A natural language processing pipeline to advance the use of Twitter data for digital epidemiology of adverse pregnancy outcomes.
A natural language processing pipeline to advance the use of Twitter data for digital epidemiology of adverse pregnancy outcomes.
复制标题
DOI：
10.1016/j.yjbinx.2020.100076
复制
发表时间：
2020-01-01
影响因子：
4.5
通讯作者：
Gonzalez-Hernandez, Graciela
中科院分区：
文献类型：
--
作者：
Klein, Ari Z;Cai, Haitao;Gonzalez-Hernandez, Graciela
背景：在美国，17%的妊娠以流产或死胎告终。早产影响美国10%的活产婴儿，是全球新生儿死亡的主要原因。早产和低出生体重是美国婴儿死亡的第二大原因。尽管流产、死产和早产的发病率很高，但其原因在很大程度上尚不清楚。目的：本研究的主要目的是（1）评估女性是否在Twitter上报告流产、死产和早产等情况，以及（2）开发自然语言处理（NLP）方法来自动识别用户，从中选择病例进行大规模观察性研究。我们手工制作了正则表达式，从一个数据库中检索提到不良妊娠结果的推文，该数据库包含超过10万名在Twitter上宣布怀孕的用户发布的4亿多条公开推文。两个注释者独立地注释了22，912条检索到的推文中的8109条（每个用户一条随机推文），将那些报告用户亲自经历了结果的推文（“结果”推文）与那些仅仅提到结果的推文（“非结果”推文）区分开。注释者间一致性为kappa=0.90（Cohen kappa）。我们使用带注释的推文来训练和评估特征工程和基于深度学习的分类器。我们进一步注释了7512条（8109条）推文，以开发一个可推广的、基于规则的模块，该模块旨在过滤掉报告的语音，即包含其他人所说内容的帖子，然后进行自动分类。我们进行了一个外在的评估，评估报告的语音过滤器是否可以提高检测妇女报告不良妊娠结局的Twitter.RESULTS：注释为“结果”的推文包括1632名妇女报告流产，119死产，749早产或早产，217低出生体重，558新生儿重症监护病房入院，458胎儿/婴儿损失一般。深度神经网络，基于BERT的分类器在自动检测“结果”推文（精确度=0.87，召回率=0.89）方面取得了最高的整体F1分数（0.88），每个不良妊娠结果的F1分数至少为0.82，精确度至少为0.84。我们报告的语音过滤显著（P
BACKGROUND: In the United States, 17% of pregnancies end in fetal loss: miscarriage or stillbirth. Preterm birth affects 10% of live births in the United States and is the leading cause of neonatal death globally. Preterm births with low birthweight are the second leading cause of infant mortality in the United States. Despite their prevalence, the causes of miscarriage, stillbirth, and preterm birth are largely unknown.OBJECTIVE: The primary objectives of this study are to (1) assess whether women report miscarriage, stillbirth, and preterm birth, among others, on Twitter, and (2) develop natural language processing (NLP) methods to automatically identify users from which to select cases for large-scale observational studies.METHODS: We handcrafted regular expressions to retrieve tweets that mention an adverse pregnancy outcome, from a database containing more than 400 million publicly available tweets posted by more than 100,000 users who have announced their pregnancy on Twitter. Two annotators independently annotated 8109 (one random tweet per user) of the 22,912 retrieved tweets, distinguishing those reporting that the user has personally experienced the outcome ("outcome" tweets) from those that merely mention the outcome ("non-outcome" tweets). Inter-annotator agreement was kappa=0.90 (Cohen's kappa). We used the annotated tweets to train and evaluate feature-engineered and deep learning-based classifiers. We further annotated 7512 (of the 8109) tweets to develop a generalizable, rule-based module designed to filter out reported speech-that is, posts containing what was said by others-prior to automatic classification. We performed an extrinsic evaluation assessing whether the reported speech filter could improve the detection of women reporting adverse pregnancy outcomes on Twitter.RESULTS: The tweets annotated as "outcome" include 1632 women reporting miscarriage, 119 stillbirth, 749 preterm birth or premature labor, 217 low birthweight, 558 NICU admission, and 458 fetal/infant loss in general. A deep neural network, BERT-based classifier achieved the highest overall F1-score (0.88) for automatically detecting "outcome" tweets (precision=0.87, recall=0.89), with an F1-score of at least 0.82 and a precision of at least 0.84 for each of the adverse pregnancy outcomes. Our reported speech filter significantly (P