akusherstvoObstetrics, Gynecology and ReproductionАкушерство, Гинекология и Репродукция2313-73472500-3194IRBIS LLC10.17749/2313-7347/ob.gyn.rep.2025.750akusherstvo-2924Research ArticleORIGINAL ARTICLEОРИГИНАЛЬНОЕ ИССЛЕДОВАНИЕIncremental value of biophysical and biochemical first trimester markers for predicting early and late preeclampsia: a nested model analysisИнкрементальная ценность биофизических и биохимических маркеров первого триместра беременности для прогнозирования ранней и поздней преэклампсии: анализ вложенных моделейhttps://orcid.org/0000-0001-7834-096XИвшинА. А.IvshinA. A.

Ившин Александр Анатольевич, к.м.н. 

Scopus Author ID: 57222275843.

WoS ResearcherID: AAG-1507-2020.

eLibrary SPIN-code: 8196-6605.

185910 Петрозаводск, проспект Ленина, д. 33 

Alexandr A. Ivshin, МD, PhD.

Scopus Author ID: 57222275843.

WoS ResearcherID: AAG-1507-2020.

eLibrary SPIN-code: 8196-6605.

33 Lenin Avenue, Petrozavodsk 185910

scipeople@mail.ruhttps://orcid.org/0000-0002-1450-650XБолдинаЮ. С.BoldinaYu. S.

Болдина Юлия Сергеевна

Scopus Author ID: 57356202000.

WoS ResearcherID: PII-8685-2026.

eLibrary SPIN-code: 2944-0409.

185910 Петрозаводск, проспект Ленина, д. 33 

Yuliya S. Boldina, МD.

Scopus Author ID: 57356202000.

WoS ResearcherID: PII-8685-2026.

eLibrary SPIN-code: 2944-0409.

33 Lenin Avenue, Petrozavodsk 185910

https://orcid.org/0009-0005-2722-5976МалышевН. А.MalyshevN. A.

Малышев Никита Андреевич 

WoS ResearcherID: OVY-0768-2025.

185910 Петрозаводск, проспект Ленина, д. 33 

Nikita A. Malyshev, МD.

WoS ResearcherID: OVY-0768-2025.

33 Lenin Avenue, Petrozavodsk 185910

ФГБОУ ВО «Петрозаводский государственный университет»РоссияPetrozavodsk State UniversityRussian Federation20260409202600Online First2924Copyright © Ivshin A.A., Boldina Y.S., Malyshev N.A., 20262026Ившин А.А., Болдина Ю.С., Малышев Н.А.Ivshin A.A., Boldina Y.S., Malyshev N.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.gynecology.su/jour/article/view/2924Aim

Aim: to compare the discriminative ability and calibration of nested-architecture machine learning (ML) models and the Fetal Medicine Foundation (FMF) algorithm for predicting early-onset (< 34 weeks) and late-onset (≥ 34 weeks) preeclampsia (PE) in the first trimester of pregnancy in Russian population.

Materials and Methods

Materials and Methods. with 23,247 singleton pregnancies was carried out. The biophysical sample comprised 22,230 observations, and the biochemical subsample included 7,581 observations. Nested ML models were developed: M0 (maternal characteristics) → M2 [(M0 + biophysical markers – mean arterial pressure (MAP) and uterine artery pulsatility index (UtAPI)] → M4 (M2 + biochemical markers – placental growth factor (PlGF), soluble fms-like tyrosine kinase-1 (sFlt-1) and pregnancy-associated plasma protein-A (PAPP-A)]. A comparison was made with the FMF algorithms – prior FMF risk (FMF prior) and posterior FMF risk (FMF posterior). Metrics included: AUC-ROC (Area Under the Receiver Operating Characteristic curve) with 95 % confidence interval (CI) calculated by the bootstrap method (n = 2000); the observed-to-expected ratio (O:E ratio); incremental value of biomarkers – change in C-statistic (ΔC), net reclassification improvement (NRI), integrated discrimination improvement (IDI), and sensitivity at fixed false-positive rates. Statistical significance of AUC differences was assessed using the DeLong test.

