模型(训练集AUC=0.72,测试集AUC=0.74),校准曲线和决策曲线分析显示预测一致且临床有用。
要点
- 联合模型纳入11个影像组学特征、硬膜下血肿存在及D-二聚体>5 mg/l预测轻中度TBI实质内出血进展。
- 联合模型测试集AUC为0.88(95%CI 0.79-0.96),训练集为0.81(95%CI 0.72-0.90)。
- 联合模型优于单纯临床模型(训练集AUC=0.72,测试集AUC=0.74)。
核心结论
- 结合影像组学评分与临床危险因素的联合临床-影像组学模型可作为预测轻中度TBI患者实质内出血进展的可靠有力工具。
研究设计与样本
- 回顾性分析2018年1月至2021年12月166例伴实质内出血的轻中度创伤性脑损伤患者,按6:4比例分为训练集和测试集,基于非增强CT提取影像组学特征,采用单因素和多因素logistic回归筛选临床-影像因素并建立临床-影像模型。
诊断标准与关键数值
- 联合模型训练集AUC为0.81(95%CI 0.72-0.90),测试集AUC为0.88(95%CI 0.79-0.96)。
- 单纯临床模型训练集AUC为0.72,测试集AUC为0.74。
- 联合模型纳入11个影像组学特征、硬膜下血肿存在及D-二聚体>5 mg/l。
临床应用与阅片要点
- 联合模型可用于预测轻中度TBI患者实质内出血进展,辅助临床决策。
- 校准曲线显示列线图预测与观察结果一致,决策曲线分析证实临床有用。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
PURPOSE: To develop a non-contrast computed tomography(NCCT)based radiomics model for predicting intraparenchymal hemorrhage progression in patients with mild to moderate traumatic brain injury(TBI).
METHODS: We retrospectively analyzed 166 mild to moderate TBI patients with intraparenchymal hemorrhage from January 2018 to December 2021. The enrolled patients were divided into training cohort and test cohort with a ratio of 6:4. Uni- and multivariable logistic regression analyses were implemented to screen clinical-radiological factors and to establish a clinical-radiological model. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), the calibration curve, the decision curve analysis, sensitivity, and specificity.
RESULTS: Eleven radiomics features, presence with SDH, and D-dimer > 5 mg/l were selected to construct the combined clinical-radiomic model for the prediction of TICH in mild to moderate TBI patients. The AUC of the combined model was 0.81(95% confidence interval (CI), 0.72 to 0.90) in the training cohort and 0.88 (95% CI 0.79 to 0.96) in the test cohort, which were superior to the clinical model alone (AUCtraining = 0.72, AUCtest = 0.74). The calibration curve demonstrated that the radiomics nomogram had a good agreement between prediction and observation. Decision curve analysis confirmed clinically useful.
CONCLUSIONS: The combined clinical-radiomic model that incorporates the radiomics score and clinical risk factors can serve as a reliable and powerful tool for Predicting intraparenchymal hemorrhage progression for patients with mild to moderate TBI.
引用
- Wei X, Tang X, You D, et al. A clinical-radiomics based nomogram to predict progressive intraparenchymal hemorrhage in mild to moderate traumatic injury patients. Eur J Radiol. 2023. PMID: 37023629. doi:10.1016/j.ejrad.2023.110785
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。