Radiomics prediction models of left atrial appendage hypercoagulability based on machine learning algorithms: an exploration about cardiac computed tomography angiography imaging
The International Journal of Cardiovascular Imaging · 2024
DOI: 10.1007/s10554-024-03248-y ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Cardiovascular Imaging, 2024. Verfasst von Hongsen Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of Cardiology, The Sixth Medical Center, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China. Hauptthemen laut MEDLINE: Atrial Appendage, Predictive Value of Tests, Machine Learning, Atrial Fibrillation. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 36 Literaturangaben. Gefördert von: General Logistics Department, People's Liberation Army, General Logistics Department, People’s Liberation Army.
Abstract (Originalsprache)
Transesophageal echocardiography (TEE) is the standard method for diagnosing left atrial appendage (LAA) hypercoagulability in patients with atrial fibrillation (AF), which means LAA thrombus/sludge, dense spontaneous echo contrast and slow LAA blood flow velocity (< 0.25 m/s). Based on machine learning algorithms, cardiac computed tomography angiography (CCTA) radiomics features were adopted to construct prediction models and explore a suitable approach for diagnosing LAA hypercoagulability and adjusting anticoagulation. This study included 652 patients with non-valvular AF. The univariate analysis were used to select meaningful clinical characteristics to predict LAA hypercoagulability. Then 3D Slicer software was adopted to extract radiomics features from CCTA imaging. The radiomics score was calculated using the least absolute shrinkage and selection operator logistic regression analysis to predict LAA hypercoagulability. We then combined clinical characteristics and radiomics scores to construct a nomogram model. Finally, we got prediction models based on machine learning algorithms and logistic regression separately. The area under the receiver operating characteristic curve of radiomics score was 0.8449 in the training set and 0.7998 in the validation set. The nomogram model had a concordance index of 0.838. The final machine-learning based prediction models had good performances (best f1 score = 0.85). Radiomics features of long maximum diameter and high uniformity of Hounsfield unit in left atrial were significant predictors of the hypercoagulable state in LAA, with better predictive efficacy than clinical characteristics. Our combined models based on machine learning were reliable for hypercoagulable state screening and anticoagulation adjustment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Cardiology, The Sixth Medical Center, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
- Tsinghua University, 30 Shuangqing Road, Haidian District, Beijing, 100853, China.
- Department of Cardiology, The Sixth Medical Center, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China. guojun301@126.com.
Förderung
- General Logistics Department, People's Liberation Army
- General Logistics Department, People’s Liberation Army
Zitieren
APA
Wang, H., Ge, L., Zhou, H., Lu, X., Yu, Z., Peng, P., Wang, X., Liu, A., Chen, T., Guo, J., & Chen, Y. (2024). Radiomics prediction models of left atrial appendage hypercoagulability based on machine learning algorithms: an exploration about cardiac computed tomography angiography imaging. The International Journal of Cardiovascular Imaging. https://doi.org/10.1007/s10554-024-03248-y
Vancouver
Wang H, Ge L, Zhou H, Lu X, Yu Z, Peng P, et al. Radiomics prediction models of left atrial appendage hypercoagulability based on machine learning algorithms: an exploration about cardiac computed tomography angiography imaging. The International Journal of Cardiovascular Imaging. 2024. doi:10.1007/s10554-024-03248-y
BibTeX
@article{Wang2024,
author = {Wang, Hongsen and Ge, Lan and Zhou, Hang and Lu, Xu and Yu, Zhe and Peng, Peng and Wang, Xinyan and Liu, