Interpretable Clinical–Radiomics Model for Prediction of Blood Stasis and Left Atrial Appendage Thrombus
Thrombosis and Haemostasis · 31.03.2026
DOI: 10.1055/a-2829-8644 ↗Kurz gefasst
Fachartikel in der Zeitschrift Thrombosis and Haemostasis, erschienen am 31.03.2026. Verfasst von Yi Zhao und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, China-Japan Union Hospital of Jilin University, Changchun, China.
Abstract (Originalsprache)
Background
The left atrial (LA) morphological profile, anatomically contiguous with the left atrial appendage (LAA), exhibits hemodynamic properties associated with thrombogenic predisposition in nonvalvular atrial fibrillation (NVAF). Integrating these structural biomarkers with clinical parameters enables noninvasive prediction of thrombosis risk. Methods and Results This single-center retrospective study analyzed 253 NVAF patients undergoing pre-ablation dual-phase delayed LA computed tomography angiography (CTA). A machine learning (ML) model incorporating clinical and radiomics features was developed to predict LAA thrombosis/blood stasis. Multi-framework interpretation revealed robust predictive performance: global accuracy 92%, thrombosis subgroup F1-score of 0.97 (95%CI: 0.89–1.00) with area under the curve of 1.00 (AUC: 95%CI: 0.99–1.00), blood stasis subgroup F1-score of 0.90 (95%CI: 0.81–0.97) with AUC of 0.97. Model reliability was confirmed by Cohen's κ = 0.88 and 5-fold cross-validation (CV) score (mean score 0.91, range 0.88–0.94). Contribution visualization analysis identified clinical parameters as the main predictors, lipid-related indicators showed high discriminative value, while the radiomics parameters LA sphericity and radiomics texture features provided incremental calibration.
Conclusion
The multimodal model integrating clinical profiles with CTA-derived radiomics effectively stratifies LAA thrombosis and blood stasis risks, demonstrating an exceptional discriminatory accuracy for thrombus detection.
Autor:innen und Institutionen
- Department of Cardiology, China-Japan Union Hospital of Jilin University, Changchun, China.
- Department of Radiology, China-Japan Union Hospital of Jilin University, Changchun, China.
Zitieren
APA
Zhao, Y., Zhou, M., Liu, J., Zhang, Y., Yu, M., Sun, H., Si, D., Yang, H., & Zhang, B. (2026). Interpretable Clinical–Radiomics Model for Prediction of Blood Stasis and Left Atrial Appendage Thrombus. Thrombosis and Haemostasis. https://doi.org/10.1055/a-2829-8644
Vancouver
Zhao Y, Zhou M, Liu J, Zhang Y, Yu M, Sun H, et al. Interpretable Clinical–Radiomics Model for Prediction of Blood Stasis and Left Atrial Appendage Thrombus. Thrombosis and Haemostasis. 2026. doi:10.1055/a-2829-8644
BibTeX
@article{Zhao2026,
author = {Zhao, Yi and Zhou, Minghao and Liu, Jiyuan and Zhang, Yining and Yu, Ming and Sun, Huan and Si, Daoyuan and Yang, Hongliang and Zhang, Butian},
title = {Interpretable Clinical–Radiomics Model for Prediction of Blood Stasis and Left Atrial Appendage Thrombus},
journal = {Thrombosis and Haemostasis},
year = {2026},
doi = {10.1055/a-2829-8644}
}
EUVIMED