自适应异质图神经网络用于区分动脉性肺动脉高压与左心疾病相关肺高压
Adaptive heterogeneous graph neural networks for differentiating pulmonary arterial hypertension from left heart disease
上海市肺科医院等机构团队在npj Digital Medicine发表研究,开发出自适应异质图神经网络(AHGNN),以胸部增强CT影像和无创临床变量区分动脉性肺动脉高压(PAH)与左心疾病相关肺高压(PH-LHD)。
基于上海市肺科医院905例患者的回顾性分析,无创AI模型融合胸部CT与临床变量区分两类肺高压的平均AUC为0.946,为该方向提供了一项性能参考。
- Article
- Open access
- Published: 08 October 2026
- Yingran Shen1 na1,
- Jie Mi1 na1,
- Xiaogang Zhao1 na1,
- Gongzhe Liu2,
- Guang Yang3,
- Bei Yang1,
- Hao Wang1,
- Yijiu Ren1 &
- …
- Jie Cai1
npj Digital Medicine (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Differentiating pulmonary arterial hypertension (PAH) from pulmonary hypertension associated with left heart disease (PH-LHD) is clinically important because management differs substantially, but definitive classification requires invasive haemodynamic assessment together with clinical evaluation. We retrospectively studied 905 patients with PAH or PH-LHD treated at Shanghai Pulmonary Hospital and developed an adaptive heterogeneous graph neural network (AHGNN) that integrates contrast-enhanced thoracic CT images with noninvasive clinical variables. The model combines differentiable graph construction using Gumbel-Softmax reparameterization, hierarchical cross-modal attention, and dual-level self-supervised contrastive learning. Across 100 outer test folds from repeated patient-level five-fold cross-validation, AHGNN achieved a mean area under the receiver operating characteristic curve (AUC) of 0.946 ± 0.023 and a precision–recall AUC of 0.952 ± 0.009. At a fixed probability threshold of 0.50, sensitivity was 0.867 ± 0.070 and specificity was 0.867 ± 0.072. The Brier score was 0.139, although a calibration slope of 3.547 indicated that recalibration may be required. These findings support the potential of multimodal noninvasive data to assist referral and diagnostic triage. Prospective external validation, recalibration, and clinical safety evaluation are required before clinical use or any change to the role of right heart catheterization.
Acknowledgements
The authors thank the healthcare professionals and researchers at the Department of Thoracic Surgery, Shanghai Pulmonary Hospital, for their assistance with data collection. This study was supported by the National Natural Science Foundation of China (82403885 to J.C.) and the Programs of Shanghai Pulmonary Hospital (China) (No. fkyc2638 to J.C.).
Author information
Author notes
These authors contributed equally: Yingran Shen, Jie Mi, Xiaogang Zhao.
Authors and Affiliations
Department of Thoracic Surgery, Shanghai Pulmonary Hospital, School of Medicine, Tongji University, Shanghai, China
Yingran Shen, Jie Mi, Xiaogang Zhao, Bei Yang, Hao Wang, Yijiu Ren & Jie Cai
Department of Cardiothoracic Surgery, People’s Hospital Affiliated to Shandong First Medical University, Jinan, China
Gongzhe Liu
Department of Thoracic Surgery, The First Hospital of Hebei Medical University, Hebei Medical University, Shijiazhuang, China
Guang Yang
Authors
- Yingran Shen
- Jie Mi
- Xiaogang Zhao
- Gongzhe Liu
- Guang Yang
- Bei Yang
- Hao Wang
- Yijiu Ren
- Jie Cai
Corresponding authors
Correspondence to Hao Wang, Yijiu Ren or Jie Cai.
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article's Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article's Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Shen, Y., Mi, J., Zhao, X. et al. Adaptive heterogeneous graph neural networks for differentiating pulmonary arterial hypertension from left heart disease. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-03305-x
Received: 18 August 2025
Accepted: 13 September 2026
Published: 08 October 2026
DOI: https://doi.org/10.1038/s41746-026-03305-x
来源:Nature 健康护理主题 · nature.com