Results

Results. The AUC of model M4 for early-onset PE (EOPE) was 0.972 (95 % CI = 0.947–0.991) compared with 0.951 for FMF posterior (p = 0.368); for late-onset PE (LOPE), the AUC was 0.871 (95 % CI = 0.833–0.906) versus 0.822 for FMF posterior (p = 0.009). After Platt scaling recalibration, the ML models demonstrated adequate calibration (O:E ≈ 1.0). FMF posterior demonstrates inadequate calibration for LOPE in the Russian population (O:E = 3.34; 95 % CI = 2.61–4.21), indicating 3.34-fold more LOPE cases than predicted by the model. Biophysical markers provided 4-fold greater incremental value for EOPE (ΔC = +0.029 vs. +0.007), while biochemical markers were more valuable for LOPE (ΔC = +0.020 vs. +0.001). For EOPE the UtAPI was a lead predictor (odds ratio (OR) = 3.28; 95 % CI = 2.68–4.70), for LOPE – previous PE (OR = 1.90; 95 % CI = 1.72–2.09).

Conclusion

Conclusion. ML models significantly outperform the FMF algorithm in discriminating late preeclampsia and provide substantially better calibration in Russian population. The inadequacy of the FMF algorithm for LOPE (O:E = 3.34 indicates 3.3-fold more LOPE cases than predicted) justifies the need for specialized models for this phenotype. Differential incremental value of biomarkers was established: biophysical markers (UtAPI) are critical for EOPE, biochemical markers (PlGF, sFlt-1) – for LOPE, supporting the concept of contingent screening.

Цель

Цель: провести сравнительную оценку дискриминационной способности и калибровки моделей машинного обучения (англ. Machine Learning, ML) вложенной архитектуры и алгоритма Фонда фетальной медицины (англ. Fetal Medicine Foundation, FMF) для прогнозирования ранней (< 34 недель) и поздней (> 34 недель) преэклампсии (ПЭ) в I триместре беременности на российской популяции.

Материалы и методы

Материалы и методы. Ретроспективное когортное исследование включало 23247 одноплодных беременностей. Биофизическая выборка составила 22230, биохимическая выборка – 7581 наблюдение. Разработаны ML-модели вложенной архитектуры: M0 (модель включает клинико-анамнестические факторы) → M2 [модель М0 дополнена биофизическими маркерами – средним артериальным давлением (англ. mean arterial pressure, MAP) и пульсационным индексом маточных артерий (англ. uterine artery pulsatility index, UtAPI)] → M4 [модель М2 дополнена биохимическими маркерами – плацентарным фактором роста (англ. placental growth factor, PlGF), растворимой fms-подобной тирозинкиназой-1 (англ. soluble fms-like tyrosine kinase-1, sFlt-1) и ассоциированным с беременностью протеином-А плазмы (англ. pregnancy-associated plasma protein-A, PAPP-A)]. Проведено сравнение с алгоритмами FMF – априорный риск FMF (англ. FMF prior) и апостериорный риск FMF (англ. FMF posterior). Оценивались: AUC-ROC (англ. Area Under the Receiver Operating Characteristic curve; площадь под кривой рабочих характеристик приемника) с 95 % доверительным интервалом (ДИ), рассчитанная методом многократной случайной выборки с возвращением (англ. bootstrap; n = 2000); соотношение наблюдаемых и ожидаемых событий O:E (англ. observed-to-expected ratio, O:E ratio); инкрементальная ценность биомаркеров – прирост С-статистики (ΔC), непрерывный индекс реклассификации (англ. net reclassification improvement, NRI), интегральный индекс улучшения дискриминации (англ. integrated discrimination improvement, IDI); чувствительность при фиксированной доле ложноположительных результатов. Статистическая значимость различий AUC оценивалась тестом DeLong.

