EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Predicting adverse perinatal outcomes in small-for-gestational-age fetuses using MRI, ultrasound, and clinical data

Aviad Rabinowich iD, Aaron Olender, Netanell Avisdris, Yair Wexler, Bossmat Yehuda iD, Sharon Vanetik, Jayan Khawaja, Tamir Graziani, Bar Neeman, Ayala Zilberman, Maya Yanko, Dana Schonberger und 10 weitere

Radiology Advances · 04.09.2025 · 2 (5)

DOI: 10.1093/radadv/umaf030 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Radiology Advances, online erschienen am 01.09.2025. Verfasst von Aviad Rabinowich und 21 weiteren Autor:innen. Beteiligte Einrichtung: Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, 6423906, Israel. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Leo Mintz grant from the Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Fetal growth restriction (FGR) is associated with adverse perinatal outcomes. Existing sonographic approaches offer limited predictive accuracy. Combining fetal MRI, ultrasound and clinical data may improve perinatal prognostication.

Purpose

To evaluate whether integrating prenatal MRI, ultrasound, and clinical features using machine learning (ML) improves prediction of adverse perinatal outcomes in FGR or small-for-gestational-age (SGA) pregnancies. Materials and Methods This single-center study included prospectively enrolled FGR/SGA and retrospectively included appropriate-for-gestational-age cases, with follow-up through neonatal discharge. Twenty-seven features from MRI, ultrasound, and clinical data were used in the final analysis. Seven ML classifiers were trained using stratified 5-fold cross-validation to predict composite adverse neonatal outcomes (CANO) and non-reassuring fetal status (NRFS). Sensitivity and specificity of the top-performing model (based on area under the curve [AUC]) were compared to standard biometric thresholds (estimated fetal weight and/or abdominal circumference <10th/<3rd centiles). Multiparametric, MRI-only, and ultrasound-only models were compared, along with reduced models using 4 features for CANO and 2 for NRFS.

Results

One hundred thirty-one participants were included (60 FGR/SGA, 71 appropriate-for-gestational-age). The random forest method achieved the highest AUC for predicting CANO (0.912; 95% confidence interval [CI], 0.83–0.99) and NRFS (0.834; 95% CI, 0.76–0.91). For CANO, the multiparametric model demonstrated a 25% higher sensitivity (P = 0.005) and 17% higher specificity (P < 0.001) compared with the 3rd centile threshold, and improved specificity over the 10th centile threshold by 29% (P < 0.001). Sensitivity did not differ significantly from the 10th centile threshold (P = 0.366). For NRFS, specificity increased by 26% and 40% over the 3rd and 10th centile thresholds, respectively (P < 0.001), without significant differences in sensitivity (P = 1). No statistically significant differences were observed between the multiparametric, ultrasound-only, and MRI-only models (P ≥ 0.826), or between full and reduced models (P ≥ 0.313).

Conclusions

ML-based models integrating multimodal data may improve risk stratification for predicting adverse perinatal outcomes in FGR/SGA pregnancies.

Schlagwörter

Stichwörter der Autor:innen

fetal MRIfetal growth restrictionmachine learningneonatal morbidityplacental insufficiencyquantitative MRIsmall for gestational age

Autor:innen und Institutionen

  • Sagol Brain Institute, Tel Aviv Sourasky Medical Center, Tel Aviv, 6423906, Israel.
  • Department of Radiology, Tel Aviv Sourasky Medical Center, Tel Aviv, 6423906, Israel.
  • Gray Faculty of Medical and Health Sciences, Tel Aviv University, Tel Aviv, 6997801, Israel.
  • School of Computer Science and Engineering, The Hebrew University of Jerusalem, Jerusalem, 9190401, Israel.
  • School of Neurobiology, Biochemistry and Biophysics, The George S. Wise Faculty of Life Sciences, Tel Aviv University, Tel Aviv, 6997801, Israel.
  • Sagol School of Neuroscience, Tel Aviv University, Tel Aviv, 6997801, Israel.

ORCID-Profile: Aviad Rabinowich, Bossmat Yehuda, Liran Hiersch, Leo Joskowicz

Förderung

  • Leo Mintz grant from the Faculty of Medicine, Tel Aviv University, Tel Aviv, Israel

Zitieren

APA

Rabinowich, A., Olender, A., Avisdris, N., Wexler, Y., Yehuda, B., Vanetik, S., Khawaja, J., Graziani, T., Neeman, B., Zilberman, A., Yanko, M., Schonberger, D., Sadan, O. R., Misochnik, M., Specktor-Fadida, B., Link-Sourani, D., Herzlich, J., Krajden Haratz, K., Hiersch, L., …, & Ben Bashat, D. (2025). Predicting adverse perinatal outcomes in small-for-gestational-age fetuses using MRI, ultrasound, and clinical data. Radiology Advances, 2(5). https://doi.org/10.1093/radadv/umaf030

Vancouver

Rabinowich A, Olender A, Avisdris N, Wexler Y, Yehuda B, Vanetik S, et al. Predicting adverse perinatal outcomes in small-for-gestational-age fetuses using MRI, ultrasound, and clinical data. Radiology Advances. 2025;2(5). doi:10.1093/radadv/umaf030

BibTeX
@article{Rabinowich2025,
  author = {Rabinowich, Aviad and Olender, Aaron and Avisdris, Netanell and Wexler, Yair and Yehuda, Bossmat and Vanetik, Sharon and Khawaja, Jayan and Graziani, Tamir and Neeman, Bar and Zilberman, Ayala and Yanko, Maya and Schonberger, Dana and Sadan, Or Rachel and Misochnik, Miriam and Specktor-Fadida, Bella and Link-Sourani, Daphna and Herzlich, Jacky and Krajden Haratz, Karina and Hiersch, Liran and Ben Sira, Liat and Joskowicz, Leo and Ben Bashat, Dafna},
  title = {Predicting adverse perinatal outcomes in small-for-gestational-age fetuses using MRI, ultrasound, and clinical data},
  journal = {Radiology Advances},
  year = {2025},
  volume = {2},
  number = {5},
  doi = {10.1093/radadv/umaf030}
}
Kostenlos starten →