Department of Obstetrics and Gynecology, Seoul National University College of Medicine, Seoul, Korea.
Department of Obstetrics and Gynecology, Seoul National University Hospital, Seoul, Korea.
Clin Mol Hepatol. 2022 Jan;28(1):105-116. doi: 10.3350/cmh.2021.0174. Epub 2021 Oct 15.
BACKGROUND/AIMS: To develop an early prediction model for gestational diabetes mellitus (GDM) using machine learning and to evaluate whether the inclusion of nonalcoholic fatty liver disease (NAFLD)-associated variables increases the performance of model.
This prospective cohort study evaluated pregnant women for NAFLD using ultrasound at 10-14 weeks and screened them for GDM at 24-28 weeks of gestation. The clinical variables before 14 weeks were used to develop prediction models for GDM (setting 1, conventional risk factors; setting 2, addition of new risk factors in recent guidelines; setting 3, addition of routine clinical variables; setting 4, addition of NALFD-associated variables, including the presence of NAFLD and laboratory results; and setting 5, top 11 variables identified from a stepwise variable selection method). The predictive models were constructed using machine learning methods, including logistic regression, random forest, support vector machine, and deep neural networks.
Among 1,443 women, 86 (6.0%) were diagnosed with GDM. The highest performing prediction model among settings 1-4 was setting 4, which included both clinical and NAFLD-associated variables (area under the receiver operating characteristic curve [AUC] 0.563-0.697 in settings 1-3 vs. 0.740-0.781 in setting 4). Setting 5, with top 11 variables (which included NAFLD and hepatic steatosis index), showed similar predictive power to setting 4 (AUC 0.719-0.819 in setting 5, P=not significant between settings 4 and 5).
We developed an early prediction model for GDM using machine learning. The inclusion of NAFLDassociated variables significantly improved the performance of GDM prediction. (ClinicalTrials.gov Identifier: NCT02276144).
背景/目的：利用机器学习开发一种用于预测妊娠糖尿病（GDM）的早期预测模型，并评估是否纳入非酒精性脂肪性肝病（NAFLD）相关变量可以提高模型性能。
本前瞻性队列研究在妊娠 10-14 周时使用超声评估孕妇的 NAFLD，并在妊娠 24-28 周时筛查 GDM。将 14 周前的临床变量用于建立 GDM 的预测模型（设定 1：传统危险因素；设定 2：添加近期指南中的新危险因素；设定 3：添加常规临床变量；设定 4：添加与 NAFLD 相关的变量，包括 NAFLD 的存在和实验室结果；设定 5：逐步变量选择方法确定的前 11 个变量）。使用机器学习方法（包括逻辑回归、随机森林、支持向量机和深度神经网络）构建预测模型。
在 1443 名女性中，有 86 名（6.0%）被诊断为 GDM。在设定 1-4 中，表现最好的预测模型是设定 4，该设定同时包含临床和与 NAFLD 相关的变量（设定 1-3 中的曲线下面积（AUC）为 0.563-0.697，设定 4 中的 AUC 为 0.740-0.781）。设定 5，使用前 11 个变量（包括 NAFLD 和肝脂肪变性指数），与设定 4 具有相似的预测能力（设定 5 中的 AUC 为 0.719-0.819，设定 4 和设定 5 之间无显著差异）。
我们利用机器学习开发了一种用于预测 GDM 的早期预测模型。纳入与 NAFLD 相关的变量可显著提高 GDM 预测的性能。（临床试验注册号：NCT02276144）。
