Применение моделей искусственного интеллекта на мультипараметрических наборах данных для прогнозирования осложнений беременности

Цель: провести сравнительный анализ прогностической эффективности моделей искусственного интеллекта (ИИ) и машинного обучения (МО), разработанных на мультипараметрических наборах данных, для прогнозирования преэклампсии (ПЭ) и акушерских кровотечений.

Материалы и методы. Систематический обзор выполнен согласно PRISMA. Поиск проведен в PubMed и Cochrane Central за 2015–2025 гг. Включались исследования с ИИ/МО, использующие ≥ 2 предикторов/классов данных и оценивающие ПЭ/эклампсию или акушерские кровотечения (включая послеродовые). Риск систематической ошибки оценивали с помощью инструмента ROBINS-I (англ. Risk Of Bias In Non-randomized Studies of Interventions; риск систематической ошибки в нерандомизированных исследованиях) и шкалы Ньюкасл–Оттава (англ. Newcastle–Ottawa Scale, NOS).

Результаты. В обзор включены 28 исследований (18 по ПЭ, 10 по кровотечениям). Наиболее часто применялись градиентный бустинг, случайный лес, XGBoost и нейросетевые модели. Для ПЭ наилучшие результаты чаще демонстрировали модели, объединяющие материнские факторы риска с показателями артериального давления и компонентами скрининга I триместра (доплерометрия маточных артерий и плацентарные биомаркеры). Для прогнозирования кровотечений наиболее перспективными оказались подходы на базе электронных медицинских карт и предоперационных клинико-лабораторных данных, включая риск-стратификацию у пациенток с предлежанием плаценты (placenta previa) и врастанием плаценты (placenta accreta spectrum, PAS). Основным ограничением доказательной базы остаются преобладание ретроспективных дизайнов и дефицит внешней/проспективной валидации, что снижает переносимость моделей между клиниками и во времени.

Заключение. Модели ИИ, обученные на мультипараметрических данных мониторинга, способны улучшать прогнозирование ПЭ и акушерских кровотечений, однако клиническое внедрение требует стандартизированной отчетности, внешней проверки и контроля калибровки моделей в реальной практике.

1. World Health Organization, United Nations Children’s Fund, United Nations Population Fund, World Bank Group, United Nations Population Division. Trends in maternal mortality 2000 to 2017: estimates by WHO, UNICEF, UNFPA, World Bank Group and the United Nations Population Division. Geneva: World Health Organization, 2019. Available at: https://www.who.int/publications/i/item/9789241516488. [Accessed: 15.01.2026].

2. Zhang Y., Ding W., Wu T. et al. Pregnancy with multiple high-risk factors: a systematic review and meta-analysis. J Glob Health. 2025;15:04027. https://doi.org/10.7189/jogh.15.04027.

3. Edwards P., Wright G. Obesity in pregnancy. Obstet Gynaecol Reprod Med. 2020;30(10):315–20. https://doi.org/10.1016/j.ogrm.2020.07.003.

4. Briganti G., Le Moine O. Artificial intelligence in medicine: today and tomorrow. Front Med (Lausanne). 2020;7:27. https://doi.org/10.3389/fmed.2020.00027.

5. Sanchez P., Voisey J.P., Xia T. et al. Causal machine learning for healthcare and precision medicine. R Soc Open Sci. 2022;9(8):220638. https://doi.org/10.1098/rsos.220638.

6. Frizzell J.D., Liang L., Schulte P.J. et al. Prediction of 30-day all-cause readmissions in patients hospitalized for heart failure: comparison of machine learning and other statistical approaches. JAMA Cardiol. 2017;2(2):204–9. https://doi.org/10.1001/jamacardio.2016.3956.

7. Sivakumar M., Parthasarathy S., Padmapriya T. Trade-off between training and testing ratio in machine learning for medical image processing. Peer J Comput Sci. 2024;10:e2245. https://doi.org/10.7717/peerj-cs.2245.

8. Plevris V., Solorzano G., Bakas N.P., Ben Seghier M.E.A. Investigation of performance metrics in regression analysis and machine learning-based prediction models. In: 8th European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS 2022), 2022 Jun 5–9; Oslo, Norway. CIMNE, 2022. https://doi.org/10.23967/eccomas.2022.155.

