PDF(Pubmed)
Abstract：
UNASSIGNED: Visceral adipose tissue (VAT) is involved in the pathogenesis of Crohn\'s disease (CD). However, data describing its effects on CD progression remain scarce. We developed and validated a VAT-radiomics model (RM) using computed tomography (CT) images to predict disease progression in patients with CD and compared it with a subcutaneous adipose tissue (SAT)-RM.
UNASSIGNED: This retrospective study included 256 patients with CD (training, n = 156; test, n = 100) who underwent baseline CT examinations from June 19, 2015 to June 14, 2020 at three tertiary referral centres (The First Affiliated Hospital of Sun Yat-Sen University, The First Affiliated Hospital of Shantou University Medical College, and The First People\'s Hospital of Foshan City) in China. Disease progression referred to the development of penetrating or stricturing diseases or the requirement for CD-related surgeries during follow-up. A total of 1130 radiomics features were extracted from VAT on CT in the training cohort, and a machine-learning-based VAT-RM was developed to predict disease progression using selected reproducible features and validated in an external test cohort. Using the same modeling methodology, a SAT-RM was developed and compared with the VAT-RM.
UNASSIGNED: The VAT-RM exhibited satisfactory performance for predicting disease progression in total test cohort (the area under the ROC curve [AUC] = 0.850, 95% confidence Interval [CI] 0.764-0.913, P < 0.001) and in test cohorts 1 (AUC = 0.820, 95% CI 0.687-0.914, P < 0.001) and 2 (AUC = 0.871, 95% CI 0.744-0.949, P < 0.001). No significant differences in AUC were observed between test cohorts 1 and 2 (P = 0.673), suggesting considerable efficacy and robustness of the VAT-RM. In the total test cohort, the AUC of the VAT-RM for predicting disease progression was higher than that of SAT-RM (AUC = 0.786, 95% CI 0.692-0.861, P < 0.001). On multivariate Cox regression analysis, the VAT-RM (hazard ratio [HR] = 9.285, P = 0.005) was the most important independent predictor, followed by the SAT-RM (HR = 3.280, P = 0.060). Decision curve analysis further confirmed the better net benefit of the VAT-RM than the SAT-RM. Moreover, the SAT-RM failed to significantly improve predictive efficacy after it was added to the VAT-RM (integrated discrimination improvement = 0.031, P = 0.102).
UNASSIGNED: Our results suggest that VAT is an important determinant of disease progression in patients with CD. Our VAT-RM allows the accurate identification of high-risk patients prone to disease progression and offers notable advantages over SAT-RM.
UNASSIGNED: This study was supported by the National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Nature Science Foundation of Shenzhen, and Young S&T Talent Training Program of Guangdong Provincial Association for S&T.
UNASSIGNED: For the Chinese translation of the abstract see Supplementary Materials section.
UNASSIGNED: This retrospective study included 256 patients with CD (training, n = 156; test, n = 100) who underwent baseline CT examinations from June 19, 2015 to June 14, 2020 at three tertiary referral centres (The First Affiliated Hospital of Sun Yat-Sen University, The First Affiliated Hospital of Shantou University Medical College, and The First People\'s Hospital of Foshan City) in China. Disease progression referred to the development of penetrating or stricturing diseases or the requirement for CD-related surgeries during follow-up. A total of 1130 radiomics features were extracted from VAT on CT in the training cohort, and a machine-learning-based VAT-RM was developed to predict disease progression using selected reproducible features and validated in an external test cohort. Using the same modeling methodology, a SAT-RM was developed and compared with the VAT-RM.
UNASSIGNED: The VAT-RM exhibited satisfactory performance for predicting disease progression in total test cohort (the area under the ROC curve [AUC] = 0.850, 95% confidence Interval [CI] 0.764-0.913, P < 0.001) and in test cohorts 1 (AUC = 0.820, 95% CI 0.687-0.914, P < 0.001) and 2 (AUC = 0.871, 95% CI 0.744-0.949, P < 0.001). No significant differences in AUC were observed between test cohorts 1 and 2 (P = 0.673), suggesting considerable efficacy and robustness of the VAT-RM. In the total test cohort, the AUC of the VAT-RM for predicting disease progression was higher than that of SAT-RM (AUC = 0.786, 95% CI 0.692-0.861, P < 0.001). On multivariate Cox regression analysis, the VAT-RM (hazard ratio [HR] = 9.285, P = 0.005) was the most important independent predictor, followed by the SAT-RM (HR = 3.280, P = 0.060). Decision curve analysis further confirmed the better net benefit of the VAT-RM than the SAT-RM. Moreover, the SAT-RM failed to significantly improve predictive efficacy after it was added to the VAT-RM (integrated discrimination improvement = 0.031, P = 0.102).
UNASSIGNED: Our results suggest that VAT is an important determinant of disease progression in patients with CD. Our VAT-RM allows the accurate identification of high-risk patients prone to disease progression and offers notable advantages over SAT-RM.
