Comparison of Machine Learning Models and the FMF Competing-Risks Algorithm for First-Trimester Preeclampsia Screening in a Romanian Cohort
Diagnostics · 19.05.2026 · 16 (10) · 1540
DOI: 10.3390/diagnostics16101540 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 19.05.2026. Verfasst von Alexandra-Elena Cristofor und 5 weiteren Autor:innen. Beteiligte Einrichtung: Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Background/Objectives: First-trimester preeclampsia (PE) screening is most widely implemented using the Fetal Medicine Foundation (FMF) algorithm, which combines maternal factors with biophysical and biochemical markers via a competing-risks/Bayes framework to produce individualized risks and guide prophylaxis decisions. We aimed to compare commonly used machine-learning (ML) classifiers (logistic regression, random forest, XGBoost) against FMF a priori and a posteriori risk estimates in a Romanian screening cohort.
Methods
We analyzed 1583 singleton pregnancies screened at 11–14 weeks’ gestation. Primary analyses excluded aspirin-treated women to reduce treatment-induced outcome modification. We evaluated two feature sets mirroring FMF structure: (1) a maternal-factor “a priori” set and (2) a “a posteriori” set additionally incorporating mean arterial pressure (MAP), uterine artery pulsatility index (UtA-PI), and Pregnancy-Associated Plasma Protein A (PAPP-A). Models were trained using stratified repeated cross-validation (5-fold × 10 repeats) and evaluated using AUC-ROC, DeLong tests, and sensitivity at 10% false-positive rate. Calibration of the model, sensitivity analyses and decision-curve analysis (DCA) were also assessed.
Results
In the a priori comparison, the best ML model was logistic regression (AUC 0.796) versus FMF prior risk AUC 0.841 (DeLong p = 0.349). The sensitivity at 10% false positive rate (FPR) was 33.3% for the model versus 50.0% for FMF model. In the a posteriori comparison, the best ML model was random forest (AUC 0.844) versus FMF posterior risk AUC 0.929 (DeLong p = 0.087), with sensitivity at 10% FPR of 57.1% for ML and 71.4% for FMF. Random undersampling did not improve ML performance. Including aspirin-treated pregnancies did not significantly change our results.
Conclusions
In this study, the FMF competing-risks outputs outperformed or matched ML classifiers in both maternal-only and biomarker-augmented screening, and DCA favored FMF particularly for the a posteriori model.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Grigore T. Popa University of Medicine and Pharmacy, 700115 Iasi, Romania.
- Faculty of Medicine and Biological Sciences, 'Ștefan cel Mare' University, 720229 Suceava, Romania.
ORCID-Profile: Alexandra-Elena Cristofor, Alexandru Carauleanu, Ingrid-Andrada Vasilache, Iustina Condriuc, Ovidiu Bica, Dragos Nemescu
Zitieren
APA
Cristofor, A. E., Carauleanu, A., Vasilache, I. A., Condriuc, I., Bica, O., & Nemescu, D. (2026). Comparison of Machine Learning Models and the FMF Competing-Risks Algorithm for First-Trimester Preeclampsia Screening in a Romanian Cohort. Diagnostics, 16(10), 1540. https://doi.org/10.3390/diagnostics16101540
Vancouver
Cristofor AE, Carauleanu A, Vasilache IA, Condriuc I, Bica O, Nemescu D. Comparison of Machine Learning Models and the FMF Competing-Risks Algorithm for First-Trimester Preeclampsia Screening in a Romanian Cohort. Diagnostics. 2026;16(10):1540. doi:10.3390/diagnostics16101540
BibTeX
@article{Cristofor2026,
author = {Cristofor, Alexandra-Elena and Carauleanu, Alexandru and Vasilache, Ingrid-Andrada and Condriuc, Iustina and Bica, Ovidiu and Nemescu, Dragos},
title = {Comparison of Machine Learning Models and the FMF Competing-Risks Algorithm for First-Trimester Preeclampsia Screening in a Romanian Cohort},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {10},
pages = {1540},
doi = {10.3390/diagnostics16101540}
}
EUVIMED