Результаты

Результаты. AUC модели M4 для ранней ПЭ составила 0,972 (95 % ДИ = 0,947–0,991) по сравнению с AUC апостериорного риска FMF (FMF posterior), составившей 0,951 (p = 0,368); для поздней ПЭ AUC составила 0,871 (95 % ДИ = 0,833–0,906) против 0,822 для FMF posterior (p = 0,009). ML-модели продемонстрировали адекватную калибровку после рекалибровки методом Платта (англ. Platt scaling; логистическая рекалибровка) (O:E ≈ 1,0). Установлено, что алгоритм FMF posterior ограниченно применим для прогнозирования поздней ПЭ в российской популяции: O:E ratio = 3,34 (95 % ДИ = 2,61–4,21) указывает, что поздних ПЭ возникает в 3,3 раза больше, чем прогнозирует модель. Биофизические маркеры обеспечивают 4-кратно больший инкремент для ранней ПЭ (ΔC = +0,029 vs. +0,007), биохимические – для поздней ПЭ (ΔC = +0,020 vs. +0,001). Ведущий предиктор ранней ПЭ – UtAPI (odds ratio (OR) = 3,28; 95 % ДИ = 2,68–4,70), поздней ПЭ – ПЭ в анамнезе (OR = 1,90; 95 % ДИ = 1,72–2,09).

Заключение

Заключение. ML-модели статистически значимо превосходят алгоритм FMF по дискриминации для поздней ПЭ и обеспечивают существенно лучшую калибровку в российской популяции. Ограниченность алгоритма FMF для поздней ПЭ (O:E = 3,34 – поздних ПЭ в 3,3 раза больше прогноза) обосновывает необходимость применения специализированных моделей для данного фенотипа. Установлена дифференцированная инкрементальная ценность биомаркеров: биофизические маркеры (UtAPI) критичны для ранней ПЭ, биохимические (PlGF, sFlt-1) – для поздней, что обосновывает концепцию этапного скрининга.

