Nogueira Mariana, Aparício Sandra Lopes, Duarte Ivone, Silvestre Margarida
Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal.
RISE-Health, Health Research and Innovation, Faculty of Medicine, University of Porto, 4200-319 Porto, Portugal.
J Clin Med. 2025 May 30;14(11):3860. doi: 10.3390/jcm14113860.
: Adverse pregnancy outcomes (APOs), which include hypertensive disorders of pregnancy (gestational hypertension, preeclampsia, and related disorders), gestational diabetes, preterm birth, fetal growth restriction, low birth weight, small-for-gestational-age newborn, placental abruption, and stillbirth, are health risks for pregnant women that can have fatal outcomes. This study's aim is to investigate the usefulness of artificial intelligence (AI) in improving these outcomes and includes changes in the utilization of ultrasound, continuous monitoring, and an earlier prediction of complications, as well as being able to individualize processes and support clinical decision-making. This study evaluates the use of AI in improving at least one APO. : PubMed, Web of Science, and Scopus databases were searched and limited to the English language, humans, and between 2020 and 2024. This scoping review included peer-reviewed articles across any study design. However, systematic reviews, meta-analyses, unpublished studies, and grey literature sources (e.g., reports and conference abstracts) were excluded. Studies were eligible for inclusion if they described the use of AI in improving APOs and the associated ethical issues. : Five studies met the inclusion criteria and were included in this scoping review. Although this review initially aimed to evaluate AI's role across a wide range of APOs, including placental abruption and stillbirth, the five selected studies focused primarily on preterm birth, hypertensive disorders of pregnancy, and gestational diabetes. None of the included studies addressed placental abruption or stillbirth directly. The studies primarily utilized machine-learning models, including extreme gradient boosting (XGBoost) and random forest (RF), showing promising results in enhancing prenatal care and supporting clinical decision-making. Ethical considerations, including algorithmic bias, transparency, and the need for regulatory oversight, were highlighted as critical challenges. : The application of these tools can improve prenatal care by predicting obstetric complications, but ethics and transparency are pivotal. Empathy and humanization in healthcare must remain fundamental, and flexible training mechanisms are needed to keep up with rapid innovation. AI offers an opportunity to support, not replace, the doctor-patient relationship and must be subject to strict legislation if it is to be used safely and fairly.
不良妊娠结局（APO）包括妊娠高血压疾病（妊娠期高血压、子痫前期及相关疾病）、妊娠期糖尿病、早产、胎儿生长受限、低出生体重、小于胎龄儿、胎盘早剥和死产，这些都是孕妇面临的健康风险，可能会导致致命后果。本研究的目的是调查人工智能（AI）在改善这些结局方面的作用，包括超声使用的变化、持续监测、并发症的早期预测，以及能够实现流程个性化并支持临床决策。本研究评估了AI在改善至少一种不良妊娠结局方面的应用。在PubMed、科学网和Scopus数据库中进行了检索，限定语言为英语、研究对象为人类且时间范围在2020年至2024年之间。本范围综述纳入了任何研究设计的同行评审文章。然而，系统评价、荟萃分析、未发表的研究以及灰色文献来源（如报告和会议摘要）被排除在外。如果研究描述了AI在改善不良妊娠结局方面的应用及相关伦理问题，则有资格被纳入。五项研究符合纳入标准并被纳入本范围综述。尽管本综述最初旨在评估AI在广泛的不良妊娠结局（包括胎盘早剥和死产）中的作用，但所选的五项研究主要集中在早产、妊娠高血压疾病和妊娠期糖尿病。纳入的研究均未直接涉及胎盘早剥或死产。这些研究主要使用机器学习模型，包括极端梯度提升（XGBoost）和随机森林（RF），在加强产前护理和支持临床决策方面显示出有前景的结果。算法偏差、透明度以及监管监督的必要性等伦理考量被强调为关键挑战。这些工具的应用可以通过预测产科并发症来改善产前护理，但伦理和透明度至关重要。医疗保健中的同理心和人性化必须始终是根本，需要灵活的培训机制来跟上快速的创新。AI提供了支持医患关系而非取代它的机会，如果要安全、公平地使用AI，就必须有严格的立法。
