多模态数据联合人工智能预测子痫前期的研究进展
Research Progress on the Prediction of Preeclampsia Using Multimodal Data Combined with Artificial Intelligence
DOI: 10.12677/md.2025.154048, PDF,    科研立项经费支持
作者: 王蒙蒙：延安大学医学院，陕西 延安；李 丽*：延安大学附属医院产科，陕西 延安
关键词: 人工智能；多模态数据；子痫前期；预测；Artificial Intelligence； Multimodal Data； Preeclampsia； Prediction
摘要: 子痫前期是妊娠期特有的严重并发症，对母婴健康构成重大威胁。早期预测和干预对改善妊娠结局至关重要。近年来，人工智能技术的快速发展为子痫前期的预测提供了新的思路和方法。本文综述了多模态数据联合人工智能在子痫前期预测中的研究进展，包括临床数据、生物标志物、影像学数据等多种模态数据的应用现状，探讨了人工智能模型在该领域的应用现状，并对未来的研究方向进行了展望。
Abstract: Preeclampsia is a severe pregnancy-specific complication that poses a significant threat to maternal and fetal health. Early prediction and intervention are crucial for improving pregnancy outcomes. In recent years, the rapid development of artificial intelligence (AI) technology has provided new approaches for the prediction of preeclampsia. This review summarizes the research progress on the prediction of preeclampsia using multimodal data combined with AI, including the current applications of various types of data such as clinical data, biomarkers, and imaging data. It also discusses the current status of AI models in this field and provides insights into future research directions.
文章引用：王蒙蒙, 李丽. 多模态数据联合人工智能预测子痫前期的研究进展[J]. 医学诊断, 2025, 15(4): 358-363. https://doi.org/10.12677/md.2025.154048

参考文献

[1] 张洋洋, 顾珣可, 王永清, 等. 子痫前期预测模型的研究进展[J]. 临床检验杂志, 2023, 41(4): 269-273.
[2] Cho, G.J., Jung, U.S., Kim, H.Y., Lee, S.B., Kim, M., Ahn, K., et al. (2021) Women with Multiple Gestations Have an Increased Risk of Development of Hypertension in the Future. BMC Pregnancy and Childbirth, 21, Article No. 510. [Google Scholar] [CrossRef] [PubMed]
[3] Dolgushina Valentina, F., Syundyukova Elena, G., Chulkov Vasiliy, S. and Ryabikina Marya, G. (2021) Long-Term Outcomes of Hypertensive Disorders of Pregnancy. Obstetrics and Gynecology, 10, 14-20.
[4] 谢幸, 孔北华, 段涛, 主编. 妇产科学[M]. 第9版. 北京: 人民卫生出版社, 2018: 83-89.
[5] Kanani, F., Asher, N., Majeed, M., Shuja, S., Ghouri, N. and Zubairi, A. (2024) Evaluation of sFLT-1/PLGF for Prediction of Pre-Eclampsia. Clinica Chimica Acta, 558, Article ID: 118951. [Google Scholar] [CrossRef] 
[6] Lubis, M.P. (2020) The Role of Predictor Placental Growth Factor, Soluble Endoglin, Soluble-FMS-Like-Tyrosine Kinase-1 and Pulsatil Uterina Arterial Index to Predict the Early Onset of Preeclampsia. International Journal of Current Pharmaceutical Research, 12, 45-57. [Google Scholar] [CrossRef] 
[7] 苏小梅, 郑楚豪, 付安. PLGF、PAPP-A与Hcy联合检测对孕早期先兆流产的预测价值[J]. 中国医学创新, 2024, 21(24): 121-124.
[8] 刘纪君, 李雪蕾, 陈红波, 韩保良, 邵坤, 赵雪芬, 刘静, 晏艳, 许晓红. 孕早期PlGF联合PAPP-A、MAP、UtPI预测子痫前期的临床应用研究[J]. 临床输血与检验, 2022, 24(4): 476-481.
