临床医学工程2025，Vol.32Issue(9)：925-929,5.DOI:10.3969/j.issn.1674-4659.2025.09.0925
基于孕早期胎盘超声影像组学的妊娠期糖尿病风险预测模型研究
Study on Risk Prediction Model of Gestational Diabetes Mellitus Based on Placental Ultrasound Radiomics in Early Pregnancy
摘要
Abstract
Objective To explore the application value of early-pregnancy placental ultrasound radiomics in predicting the risk of gestational diabetes mellitus(GDM),and to evaluate the efficacy of different models in predicting GDM.Methods The clinical data and placental ultrasound images of 198 pregnant women who gave birth in Guangzhou Red Cross Hospital from January 2021 to June 2024 were retrospectively analyzed.The pregnant women were randomly divided into training set(n=139)and validation set(n=59)according to the ratio of 7∶3.Radiomics features were extracted from placental ultrasound images in early pregnancy.After dimensionality reduction by least absolute shrinkage and selection operator(LASSO),support vector machine(SVM),random forest(RF)and gaussian process classification(GPC)models were constructed respectively.The performance of the models was evaluated by indicators such as area under the curve(AUC),accuracy,sensitivity,and specificity,etc.Results After feature screening,eight features with the best predictive efficacy for GDM were retained to establish SVM,RF,and GPC models,respectively.The A UCs of SVM in the training set and validation set were 0.766 and 0.740,indicating superior predictive performance and robustness in effectively identifying individuals at high risk of GDM.Conclusions The SVM model constructed based on placental ultrasound radiomics in early pregnancy can serve as a non-invasive auxiliary tool for early identification of high-risk pregnant women with GDM,and provide scientific evidence for clinical intervention.关键词
妊娠期糖尿病/孕早期/胎盘/超声影像组学/风险预测Key words
Gestational diabetes mellitus/Early pregnancy/Placenta/Ultrasound radiomics/Risk prediction分类
医药卫生引用本文复制引用
曾燕莹,陈婉明,林健如,梅乐,过新民..基于孕早期胎盘超声影像组学的妊娠期糖尿病风险预测模型研究[J].临床医学工程,2025,32(9):925-929,5.基金项目
2025年度广州市卫生健康科技项目(20251A010017) （20251A010017）