преэклампсияПЭпрогнозированиепервый триместрмашинное обучениеMLФонд фетальной медициныFMFалгоритм FMFкалибровкавалидацияроссийская популяцияплацентарный фактор ростаPlGFпульсационный индекс маточных артерийUtAPIpreeclampsiaPEpredictionfirst trimestermachine learningMLFetal Medicine FoundationFMFFMF algorithmcalibrationvalidationRussian populationplacental growth factorPlGFuterine artery pulsatility indexUtAPIReferencesСидорова И.С., Никитина Н.А., Филиппов О.С., Гусева Е.В. Решенные и нерешенные вопросы преэклампсии по результатам анализа материнской смертности за последние 10 лет. Акушерство и гинекология. 2021;(4):64–72. https://doi.org/10.18565/aig.2021.4.64-74.Sidorova I.S., Nikitina N.A., Filippov O.S., Guseva E.V. Solved and unsolved issues of preeclampsia based on the analysis of maternal mortality over the past 10 years. Akusherstvo i ginekologiya. 2021;(4):64–72. (In Russ.). https://doi.org/10.18565/aig.2021.4.64-74.Клинические рекомендации – Преэклампсия. Эклампсия. Отеки, протеинурия и гипертензивные расстройства во время беременности, в родах и послеродовом периоде – 2024 (15.01.2025). М.: Министерство здравоохранения Российской Федерации, 2024. 43 с. Режим доступа: https://www.consultant.ru/cons/cgi/online.cgi?req=doc&base=LAW&n=485411&dst=100001#noHiNFVsRFLrFt9f1. [Дата обращения: 30.03.2026].Clinical guidelines – Preeclampsia. Eclampsia. Edema, proteinuria, and hypertensive disorders during pregnancy, childbirth, and the postpartum period – 2024 (15.01.2025). [Klinicheskie rekomendacii – Preeklampsiya. Eklampsiya. Oteki, proteinuriya i gipertenzivnye rasstrojstva vo vremya beremennosti, v rodah i poslerodovom periode – 2024 (15.01.2025)]. Moscow: Ministerstvo zdravoohraneniya Rossijskoj Federacii, 2024. 43 p. (In Russ.). Available at: https://www.consultant.ru/cons/cgi/online.cgi?req=doc&base=LAW&n=485411&dst=100001#noHiNFVsRFLrFt9f1. [Accessed: 30.03.2026].Сидорова И.С., Никитина Н.А. Преэклампсия и снижение материнской смертности в России. Акушерство и гинекология. 2018;(1):89–97. https://doi.org/10.18565/aig.2018.1.89-97.Sidorova I.S., Nikitina N.A. Preeclampsia and reduction of maternal mortality in Russia. Akusherstvo i ginekologiya. 2018;(1):89–97. (In Russ.). https://doi.org/10.18565/aig.2018.1.89-97.Борис Д.А., Шмаков Р.Г. Преэклампсия: современные концепции патогенеза. Акушерство и гинекология. 2022;(12):5–14. https://doi.org/10.18565/aig.2022.12.5-14.Boris D.A., Shmakov R.G. Preeclampsia: modern concepts of pathogenesis. Akusherstvo i ginekologiya. 2022;(12):5–14. (In Russ.). https://doi.org/10.18565/aig.2022.12.5-14.Nicolaides K.H. Turning the pyramid of prenatal care. Fetal Diagn Ther. 2011;29(3):183–96. https://doi.org/10.1159/000324320.Nicolaides K.H. Turning the pyramid of prenatal care. Fetal Diagn Ther. 2011;29(3):183–96. https://doi.org/10.1159/000324320.Gallo D.M., Wright D., Casanova C. et al. Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 19-24 weeks’ gestation. Am J Obstet Gynecol. 2016;214(5):619.e1-619.e17. https://doi.org/10.1016/j.ajog.2015.11.016.Gallo D.M., Wright D., Casanova C. et al. Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 19-24 weeks’ gestation. Am J Obstet Gynecol. 2016;214(5):619.e1-619.e17. https://doi.org/10.1016/j.ajog.2015.11.016.Akolekar R., Syngelaki A., Poon L. et al. Competing risks model in early screening for preeclampsia by biophysical and biochemical markers. Fetal Diagn Ther. 2013;33(1):8–15. https://doi.org/10.1159/000341264.Akolekar R., Syngelaki A., Poon L. et al. Competing risks model in early screening for preeclampsia by biophysical and biochemical markers. Fetal Diagn Ther. 2013;33(1):8–15. https://doi.org/10.1159/000341264.O’Gorman N., Wright D., Syngelaki A. et al. Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 11-13 weeks gestation. Am J Obstet Gynecol. 2016;214(1):103.e1–103.e12. https://doi.org/10.1016/j.ajog.2015.08.034.O’Gorman N., Wright D., Syngelaki A. et al. Competing risks model in screening for preeclampsia by maternal factors and biomarkers at 11-13 weeks gestation. Am J Obstet Gynecol. 