Machine learning model based on chest non-contrast CT radiomics for diagnosing metabolic syndrome in males
10.13929/j.issn.1003-3289.2025.07.014
- VernacularTitle:基于胸部平扫CT影像组学机器学习模型筛查男性代谢综合征
- Author:
Yi WEI
1
;
Zhimin DING
;
Jian ZHAI
;
Xingwang WU
Author Information
1. 安徽医科大学第一附属医院放射科,安徽 合肥 230022;皖南医学院第一附属医院放射科,安徽芜湖 241000
- Publication Type:Journal Article
- Keywords:
male;
metabolic syndrome;
tomography,X-ray computed;
radiomics;
machine learning;
prospective studies
- From:
Chinese Journal of Medical Imaging Technology
2025;41(7):1103-1108
- CountryChina
- Language:Chinese
-
Abstract:
Objective To observe the value of machine learning(ML)model based on chest non-contrast CT(NCCT)radiomics for diagnosing metabolic syndrome(MetS)in males.Methods A total of 792 males who would undergo chest NCCT and bone density CT examination for physical check-up were prospectively enrolled and divided into training set(n=554,including 171 cases of MetS)and validation set(n=238,including 70 cases of MetS)at the ratio of 7∶3.Chest NCCT was performed,ROI of liver,intra-abdominal fat and skeletal muscle were delineated,and visceral fat area(VFA)at L2-3 intervertebral disc level was measured.Then radiomic signature(RS)of liver,intra-abdominal fat and skeletal muscle were established,and ML models were constructed using logistic regression(LR),random forests(RF)and extreme gradient boosting(XGBoost)algorithms,respectively,and their diagnostic performance were observed.Results Significant difference of age was found between MetS and non-MetS males in training set(P=0.010),while of RS scores were noticed in both training set and validation set(all P＜0.001).Combined ML models were constructed with age and RS.The area under the curve(AUC)of combined LR,RF and XGBoost models for diagnosing male MetS in training set was 0.899,0.996 and 0.943,while that in validation set was 0.861,0.860 and 0.876,respectively.Combined XGBoost model had the best performance.Conclusion XGBoost model based on chest NCCT radiomics was helpful for diagnosing male MetS.Combining with age could further improve its efficacy.
