EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Harnessing Artificial Intelligence-Derived Pulmonary Signatures and Uterine Hemodynamics: A Novel Dual-Pathway Framework for Predicting Neonatal Respiratory Distress in Gestational Diabetes Mellitus

Nutzung von KI-abgeleiteten pulmonalen Signaturen und uterinen Hämodynamik: ein neuartiges Dual-Pathway-Framework zur Vorhersage von neonatalem Atemnotsyndrom bei Gestationsdiabetes mellitus

Jing Zhang, Jing Shi, Bo Liu, Yan Ding

Clinical and Experimental Obstetrics & Gynecology · 11.02.2026 · 53 (2)

DOI: 10.31083/ceog46350 ↗

Auf einen Blick

Bei 50 Schwangeren mit Gestationsdiabetes wurde ein nicht-invasives Modell zur Vorhersage von NRDS geprüft. Die Kombination aus KI-Lungenanalyse und Uterusarterien-PI zeigte die beste Vorhersageleistung.

Fragestellung

Wie gut sagen KI-abgeleitete fetale Lungen-Textursignaturen und der Uterusarterien-Pulsatilitätsindex NRDS bei GDM voraus?

Methode

Prospektive Kohortenstudie mit 50 Patient:innen mit GDM. Ultraschallbilder wurden mit TensorFlow analysiert; 342 GLCM-Texturmerkmale und der Uterusarterien-PI wurden zur NRDS-Risikostratifizierung geprüft.

Ergebnisse

Der Uterusarterien-PI war in der NRDS-Gruppe höher als in den Kontrollen (1,52 [IQR 1,35–1,70] vs. 1,16 [IQR 0,95–1,30]; p < 0,001). Die KI-Analyse erreichte 86,4 % Sensitivität und 78,6 % Spezifität; kombiniert 92,0 % Gesamtgenauigkeit (46/50).

Schlussfolgerung der Autor:innen

Die Kombination aus KI-quantifizierter fetaler Lungen-Texturanalyse und Uterusarterien-Doppler-Hämodynamik bietet ein verfeinertes, nicht-invasives Werkzeug zur NRDS-Risikostratifizierung bei GDM.

Kernaussagen

  • PI höher bei NRDS als in der Kontrollgruppe
  • KI-Modell: 86,4 % Sensitivität und 78,6 % Spezifität
  • Kombination erreichte 92,0 % Gesamtgenauigkeit (46/50)

Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.

Kurz gefasst

Fachartikel in der Zeitschrift Clinical and Experimental Obstetrics & Gynecology, online erschienen am 11.02.2026. Verfasst von Jing Zhang und 3 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Wuxi Municipal Double Hundred Young and Middle-Aged Reserve Top Talents Program in Medical and Health Fields, Jiangsu Provincial Health Commission Scientific Research Fund Project.

Auf einen BlickAbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Gestational diabetes mellitus (GDM) elevates the risk of neonatal respiratory distress syndrome (NRDS), highlighting the need for robust predictive tools. Current assessments of fetal lung maturity assessments are invasive, creating a clinical demand for non-invasive alternatives. This study presents a dual-parameter framework that combines artificial intelligence (AI)-derived fetal lung texture signatures with uterine artery pulsatility index (PI) to predict NRDS risk in GDM pregnancies.

Methods

A prospective cohort of 50 patients with GDM patients was enrolled. Standardized four-chamber view ultrasound images were processed using a TensorFlow-based framework to extract 342 gray-level co-occurrence matrix (GLCM) texture features from the fetal lungs. A support vector machine (SVM) classifier was then employed for NRDS risk stratification. Concurrently, uterine artery PI was measured transvaginally following International Society of Ultrasound in Obstetrics and Gynecology (ISUOG) guidelines. The predictive performance of the AI model, uterine artery PI, and their combination was evaluated for predicting NRDS.

Results

The uterine artery PI was significantly elevated in the NRDS group (n = 22) compared with controls (n = 28) (median 1.52 [interquartile range, IQR: 1.35–1.70] vs. 1.16 [IQR: 0.95–1.30]; p < 0.001). The standalone AI-based pulmonary texture analysis achieved 86.4% sensitivity and 78.6% specificity for NRDS prediction, with substantial agreement with clinical diagnosis (κ = 0.67). The synergistic integration of an AI-based high-risk classification with a uterine artery PI ≥1.28 yielded superior predictive performance, attaining 92.0% overall accuracy (46/50). Decision curve analysis confirmed that the combined model provided a superior net benefit across clinically relevant threshold probabilities (10%–50%).

Conclusions

The integration of AI-quantified fetal lung texture analysis with uterine artery Doppler hemodynamics provides a refined, non-invasive tool for NRDS risk stratification in pregnancies complicated by GDM. This dual-pathway framework effectively captures the interplay between placental vascular insufficiency and pulmonary immaturity, offering high diagnostic accuracy and clinical utility to guide perinatal management decisions.

Förderung

  • Wuxi Municipal Double Hundred Young and Middle-Aged Reserve Top Talents Program in Medical and Health Fields
  • Jiangsu Provincial Health Commission Scientific Research Fund Project

Zitieren

APA

Zhang, J., Shi, J., Liu, B., & Ding, Y. (2026). Harnessing Artificial Intelligence-Derived Pulmonary Signatures and Uterine Hemodynamics: A Novel Dual-Pathway Framework for Predicting Neonatal Respiratory Distress in Gestational Diabetes Mellitus. Clinical and Experimental Obstetrics & Gynecology, 53(2). https://doi.org/10.31083/ceog46350

Vancouver

Zhang J, Shi J, Liu B, Ding Y. Harnessing Artificial Intelligence-Derived Pulmonary Signatures and Uterine Hemodynamics: A Novel Dual-Pathway Framework for Predicting Neonatal Respiratory Distress in Gestational Diabetes Mellitus. Clinical and Experimental Obstetrics & Gynecology. 2026;53(2). doi:10.31083/ceog46350

BibTeX
@article{Zhang2026,
  author = {Zhang, Jing and Shi, Jing and Liu, Bo and Ding, Yan},
  title = {Harnessing Artificial Intelligence-Derived Pulmonary Signatures and Uterine Hemodynamics: A Novel Dual-Pathway Framework for Predicting Neonatal Respiratory Distress in Gestational Diabetes Mellitus},
  journal = {Clinical and Experimental Obstetrics & Gynecology},
  year = {2026},
  volume = {53},
  number = {2},
  doi = {10.31083/ceog46350}
}
Kostenlos starten →