Qiu Yi-Hui, Chen Fan-Feng, Zhang Yin-He, Yang Zhe, Zhu Guan-Xia, Chen Bi-Cheng, Miao Shou-Liang
Department of Vascular Surgery, The First Affiliated Hospital of Wenzhou Medical University, Wenzhou, China.
Molecular Pharmacology Research Center, School of Pharmaceutical Science, Wenzhou Medical University, Wenzhou, China.
Abdom Radiol (NY). 2025 Jan 15. doi: 10.1007/s00261-024-04745-3.
Mesenteric artery embolism (MAE) is a relatively uncommon abdominal surgical emergency, but it can lead to catastrophic clinical outcomes if the diagnosis is delayed. This study aims to build a prediction model of clinical-radiomics nomogram for early diagnosis of MAE based on non-contrast computed tomography (CT) and biomarkers.
In this retrospective study, a total of 364 patients confirmed as MAE (n = 131) or non-MAE (n = 233) who were randomly divided into a training cohort (70%) and a validation cohort (30%). In the training cohort, the minimum redundancy maximum relevance (mRMR) and the least absolute shrinkage and selection operator (LASSO) algorithms were used to select optimal radiomics features from non-contrast CT images for calculating Radscore which was utilized to establish the radiomics model. Logistic regression analysis was performed to screen clinical factors, and then generate the clinical model. A predictive nomogram model was built using Radscore and the selected clinical risk factors, which was evaluated through the receiver operating characteristic (ROC) curve, calibration curve and decision curve analysis (DCA).
Thirteen radiomics features were chosen to calculate Radscore. Age, white blood cell (WBC) count, creatine kinase (CK) and D-dimer were determined as the independent clinical factors. The clinical-radiomics nomogram model showed the best performance in training cohort. The nomogram model was with higher area under curve (AUC) value of 0.93, compared to radiomics model with AUC value of 0.90 or clinical model with AUC value of 0.78 in the validation cohort. The calibration curve showed that nomogram model achieved a good fit in both cohorts (P = 0.59 and 0.92, respectively). The DCA indicated that nomogram model was significantly favorable for clinical usefulness of MAE diagnosis.
The nomogram provides an effective tool for the early diagnosis of MAE, which may play a crucial role in shortening the time for therapeutic decision-making, thereby reducing the risk of intestinal necrosis and death.
肠系膜动脉栓塞（MAE）是一种相对罕见的腹部外科急症，但如果诊断延迟，可能导致灾难性的临床后果。本研究旨在基于非增强计算机断层扫描（CT）和生物标志物建立一种用于MAE早期诊断的临床-影像组学列线图预测模型。
在这项回顾性研究中，共有364例确诊为MAE（n = 131）或非MAE（n = 233）的患者被随机分为训练队列（70%）和验证队列（30%）。在训练队列中，使用最小冗余最大相关（mRMR）和最小绝对收缩和选择算子（LASSO）算法从非增强CT图像中选择最佳影像组学特征以计算Radscore，该Radscore用于建立影像组学模型。进行逻辑回归分析以筛选临床因素，进而生成临床模型。使用Radscore和选定的临床风险因素构建预测列线图模型，并通过受试者工作特征（ROC）曲线、校准曲线和决策曲线分析（DCA）对其进行评估。
选择了13个影像组学特征来计算Radscore。年龄、白细胞（WBC）计数、肌酸激酶（CK）和D-二聚体被确定为独立的临床因素。临床-影像组学列线图模型在训练队列中表现最佳。在验证队列中，列线图模型的曲线下面积（AUC）值更高，为0.93，而影像组学模型的AUC值为0.90，临床模型的AUC值为0.78。校准曲线表明列线图模型在两个队列中均具有良好的拟合度（P分别为0.59和0.92）。DCA表明列线图模型对MAE诊断的临床实用性具有显著优势。
该列线图为MAE的早期诊断提供了一种有效工具，可能在缩短治疗决策时间方面发挥关键作用，从而降低肠坏死和死亡风险。
