Xu Wei, Guo Hongquan, Li Huiping, Dai Qiliang, Song Kangping, Li Fangyi, Zhou Junjie, Yao Jingjiang, Wang Zhen, Liu Xinfeng
Department of Neurology, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.
Department of Neurology, The Affiliated Changsha Central Hospital, Hengyang Medical School, University of South China, Changsha, China.
Front Neurol. 2022 Oct 11;13:974183. doi: 10.3389/fneur.2022.974183. eCollection 2022.
Hematoma expansion (HE) is a critical event following acute intracerebral hemorrhage (ICH). We aimed to construct a non-contrast computed tomography (NCCT) model combining clinical characteristics, radiological signs, and radiomics features to predict HE in patients with spontaneous ICH and to develop a nomogram to assess the risk of early HE.
We retrospectively reviewed 388 patients with ICH who underwent initial NCCT within 6 h after onset and follow-up CT within 24 h after initial NCCT, between January 2015 and December 2021. Using the LASSO algorithm or stepwise logistic regression analysis, five models (clinical model, radiological model, clinical-radiological model, radiomics model, and combined model) were developed to predict HE in the training cohort ( = 235) and independently verified in the test cohort ( = 153). The Akaike information criterion (AIC) and the likelihood ratio test (LRT) were used for comparing the goodness of fit of the five models, and the AUC was used to evaluate their ability in discriminating HE. A nomogram was developed based on the model with the best performance.
The combined model (AIC = 202.599, χ2 = 80.6) was the best fitting model with the lowest AIC and the highest LRT chi-square value compared to the clinical model (AIC = 232.263, χ2 = 46.940), radiological model (AIC = 227.932, χ2 = 51.270), clinical-radiological model (AIC = 212.711, χ2 = 55.490) or radiomics model (AIC = 217.647, χ2 = 57.550). In both cohorts, the nomogram derived from the combined model showed satisfactory discrimination and calibration for predicting HE (AUC = 0.900, sensitivity = 83.87%; AUC = 0.850, sensitivity = 80.10%, respectively).
The NCCT-based model combining clinical characteristics, radiological signs, and radiomics features could efficiently discriminate early HE, and the nomogram derived from the combined model, as a non-invasive tool, exhibited satisfactory performance in stratifying HE risks.
血肿扩大（HE）是急性脑出血（ICH）后的关键事件。我们旨在构建一个结合临床特征、影像学征象和影像组学特征的非增强计算机断层扫描（NCCT）模型，以预测自发性ICH患者的HE情况，并开发一种列线图来评估早期HE的风险。
我们回顾性分析了2015年1月至2021年12月期间388例ICH患者，这些患者在发病后6小时内接受了首次NCCT检查，并在首次NCCT检查后24小时内接受了随访CT检查。使用LASSO算法或逐步逻辑回归分析，建立了五个模型（临床模型、影像学模型、临床 - 影像学模型、影像组学模型和联合模型），用于在训练队列（n = 235）中预测HE，并在测试队列（n = 153）中进行独立验证。采用赤池信息准则（AIC）和似然比检验（LRT）比较五个模型的拟合优度，并用AUC评估它们区分HE的能力。基于性能最佳的模型开发了列线图。
与临床模型（AIC = 232.263，χ2 = 46.940）、影像学模型（AIC = 227.932，χ2 = 51.270）、临床 - 影像学模型（AIC = 212.711，χ2 = 55.490）或影像组学模型（AIC = 217.647，χ2 = 57.550）相比，联合模型（AIC = 202.599，χ2 = 80.6）是拟合度最佳的模型，具有最低的AIC和最高的LRT卡方值。在两个队列中，源自联合模型的列线图在预测HE方面显示出令人满意的区分度和校准度（AUC分别为0.900，灵敏度为83.87%；AUC为0.850，灵敏度为80.10%）。
基于NCCT的结合临床特征、影像学征象和影像组学特征的模型能够有效区分早期HE，并且源自联合模型的列线图作为一种非侵入性工具，在分层HE风险方面表现出令人满意的性能。