9. Ansbacher-Feldman Z., Syngelaki A., Meiri H. et al. Machine-learning-based prediction of pre-eclampsia using first-trimester maternal characteristics and biomarkers. Ultrasound Obstet Gynecol. 2022;60(6):739–45. https://doi.org/10.1002/uog.26105.

10. Gil M.M., Cuenca-Gómez D., Rolle V. et al. Validation of machine-learning model for first-trimester prediction of pre-eclampsia using cohort from PREVAL study. Ultrasound Obstet Gynecol. 2024;63(1):68–74. https://doi.org/10.1002/uog.27478.

11. Li T., Xu M., Wang Y. et al. Prediction model of preeclampsia using machine learning based methods: a population based cohort study in China. Front Endocrinol (Lausanne). 2024;15:1345573. https://doi.org/10.3389/fendo.2024.1345573.

12. Liang H., Zhao X., Zhang Y. et al. A comprehensive first-trimester predictive model for preeclampsia based on multi-indicators and machine learning: a retrospective single-center study. Medicine (Baltimore). 2025;104(47):e45555. https://doi.org/10.1097/MD.0000000000045555.

13. Zhao Z., Dai J., Chen H. et al. A prospective study on risk prediction of preeclampsia using bi-platform calibration and machine learning. Int J Mol Sci. 2024;25(19):10684. https://doi.org/10.3390/ijms251910684.

14. Kovacheva V.P., Eberhard B.W., Cohen R.Y. et al. Preeclampsia prediction using machine learning and polygenic risk scores from clinical and genetic risk factors in early and late pregnancies. Hypertension. 2024;81(2):264–72. https://doi.org/10.1161/HYPERTENSIONAHA.123.21053.

15. Li Y.X., Shen X.P., Yang C., et al. Novel electronic health records applied for prediction of pre-eclampsia: machine-learning algorithms. Pregnancy Hypertens. 2021;26:102–9. https://doi.org/10.1016/j.preghy.2021.10.006.

16. Jhee J.H., Lee S., Park Y. et al. Prediction model development of late-onset preeclampsia using machine learning-based methods. PLoS One. 2019;14(8):e0221202. https://doi.org/10.1371/journal.pone.0221202.

17. Chen S., Li J., Zhang X. et al. Predicting preeclampsia in early pregnancy using clinical and laboratory data via machine learning model. BMC Med Inform Decis Mak. 2025;25(1):178. https://doi.org/10.1186/s12911-025-02999-5.

18. Lin Y.C., Mallia D., Clark-Sevilla A.O. et al. A comprehensive and bias-free machine learning approach for risk prediction of preeclampsia with severe features in a nulliparous study cohort. BMC Pregnancy Childbirth. 2024;24(1):853. https://doi.org/10.1186/s12884-024-06988-w.

19. Tiruneh S.A., Rolnik D.L., Teede H.J., Enticott J. Prediction of pre-eclampsia with machine learning approaches: leveraging important information from routinely collected data. Int J Med Inform. 2024;192:105645. https://doi.org/10.1016/j.ijmedinf.2024.105645.

20. Tiruneh S.A., Rolnik D.L., Teede H.J., Enticott J. Temporal validation of machine learning models for pre-eclampsia prediction using routinely collected maternal characteristics: a validation study. Comput Biol Med. 2025;191:110183. https://doi.org/10.1016/j.compbiomed.2025.110183.

21. Shyu I.-L., Liu C.-F., Tsai Y.-C. et al. Machine learning predictive system to predict the risk of developing pre-eclampsia. BMJ Health Care Inform. 2025;32(1):e101151. https://doi.org/10.1136/bmjhci-2024-101151.

22. Eberhard B.W., Gray K.J., Bates D.W., Kovacheva V.P. Deep survival analysis for interpretable time-varying prediction of preeclampsia risk. J Biomed Inform. 2024;156:104688. https://doi.org/10.1016/j.jbi.2024.104688.