UNASSIGNED: This study was supported by the National Natural Science Foundation of China, Guangdong Basic and Applied Basic Research Foundation, Shenzhen-Hong Kong Institute of Brain Science-Shenzhen Fundamental Research Institutions, Nature Science Foundation of Shenzhen, and Young S&T Talent Training Program of Guangdong Provincial Association for S&T.
UNASSIGNED: For the Chinese translation of the abstract see Supplementary Materials section.
摘要：
未经证实：内脏脂肪组织（VAT）与克罗恩病（CD）的发病机制有关。然而,描述其对CD进展影响的数据仍然很少。我们使用计算机断层扫描（CT）图像开发并验证了VAT-影像组学模型（RM），以预测CD患者的疾病进展，并将其与皮下脂肪组织（SAT）-RM进行了比较。
未经评估：这项回顾性研究包括256名CD患者（训练，n=156;试验,n=100），从2015年6月19日至2020年6月14日在三个三级转诊中心接受基线CT检查（中山大学附属第一医院，汕头大学医学院第一附属医院,和中国佛山市第一人民医院）。疾病进展是指穿透或狭窄疾病的发展或在随访期间对CD相关手术的要求。在训练队列中，从CT上的增值税中提取了1130个影像组学特征，我们开发了一种基于机器学习的VAT-RM,使用选定的可重复特征预测疾病进展,并在外部测试队列中进行了验证.使用相同的建模方法，开发了SAT-RM，并与VAT-RM进行了比较。
UNASSIGNED：VAT-RM在总测试队列（ROC曲线下面积[AUC]=0.850，95％置信区间[CI]0.764-0.913，P<0.001）和测试队列1（AUC=0.820，95％CI0.687-0.914，P<0.001）和2（AUC=0.849，0.7P<在测试队列1和2之间没有观察到AUC的显着差异（P=0.673），表明增值税-RM具有相当大的功效和稳健性。在总测试队列中，VAT-RM预测疾病进展的AUC高于SAT-RM(AUC=0.786,95%CI0.692-0.861,P<0.001)。在多元Cox回归分析中，VAT-RM（危险比[HR]=9.285，P=0.005）是最重要的独立预测因子，其次是SAT-RM(HR=3.280,P=0.060)。决策曲线分析进一步证实了增值税-RM比SAT-RM更好的净收益。此外，SAT-RM加入VAT-RM后未能显著改善预测效能(综合辨别改善=0.031,P=0.102).
UNASSIGNED：我们的结果表明，VAT是CD患者疾病进展的重要决定因素。我们的VAT-RM可以准确识别容易发生疾病进展的高风险患者，并提供优于SAT-RM的显著优势。
UNASSIGNED：这项研究得到了国家自然科学基金的支持，广东省基础与应用基础研究基金会,深港脑科学研究所-深圳市基础研究机构,深圳市自然科学基金,广东省科技协会青年科技人才培养计划
UASSIGNED：有关摘要的中文翻译，请参见补充材料部分。
未经评估：这项回顾性研究包括256名CD患者（训练，n=156;试验,n=100），从2015年6月19日至2020年6月14日在三个三级转诊中心接受基线CT检查（中山大学附属第一医院，汕头大学医学院第一附属医院,和中国佛山市第一人民医院）。疾病进展是指穿透或狭窄疾病的发展或在随访期间对CD相关手术的要求。在训练队列中，从CT上的增值税中提取了1130个影像组学特征，我们开发了一种基于机器学习的VAT-RM,使用选定的可重复特征预测疾病进展,并在外部测试队列中进行了验证.使用相同的建模方法，开发了SAT-RM，并与VAT-RM进行了比较。
UNASSIGNED：VAT-RM在总测试队列（ROC曲线下面积[AUC]=0.850，95％置信区间[CI]0.764-0.913，P<0.001）和测试队列1（AUC=0.820，95％CI0.687-0.914，P<0.001）和2（AUC=0.849，0.7P<在测试队列1和2之间没有观察到AUC的显着差异（P=0.673），表明增值税-RM具有相当大的功效和稳健性。在总测试队列中，VAT-RM预测疾病进展的AUC高于SAT-RM(AUC=0.786,95%CI0.692-0.861,P<0.001)。在多元Cox回归分析中，VAT-RM（危险比[HR]=9.285，P=0.005）是最重要的独立预测因子，其次是SAT-RM(HR=3.280,P=0.060)。决策曲线分析进一步证实了增值税-RM比SAT-RM更好的净收益。此外，SAT-RM加入VAT-RM后未能显著改善预测效能(综合辨别改善=0.031,P=0.102).
UNASSIGNED：我们的结果表明，VAT是CD患者疾病进展的重要决定因素。我们的VAT-RM可以准确识别容易发生疾病进展的高风险患者，并提供优于SAT-RM的显著优势。
UNASSIGNED：这项研究得到了国家自然科学基金的支持，广东省基础与应用基础研究基金会,深港脑科学研究所-深圳市基础研究机构,深圳市自然科学基金,广东省科技协会青年科技人才培养计划
UASSIGNED：有关摘要的中文翻译，请参见补充材料部分。
