基于超声影像组学的临床列线图预测模型在慢性肾脏病纤维化程度诊断中的价值  

Evaluation of the Degree of Fibrosis in Chronic Kidney Disease via Clinical Radiomics Nomogram Prediction Model

作　　者：胡小敏 肖为瀚 刘学彬[2] 张超学[3] 覃夏川 HU Xiaomin;XIAO Weihan;LIU Xuebin;ZHANG Chaoxue;QIN Xiachuan(Department of Ultrasound,Chengdu Second People’s Hospital,Chengdu 610000,China;不详)

机构地区：[1]川北医学院,四川南充637000 [2]川北医学院第二临床学院·南充市中心医院超声科,四川南充637000 [3]安徽医科大学第一附属医院超声科,安徽合肥230022 [4]成都市第二人民医院超声科,四川成都610000

出　　处：《中国医学影像学杂志》2025年第3期331-336,共6页Chinese Journal of Medical Imaging

基　　金：南充市市校科技战略合作项目(22JCYJPT0004);四川省医学会专项科研项目(2024HR143)。

摘　　要：目的探讨基于超声组学的临床列线图预测模型诊断慢性肾脏病(CKD)纤维化程度的价值。资料与方法回顾性分析南充市中心医院2014年1月—2022年7月经肾穿刺活检确诊CKD患者350例。根据肾间质纤维化肾小管萎缩(TA/IF)将患者进行分类,按照7∶3随机分为训练组245例和验证组105例。通过评估患者人口统计学建立临床预测模型,根据从肾脏超声图像中提取出的影像组学特征建立XGBoost机械学习模型,随后结合影像组学评分和临床独立预测因子建立临床超声影像组学列线图预测模型。利用受试者工作特征曲线及校准曲线评估3种模型的诊断效能。结果350例CKD患者中,TA/IF 0类226例,TA/IF 1类124例。基于临床特征和影像组学评分的临床影像组学列线图模型的预测效果最佳,其训练组和验证组曲线下面积分别为0.938(95%CI 0.909~0.969)和0.933(95%CI 0.891~0.980)。结论超声影像组学预测模型在无创诊断CKD患者的TA/IF方面具有潜力。基于影像组学评分联合临床数据的列线图预测模型可能有助于患者临床管理。Purpose To explore the value of the clinical radiomics nomogram based on ultrasound in evaluating the degree of fibrosis in chronic kidney disease(CKD).Materials and Methods This retrospective study included 350 patients with CKD in Nanchong Central Hospital from January 2014 to July 2022 who underwent renal biopsy.The patients were categorized by the tubule atrophy with interstitial fibrosis(TA/IF)and divided into a training cohort(n=245)and test cohort(n=105).The patient demographics were evaluated to establish a clinical prediction model.The XGBoost machine learning model was constructed by extracting the radiomics features from the ultrasound images.The clinical radiomics nomogram prediction model was constructed by combining the radiomics score(Rad score)and important clinical features.The diagnostic performance of the three models was evaluated using receiver operating characteristic curve analysis.Results Among the 350 patients with CKD,226 had TA/IF 0 and 124 had TA/IF 1.Based on the clinical characteristics and Rad score,the clinical radiomics nomogram prediction model had the highest area under the curve in the training and testing cohorts,with the area under the curve of 0.938(95%CI 0.909-0.969)and 0.933(95%CI 0.891-0.980),respectively.Conclusion The ultrasound-based radiomics prediction model has potential value for the noninvasive diagnosis of TA/IF in CKD.Nomogram prediction models based on renal Rad scores and clinic may help clinicians to manage patients.

关 键 词：肾功能不全 慢性 纤维化 超声检查 影像组学 列线图表 

分 类 号：R692[医药卫生—泌尿科学] R445.1[医药卫生—外科学]