Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics
Vascular · 2025
DOI: 10.1177/17085381241262575 ↗Kurz gefasst
Fachartikel in der Zeitschrift Vascular, 2025. Verfasst von Yonggang Wang und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Vascular Surgery, The First Affiliated Hospital of Naval Medical University, Shanghai, China. Hauptthemen laut MEDLINE: Aortic Aneurysm, Abdominal, Endovascular Procedures, Unsupervised Machine Learning, Blood Vessel Prosthesis Implantation. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Objective
This study used unsupervised machine learning (UML) cluster analysis to explore clinical phenotypes of endovascular aortic repair (EVAR) for abdominal aortic aneurysm (AAA) patients based on radiomics.
Method
We retrospectively reviewed 1785 patients with infra-renal AAA who underwent elective EVAR procedures between January 2010 and December 2020. Pyradiomics was used to extract the radiomics features. Statistical analysis was applied to determine the radiomics features that related to severe adverse events (SAEs) after EVAR. The selected features were used for UML cluster analysis in training set and validation in test set. Comparison of basic characteristics and radiomics features of different clusters. The Kaplan-Meier analysis was conducted to generate the cumulative incidence of freedom from SAEs rate.
Result
A total of 1180 patients were enrolled. During the follow-up, 353 patients experienced EVAR-related SAEs. In total, 1223 radiomics features were extracted from each patient, of which 23 radiomics features were finally preserved to identify different clinical phenotypes. 944 patients were allocated to the training set. Three clusters were identified in training set, in which patients had identical clinical characteristics and morphological features, while varied considerably of selected radiomics features. This encouraging performance was further approved in the test set. In addition, each cluster was well differentiated from other clusters and Kaplan-Meier analysis showed significant differences of freedom from SAEs rate between different clusters both in the training ( p = .0216) and test sets ( p = .0253).
Conclusion
Based on radiomics, UML cluster analysis can identify clinical phenotypes in EVAR patients with distinct long-term outcomes.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Vascular Surgery, The First Affiliated Hospital of Naval Medical University, Shanghai, China.
- Department of Vascular Surgery, Zhongshan Hospital, Institute of Vascular Surgery, Fudan University, National Clinical Research Center for Interventional Medicine, Shanghai, China.
ORCID-Profile: Yonggang Wang
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Wang, Y., Zhou, M., Ding, Y., Li, X., Xie, T., Zhou, Z., Fu, W., & Shi, Z. (2025). Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics. Vascular. https://doi.org/10.1177/17085381241262575
Vancouver
Wang Y, Zhou M, Ding Y, Li X, Xie T, Zhou Z, et al. Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics. Vascular. 2025. doi:10.1177/17085381241262575
BibTeX
@article{Wang2025,
author = {Wang, Yonggang and Zhou, Min and Ding, Yong and Li, Xu and Xie, Tianchen and Zhou, Zhenyu and Fu, Weiguo and Shi, Zhenyu},
title = {Unsupervised machine learning cluster analysis to identification EVAR patients clinical phenotypes based on radiomics},
journal = {Vascular},
year = {2025},
doi = {10.1177/17085381241262575}
}
EUVIMED