[9] Droste, L., Fox, L., Gellhaus, A. and Birdir, C. (2018) Prospektive Analyse der maternalen Serumwerte von PlGF, sFlt-1, PAPP-A und MR-proANP im 3. Trimenon für die Prädiktion der late-onset Präeklampsie, der intrauterinen Wachstumsretardierung und der Schwangerschafts-induzierten Hypertonie. Geburtshilfe und Frauenheilkunde, 78, A14. [Google Scholar] [CrossRef] 
[10] Karadzov Orlic, N. and Joksić, I. (2025) Preeclampsia Pathogenesis and Prediction—Where Are We Now: The Focus on the Role of Galectins and miRNAs. Hypertension in Pregnancy, 44, Article ID: 2470626. [Google Scholar] [CrossRef] [PubMed]
[11] Puttaiah, A., Kirthan, J.P.A., Sadanandan, D.M. and Somannavar, M.S. (2024) Inflammatory Markers and Their Association with Preeclampsia among Pregnant Women: A Systematic Review and Meta-Analysis. Clinical Biochemistry, 129, Article ID: 110778. [Google Scholar] [CrossRef] [PubMed]
[12] Gupta, T., Arora, S., Kumar, A., Gupta, N. and Gupta, S. (2017) Evaluation of Maternal Serum Levels of Cell Adhesion Molecules and Endothelial Inflammatory Markers in Normal Pregnancy, Gestational Hypertension and Pre-Eclampsia. International Journal of Reproduction, Contraception, Obstetrics and Gynecology, 6, 2231-2237. [Google Scholar] [CrossRef] 
[13] Karpagam, R.K., Ramakrishnan, K.K., Gunasekaran, D., Aram, A. and Natarajan, P. (2024) Role of Uterine Artery Doppler Study Between 11 and 14 Weeks as a Predictor of Preeclampsia. Cureus, 16, e63591.
[14] Bonacina, E., Del Barco, E., Farràs, A., Dalmau, M., Garcia, E., Gleeson‐Vallbona, L., et al. (2024) Role of Routine Uterine Artery Doppler at 18-22 and 24-28 Weeks’ Gestation Following Routine First‐Trimester Screening for Pre‐eclampsia. Ultrasound in Obstetrics & Gynecology, 65, 63-70. [Google Scholar] [CrossRef] [PubMed]
[15] Jagdish, S., Kiruthiga, T., Prashanth, S., Vijayaraghavan, J. and Palanisamy, S.T. (2024) Role of Soluble fms-Like Tyrosine Kinase-1/Placental Growth Factor Ratio along with Uterine Artery Doppler for the Prediction of Pre-Eclampsia—A Case-Control Study. Asian Journal of Medical Sciences, 15, 133-138. [Google Scholar] [CrossRef] 
[16] 周天凡, 邵飞雪, 万盛, 周晨晨, 周思锦, 花晓琳. 基于人工智能模型量化视网膜血管特征参数预测子痫前期的可行性研究[J]. 上海交通大学学报(医学版), 2024, 44(5): 552-559.
[17] Bari, F., Nasreen, R. and Rahman, T. (2019) Role of Color Doppler Ultrasound to Evaluate Preeclampsia. Ultrasound in Medicine & Biology, 45, S81. [Google Scholar] [CrossRef] 
[18] Zhang, N., Yang, L., Han, A., Wang, Y., Zhao, G., Wang, Y., et al. (2023) Advances in Imaging Findings of Preeclampsia-Related Reversible Posterior Leukoencephalopathy Syndrome. Frontiers in Neuroscience, 17, Article 1144867. [Google Scholar] [CrossRef] [PubMed]
[19] Aughwane, R., Ingram, E., Johnstone, E.D., Salomon, L.J., David, A.L. and Melbourne, A. (2019) Placental MRI and Its Application to Fetal Intervention. Prenatal Diagnosis, 40, 38-48. [Google Scholar] [CrossRef] [PubMed]
[20] 吕伯瀚. 基于机器学习的子痫前期预测模型构建与评价[D]: [硕士学位论文]. 青岛: 青岛大学, 2022.
[21] Villalaín, C., Herraiz, I., Domínguez-Del Olmo, P., Angulo, P., Ayala, J.L. and Galindo, A. (2022) Prediction of Delivery within 7 Days after Diagnosis of Early Onset Preeclampsia Using Machine-Learning Models. Frontiers in Cardiovascular Medicine, 9, Article 910701. [Google Scholar] [CrossRef] [PubMed]
[22] 许兴能, 陈胜柱, 周嘉怡, 等. Logistic回归法和机器学习算法构建子痫前期预测模型的比较[J]. 中华围产医学杂志, 2024, 27(7): 572-581.
[23] Schmidt, L.J., Rieger, O., Nexanski, M., Hackelöer, M., Dröge, L.A., Henrich, W., et al. (2023) A Machine-Learning-Based Algorithm Improves Prediction of Preeclampsia-Associated Adverse Outcomes. Obstetric Anesthesia Digest, 43, 81-82. [Google Scholar] [CrossRef] 
[24] Zhou, T., Gu, S., Shao, F., Li, P., Wu, Y., Xiong, J., et al. (2024) Prediction of Preeclampsia from Retinal Fundus Images via Deep Learning in Singleton Pregnancies: A Prospective Cohort Study. Journal of Hypertension, 42, 701-710. [Google Scholar] [CrossRef] [PubMed]
[25] 冯薇, 伊诺. FCNN模型对妊娠早期高血压和子痫前期-子痫发病风险的预测价值[J]. 转化医学杂志, 2023, 12(4): 180-184.