2016;214(1):103.e1–103.e12. https://doi.org/10.1016/j.ajog.2015.08.034.Rolnik D.L., Wright D., Poon L.C. et al. Aspirin versus placebo in pregnancies at high risk for preterm preeclampsia. N Engl J Med. 2017;377(7):613–22. https://doi.org/10.1056/NEJMoa1704559.Rolnik D.L., Wright D., Poon L.C. et al. Aspirin versus placebo in pregnancies at high risk for preterm preeclampsia. N Engl J Med. 2017;377(7):613–22. https://doi.org/10.1056/NEJMoa1704559.Poon L.C., Shennan A., Hyett J.A. et al. The International Federation of Gynecology and Obstetrics (FIGO) initiative on pre-eclampsia: A pragmatic guide for first-trimester screening and prevention. Int J Gynaecol Obstet. 2019;145(Suppl 1):1–33. https://doi.org/10.1002/ijgo.12802.Poon L.C., Shennan A., Hyett J.A. et al. The International Federation of Gynecology and Obstetrics (FIGO) initiative on pre-eclampsia: A pragmatic guide for first-trimester screening and prevention. Int J Gynaecol Obstet. 2019;145(Suppl 1):1–33. https://doi.org/10.1002/ijgo.12802.ACOG Practice Bulletin No. 222: Gestational Hypertension and Preeclampsia. Obstet Gynecol. 2020;135(6):e237–e260. https://doi.org/10.1097/AOG.0000000000003891.ACOG Practice Bulletin No. 222: Gestational Hypertension and Preeclampsia. Obstet Gynecol. 2020;135(6):e237–e260. https://doi.org/10.1097/AOG.0000000000003891.NICE Guideline [NG133]. Hypertension in pregnancy: diagnosis and management. London: National Institute for Health and Care Excellence, 2019. 55 p.NICE Guideline [NG133]. Hypertension in pregnancy: diagnosis and management. London: National Institute for Health and Care Excellence, 2019. 55 p.Montgomery-Csobán T., Kavanagh K., Murray P. et al. Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study. Lancet Digit Health. 2024;6(2):e91–e100. https://doi.org/10.1016/S2589-7500(23)00267-4.Montgomery-Csobán T., Kavanagh K., Murray P. et al. Machine learning-enabled maternal risk assessment for women with pre-eclampsia (the PIERS-ML model): a modelling study. Lancet Digit Health. 2024;6(2):e91–e100. https://doi.org/10.1016/S2589-7500(23)00267-4.Zwertbroek E.F., Zwertbroek J., Broekhuijsen K. et al. External validation of the Fetal Medicine Foundation algorithm for pre-eclampsia screening in a Dutch population. Eur J Obstet Gynecol Reprod Biol. 2021;264:341–6. https://doi.org/10.1016/j.ejogrb.2021.07.007.Zwertbroek E.F., Zwertbroek J., Broekhuijsen K. et al. External validation of the Fetal Medicine Foundation algorithm for pre-eclampsia screening in a Dutch population. Eur J Obstet Gynecol Reprod Biol. 2021;264:341–6. https://doi.org/10.1016/j.ejogrb.2021.07.007.Холин А.М., Муминова К.Т., Балашов И.С. и др. Прогнозирование преэклампсии в первом триместре беременности: валидация алгоритмов скрининга на российской популяции. Акушерство и гинекология. 2017;(8):74–84. https://doi.org/10.18565/aig.2017.8.74-84.Kholin A.M., Muminova K.T., Balashov I.S. et al. Prediction of preeclampsia in the first trimester of pregnancy: validation of screening algorithms in the Russian population. Akusherstvo i ginekologiya. 2017;(8):74–84. (In Russ.). https://doi.org/10.18565/aig.2017.8.74-84.Андрейченко А.Е., Лучинин А.С., Ившин А.А., Гусев А.В. Разработка и валидация моделей прогнозирования общего риска преэклампсии и риска ранней преэклампсии с использованием алгоритмов машинного обучения в первом триместре беременности. Акушерство и гинекология. 2023;(10):94–107. https://doi.org/10.18565/aig.2023.101.Andreichenko A.E., Luchinin A.S., Ivshin A.A., Gusev A.V. Development and validation of models for predicting the overall risk of preeclampsia and the risk of early preeclampsia using machine learning algorithms in the first trimester of pregnancy. Akusherstvo i ginekologiya. 2023;(10):94–107. (In Russ.). https://doi.org/10.18565/aig.2023.101.Hackelöer M., Schmidt L., Verlohren S. New advances in prediction and surveillance of preeclampsia: role of machine learning approaches and remote monitoring. Arch Gynecol Obstet. 