23. Eberhard B.W., Cohen R.Y., Wheeler N. et al. Development and validation of an interpretable longitudinal preeclampsia risk prediction using machine learning. PLoS One. 2025;20(6):e0323873. https://doi.org/10.1371/journal.pone.0323873.

24. Bennett R., Mulla Z.D., Parikh P. et al. An imbalance-aware deep neural network for early prediction of preeclampsia. PLoS One. 2022;17(4):e0266042. https://doi.org/10.1371/journal.pone.0266042.

25. Sufriyana H., Wu Y.-W., Su E.C.-Y. Artificial intelligence-assisted prediction of preeclampsia: development and external validation of a nationwide health insurance dataset of the BPJS Kesehatan in Indonesia. EBioMedicine. 2020;54:102710. https://doi.org/10.1016/j.ebiom.2020.102710.

26. Chen Y., Shi X., Wang Z., Zhang L. Machine learning-based management of hypertensive disorders in pregnancy: analysis of differences in key risk factors between gestational hypertension and pre-eclampsia and construction of a pre-eclampsia prediction model. Eur J Med Res. 2025;30(1):1135. https://doi.org/10.1186/s40001-025-03407-4.

27. Westcott J.M., Hughes F., Liu W. et al. Prediction of maternal hemorrhage using machine learning: retrospective cohort study. J Med Internet Res. 2022;24(7):e34108. https://doi.org/10.2196/34108.

28. Krishnamoorthy S., Liu Y., Liu K. A novel oppositional binary crow search algorithm with optimal machine learning based postpartum hemorrhage prediction model. BMC Pregnancy Childbirth. 2022;22(1):560. https://doi.org/10.1186/s12884-022-04775-z.

29. Akazawa M., Hashimoto K., Noda K., Yoshida K. Machine learning approach for the prediction of postpartum hemorrhage in vaginal birth. Sci Rep. 2021;11(1):22620. https://doi.org/10.1038/s41598-021-02198-y.

30. Song Z., Lin H., Shao M., et al. Integrating SHAP analysis with machine learning to predict postpartum hemorrhage in vaginal births. BMC Pregnancy Childbirth. 2025;25(1):529. https://doi.org/10.1186/s12884-025-07633-w.

31. Holcroft S., Karangwa I., Little F. et al. Predictive modelling of postpartum haemorrhage using early risk factors: a comparative analysis of statistical and machine learning models. Int J Environ Res Public Health. 2024;21(5):600. https://doi.org/10.3390/ijerph21050600.

32. Akazawa M., Hashimoto K. A multimodal deep learning model for predicting severe hemorrhage in placenta previa. Sci Rep. 2023;13(1):17320. https://doi.org/10.1038/s41598-023-44634-1.

33. Li M., Su X., Liao W., et al. Development and validation of an interpretable machine learning-based prediction model of postpartum hemorrhage in placenta previa following cesarean section: a multicenter study. Reprod Sci. 2025;32(9):3062–73. https://doi.org/10.1007/s43032-025-01937-0.

34. Wang M., Yi G., Zhang Y. et al. Quantitative prediction of postpartum hemorrhage in cesarean section on machine learning. BMC Med Inform Decis Mak. 2024;24(1):166. https://doi.org/10.1186/s12911-024-02571-7.

35. Miller S., Lyell D., Maric I. et al. Predicting placenta accreta spectrum disorder through machine learning using metabolomic and lipidomic profiling and clinical characteristics. Obstet Gynecol. 2025;145(6):721–31. https://doi.org/10.1097/AOG.0000000000005922.

36. Susanu C., Hărăbor A., Vasilache I.-A. et al. Predicting intra- and postpartum hemorrhage through artificial intelligence. Medicina (Kaunas). 2024;60(10):1604. https://doi.org/10.3390/medicina60101604.

37. Silasi M., Azzi M., Potchileev S. et al. Placental biomarker testing for evaluation of suspected preeclampsia. Clin Chem. 2025;71(5):548–58. https://doi.org/10.1093/clinchem/hvaf024.

38. Rolnik D.L., Nicolaides K.H., Poon L.C. Prevention of preeclampsia with aspirin. Am J Obstet Gynecol. 2022;226(2):S1108–S1119. https://doi.org/10.1016/j.ajog.2020.08.045.