EUVIMEDEUVIMED entdecken
Open Access

Multimodal Nomogram for the Prenatal Risk Assessment of Hypoplastic Left Heart Syndrome Using Self‐Supervised Learning

Xinglong Wu iD, Chen Cheng iD, Zhenchun Ran iD, Hao Zhu, Guoping Xu, Tongquan Wu, Sheng Zhao iD

Journal of Ultrasound in Medicine · 2026-09 · 45 (9) · 1983-1999

DOI: 10.1002/jum.70254 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Ultrasound in Medicine, online erschienen am 08.05.2026. Verfasst von Xinglong Wu und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, People's Republic of Chi…. Hauptthemen laut MEDLINE: Nomograms, Hypoplastic Left Heart Syndrome, Ultrasonography, Prenatal, Supervised Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Natural Science Foundation of China, Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis Fund, Health Commission of Hubei Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This retrospective study aims to develop and validate a multimodal nomogram for the prenatal risk assessment of hypoplastic left heart syndrome (HLHS) and to explore significant risk factors for HLHS.

Methods

This retrospective study enrolled 161 normal pregnancies and 52 pregnancies diagnosed with HLHS at the Ultrasound Diagnosis Department of Maternal and Child Health Hospital of Hubei Province in China from September 2019 to September 2023. Experienced sonographers selected standard 4‐chamber cardiac views and delineated the boundaries of the left and right atria and ventricles. A ResNet‐like variational autoencoder (RVAE) was used to extract features from 4‐chamber views in a self‐supervised learning strategy. These features were then converted into an image score. The proposed multimodal nomogram was developed using univariate and multivariate logistic regression analysis, incorporating the image score, demographics, and morphological characteristics of the fetus' heart. To evaluate the nomogram's performance, we constructed a clinical regression model, 4 machine learning (ML) models, and an expert model comprising 3 sonographers with varying years of clinical experience.

Results

The study identified several significant risk factors for assessing the risk of HLHS, including the diameter of the left ventricle, the area ratio between the left and right atrium, the area ratio between the left and right ventricle, and the image score calculated from the 4‐chamber view. A multimodal nomogram was constructed based on these factors, achieving an accuracy of 0.935 and an AUC of 0.991. The performance of the nomogram was better than that of the traditional logistic regression and ML models, and comparable to that of the expert model. Additionally, the multimodal nomogram outperforms sonographers with 3‐ and 6‐year experience, and performs only slightly worse than the sonographer with 10‐year experience. When combined with the heat‐map generated from RVAE, the nomogram can serve as an easy‐to‐use tool to help clinicians better understand the process of computer‐aided diagnosis.

Conclusion

The proposed multimodal nomogram demonstrates its superiority, effectiveness, and interpretability in prenatal risk assessment of HLHS. Additionally, 2 risk factors, ie, the area ratio between the left and right atrium and the area ratio between the ventricle, deserve further investigation during clinical diagnosis of HLHS.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

NomogramsHypoplastic Left Heart SyndromeUltrasonography, PrenatalSupervised Machine LearningHumansFemaleRetrospective StudiesRisk AssessmentPregnancyChinaRisk FactorsAutoencoderAdultFetal Heart

Stichwörter der Autor:innen

deep learningfour‐chamber cardiac viewhypoplastic left heart syndromenomogramultrasound

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Hubei Key Laboratory of Intelligent Robot, Wuhan Institute of Technology, Wuhan, People's Republic of China.
  • Xin jiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis, Kashi, People's Republic of China.
  • Ultrasound Diagnosis Department, Maternal and Child Health Hospital of Hubei Province, Wuhan, People's Republic of China.
  • School of Mechanical Engineering, Hefei University of Technology, Hefei, People's Republic of China.

ORCID-Profile: Xinglong Wu, Chen Cheng, Zhenchun Ran, Sheng Zhao

Förderung

  • National Natural Science Foundation of China
  • Xinjiang Key Laboratory of Artificial Intelligence Assisted Imaging Diagnosis Fund
  • Health Commission of Hubei Province
  • Hubei Province Natural Science Foundation
  • Natural Science Foundation of Hubei Province

Zitieren

APA

Wu, X., Cheng, C., Ran, Z., Zhu, H., Xu, G., Wu, T., & Zhao, S. (2026). Multimodal Nomogram for the Prenatal Risk Assessment of Hypoplastic Left Heart Syndrome Using Self‐Supervised Learning. Journal of Ultrasound in Medicine, 45(9), 1983-1999. https://doi.org/10.1002/jum.70254

Vancouver

Wu X, Cheng C, Ran Z, Zhu H, Xu G, Wu T, et al. Multimodal Nomogram for the Prenatal Risk Assessment of Hypoplastic Left Heart Syndrome Using Self‐Supervised Learning. Journal of Ultrasound in Medicine. 2026;45(9):1983-1999. doi:10.1002/jum.70254

BibTeX
@article{Wu2026,
  author = {Wu, Xinglong and Cheng, Chen and Ran, Zhenchun and Zhu, Hao and Xu, Guoping and Wu, Tongquan and Zhao, Sheng},
  title = {Multimodal Nomogram for the Prenatal Risk Assessment of Hypoplastic Left Heart Syndrome Using Self‐Supervised Learning},
  journal = {Journal of Ultrasound in Medicine},
  year = {2026},
  volume = {45},
  number = {9},
  pages = {1983--1999},
  doi = {10.1002/jum.70254}
}
Kostenlos starten →