AI Center, Korea University College of Medicine, Anam Hospital, Seoul, Korea.
Department of Oral and Maxillofacial Surgery, Korea University Anam Hospital, Seoul, Korea.
PLoS One. 2024 Jan 2;19(1):e0296329. doi: 10.1371/journal.pone.0296329. eCollection 2024.
This study employs machine learning analysis with population data for the associations of preterm birth (PTB) with temporomandibular disorder (TMD) and gastrointestinal diseases. The source of the population-based retrospective cohort was Korea National Health Insurance claims for 489,893 primiparous women with delivery at the age of 25-40 in 2017. The dependent variable was PTB in 2017. Twenty-one predictors were included, i.e., demographic, socioeconomic, disease and medication information during 2002-2016. Random forest variable importance was derived for finding important predictors of PTB and evaluating its associations with the predictors including TMD and gastroesophageal reflux disease (GERD). Shapley Additive Explanation (SHAP) values were calculated to analyze the directions of these associations. The random forest with oversampling registered a much higher area under the receiver-operating-characteristic curve compared to logistic regression with oversampling, i.e., 79.3% vs. 53.1%. According to random forest variable importance values and rankings, PTB has strong associations with low socioeconomic status, GERD, age, infertility, irritable bowel syndrome, diabetes, TMD, salivary gland disease, hypertension, tricyclic antidepressant and benzodiazepine. In terms of max SHAP values, these associations were positive, e.g., low socioeconomic status (0.29), age (0.21), GERD (0.27) and TMD (0.23). The inclusion of low socioeconomic status, age, GERD or TMD into the random forest will increase the probability of PTB by 0.29, 0.21, 0.27 or 0.23. A cutting-edge approach of explainable artificial intelligence highlights the strong associations of preterm birth with temporomandibular disorder, gastrointestinal diseases and antidepressant medication. Close surveillance is needed for pregnant women regarding these multiple risks at the same time.
本研究采用机器学习分析方法，利用人群数据探讨了早产（PTB）与颞下颌关节紊乱（TMD）和胃肠道疾病之间的关联。本基于人群的回顾性队列研究的资料来源于 2017 年韩国国民健康保险索赔数据，纳入了年龄在 25-40 岁之间的 489893 名初产妇。因变量为 2017 年的 PTB。共纳入 21 个预测因素，包括 2002-2016 年期间的人口统计学、社会经济、疾病和药物信息。随机森林变量重要性用于发现 PTB 的重要预测因素，并评估其与 TMD 和胃食管反流病（GERD）等预测因素的关联。Shapley Additive Explanation (SHAP) 值用于分析这些关联的方向。与具有过采样的逻辑回归相比，具有过采样的随机森林登记的接收器工作特征曲线下面积更高，即 79.3%对 53.1%。根据随机森林变量重要性值和排名，PTB 与社会经济地位低、GERD、年龄、不孕、肠易激综合征、糖尿病、TMD、唾液腺疾病、高血压、三环类抗抑郁药和苯二氮䓬类药物有很强的关联。根据最大 SHAP 值，这些关联是阳性的，例如社会经济地位低（0.29）、年龄（0.21）、GERD（0.27）和 TMD（0.23）。将社会经济地位低、年龄、GERD 或 TMD 纳入随机森林会将 PTB 的概率分别提高 0.29、0.21、0.27 或 0.23。这一前沿的可解释人工智能方法强调了早产与颞下颌关节紊乱、胃肠道疾病和抗抑郁药物之间的强烈关联。对于这些多种风险，孕妇需要同时进行密切监测。
