Department of Obstetrics and Gynecology, College of Medicine, Ewha Medical Research Institute, Ewha Womans University, Seoul, Korea.
D&P Biotech, Inc, Seoul, Korea.
Am J Reprod Immunol. 2021 Sep;86(3):e13435. doi: 10.1111/aji.13435. Epub 2021 May 10.
Preterm birth (PTB) is a major cause of increased morbidity and mortality in newborns. The main cause of spontaneous PTB (sPTB) is the activation of an inflammatory response as a result of ascending genital tract infection. Despite various studies on the effects of the vaginal microbiome on PTB, a practical method for its clinical application has yet to be developed.
In this case-control study, 94 Korean pregnant women with PTB (n = 38) and term birth (TB; n = 56) were enrolled. Their cervicovaginal fluid (CVF) was sampled, and a total of 10 bacteria were analyzed using multiplex quantitative real-time PCR (qPCR). The PTB and TB groups were compared, and a PTB prediction model was created using bacterial risk scores using machine learning techniques (decision tree and support vector machine). The predictive performance of the model was validated using random subsampling.
Bacterial risk scoring model showed significant differences (P < 0.001). The PTB risk was low when the Lactobacillus iners ratio was 0.812 or more. In groups with a ratio under 0.812, moderate and high risk was classified as a U. parvum ratio of 4.6 × 10 . The sensitivity and specificity of the PTB prediction model using bacteria risk score were 71% and 59%, respectively, and 77% and 67%, respectively, when white blood cell (WBC) data were included.
Using machine learning, the bacterial risk score in CVF can be used to predict PTB.
早产（PTB）是新生儿发病率和死亡率增加的主要原因。自发性早产（sPTB）的主要原因是生殖道感染上行导致炎症反应的激活。尽管有许多关于阴道微生物组对 PTB 的影响的研究，但尚未开发出其临床应用的实用方法。
在这项病例对照研究中，纳入了 94 名韩国早产（PTB；n=38）和足月产（TB；n=56）孕妇。采集了她们的宫颈阴道液（CVF）样本，并使用多重实时定量 PCR（qPCR）分析了总共 10 种细菌。比较了 PTB 组和 TB 组，并使用机器学习技术（决策树和支持向量机）基于细菌风险评分创建了 PTB 预测模型。使用随机子抽样验证了模型的预测性能。
细菌风险评分模型显示出显著差异（P<0.001）。当惰性乳杆菌比值为 0.812 或更高时，PTB 风险较低。在比值低于 0.812 的组中，将 U. parvum 比值为 4.6×10-3 分类为中危和高危。使用细菌风险评分的 PTB 预测模型的灵敏度和特异性分别为 71%和 59%，当纳入白细胞（WBC）数据时，分别为 77%和 67%。
使用机器学习，CVF 中的细菌风险评分可用于预测 PTB。