2022;308(6):1663–77. https://doi.org/10.1007/s00404-022-06864-y.Hackelöer M., Schmidt L., Verlohren S. New advances in prediction and surveillance of preeclampsia: role of machine learning approaches and remote monitoring. Arch Gynecol Obstet. 2022;308(6):1663–77. https://doi.org/10.1007/s00404-022-06864-y.Collins G.S., Moons K.G.M., Dhiman P. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. https://doi.org/10.1136/bmj-2023-078378.Collins G.S., Moons K.G.M., Dhiman P. et al. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378. https://doi.org/10.1136/bmj-2023-078378.Collins G.S., Reitsma J.B., Altman D.G., Moons K.G.M. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): the TRIPOD Statement. Ann Intern Med. 2015;162(1):55–63. https://doi.org/10.7326/M14-0697.Collins G.S., Reitsma J.B., Altman D.G., Moons K.G.M. Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD): the TRIPOD Statement. Ann Intern Med. 2015;162(1):55–63. https://doi.org/10.7326/M14-0697.von Elm E., Altman D.G., Egger M. et al.; STROBE Initiative. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Ann Intern Med. 2007;147(8):573–77. https://doi.org/10.7326/0003-4819-147-8-200710160-00010.von Elm E., Altman D.G., Egger M. et al.; STROBE Initiative. The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies. Ann Intern Med. 2007;147(8):573–77. https://doi.org/10.7326/0003-4819-147-8-200710160-00010.Brown M.A., Magee L.A., Kenny L.C. et al.; International Society for the Study of Hypertension in Pregnancy (ISSHP). Hypertensive disorders of pregnancy: ISSHP classification, diagnosis, and management recommendations for international practice. Hypertension. 2018;72(1):24–43. https://doi.org/10.1161/HYPERTENSIONAHA.117.10803.Brown M.A., Magee L.A., Kenny L.C. et al.; International Society for the Study of Hypertension in Pregnancy (ISSHP). Hypertensive disorders of pregnancy: ISSHP classification, diagnosis, and management recommendations for international practice. Hypertension. 2018;72(1):24–43. https://doi.org/10.1161/HYPERTENSIONAHA.117.10803.Сухих Г.Т., Ванько Л.В. Иммунные факторы в этиологии и патогенезе осложнений беременности. Акушерство и гинекология. 2012;(1):128–36.Sukhikh G.T., Vanko L.V. Immune factors in the etiology and pathogenesis of pregnancy complications. Akusherstvo i ginekologiya. 2012;(1):128–36. (In Russ.).Plasencia W., Maiz N., Bonino S. et al. Uterine artery Doppler at 11 + 0 to 13 + 6 weeks in the prediction of pre-eclampsia. Ultrasound Obstet Gynecol. 2007;30(5):742–9. https://doi.org/10.1002/uog.5157.Plasencia W., Maiz N., Bonino S. et al. Uterine artery Doppler at 11 + 0 to 13 + 6 weeks in the prediction of pre-eclampsia. Ultrasound Obstet Gynecol. 2007;30(5):742–9. https://doi.org/10.1002/uog.5157.Wright D., Syngelaki A., Akolekar R. et al. Competing risks model in screening for preeclampsia by maternal characteristics and medical history. Am J Obstet Gynecol. 2015;213(1):62.e1–62.e10. https://doi.org/10.1016/j.ajog.2015.02.018.Wright D., Syngelaki A., Akolekar R. et al. Competing risks model in screening for preeclampsia by maternal characteristics and medical history. Am J Obstet Gynecol. 2015;213(1):62.e1–62.e10. https://doi.org/10.1016/j.ajog.2015.02.018.DeLong E.R., DeLong D.M., Clarke-Pearson D.L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837–45.DeLong E.R., DeLong D.M., Clarke-Pearson D.L. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44(3):837–45.Steyerberg E.W., Vickers A.J., Cook N.R. et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21(1):128–38. https://doi.org/10.1097/EDE.0b013e3181c30fb2.Steyerberg E.W., Vickers A.J., Cook N.R. et al. Assessing the performance of prediction models: a framework for traditional and novel measures. Epidemiology. 2010;21(1):128–38. https://doi.org/10.1097/EDE.0b013e3181c30fb2.Van Calster B., McLernon D.J., van Smeden M. et al. Calibration: the Achilles heel of predictive analytics. BMC Med. 2019;17(1):230. https://doi.org/10.1186/s12916-019-1466-7.Van Calster B., McLernon D.J., van Smeden M. et al. Calibration: the Achilles heel of predictive analytics. BMC Med. 2019;17(1):230. https://doi.org/10.1186/s12916-019-1466-7.Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers. Eds. A.J. Smola, P. Bartlett, B. Schölkopf, D. Schuurmans. Cambridge, MA: MIT Press, 1999. 61–74.Platt J. Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. In: Advances in Large Margin Classifiers. Eds. A.J. Smola, P. Bartlett, B. Schölkopf, D. Schuurmans. Cambridge, MA: MIT Press, 1999. 61–74.O'Gorman N., Wright D., Poon L.C. et al. Multicenter screening for pre-eclampsia by maternal factors and biomarkers at 11-13 weeks’ gestation: comparison with NICE guidelines and ACOG recommendations. Ultrasound Obstet Gynecol. 2017;49(6):756–60. https://doi.org/10.1002/uog.17455.O'Gorman N., Wright D., Poon L.C. et al. Multicenter screening for pre-eclampsia by maternal factors and biomarkers at 11-13 weeks’ gestation: comparison with NICE guidelines and ACOG recommendations. Ultrasound Obstet Gynecol. 2017;49(6):756–60. https://doi.org/10.1002/uog.17455.Tiruneh S.A., Vu T.T.T., Rolnik D.L. et al. Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review. Curr Hypertens Rep. 2024;26:309–23. https://doi.org/10.1007/s11906-024-01297-1.Tiruneh S.A., Vu T.T.T., Rolnik D.L. et al. Machine learning algorithms versus classical regression models in pre-eclampsia prediction: a systematic review. Curr Hypertens Rep. 2024;26:309–23. https://doi.org/10.1007/s11906-024-01297-1.Magee L.A., Brown M.A., Hall D.R. et al. The 2021 International Society for the Study of Hypertension in Pregnancy classification, diagnosis & management recommendations for international practice. Pregnancy Hypertens. 2022;27:148–69. https://doi.org/10.1016/j.preghy.2021.09.008.Magee L.A., Brown M.A., Hall D.R. et al. The 2021 International Society for the Study of Hypertension in Pregnancy classification, diagnosis & management recommendations for international practice. Pregnancy Hypertens. 2022;27:148–69. https://doi.org/10.1016/j.preghy.2021.09.008.Wright D., Tan M.Y., O'Gorman N. et al. Predictive performance of the competing risk model in screening for preeclampsia. Am J Obstet Gynecol. 2019;220(2):199.e1–199.e13. https://doi.org/10.1016/j.ajog.2018.11.1087.Wright D., Tan M.Y., O'Gorman N. et al. Predictive performance of the competing risk model in screening for preeclampsia. Am J Obstet Gynecol. 2019;220(2):199.e1–199.e13. https://doi.org/10.1016/j.ajog.2018.11.1087.Zeisler H., Llurba E., Chantraine F. et al. Predictive value of the sFlt-1:PlGF ratio in women with suspected preeclampsia. N Engl J Med. 2016;374(1):13–22. https://doi.org/10.1056/NEJMoa1414838.Zeisler H., Llurba E., Chantraine F. et al. Predictive value of the sFlt-1:PlGF ratio in women with suspected preeclampsia. N Engl J Med. 2016;374(1):13–22. https://doi.org/10.1056/NEJMoa1414838.Levine R.J., Maynard S.E., Qian C. et al. Circulating angiogenic factors and the risk of preeclampsia. N Engl J Med. 2004;350(7):672–83. https://doi.org/10.1056/NEJMoa031884.Levine R.J., Maynard S.E., Qian C. et al. Circulating angiogenic factors and the risk of preeclampsia. N Engl J Med. 2004;350(7):672–83. https://doi.org/10.1056/NEJMoa031884.Ившин А.А., Малышев Н.А. Ранняя стратификация риска преэклампсии на основе мультипараметрической модели машинного обучения и рутинных клинических данных. Акушерство, Гинекология и Репродукция. 2026;20(1):111–29. https://doi.org/10.17749/2313-7347/ob.gyn.rep.2025.706.Ivshin A.A., Malyshev N.A. Preeclampsia early risk stratification based on a multiparametric machine learning model and routinely collected clinical data. Obstetrics, Gynecology and Reproduction. 2026;20(1):111–29. (In Russ.). https://doi.org/10.17749/2313-7347/ob.gyn.rep.2025.706.

The authors declare that there are no conflicts of interest present.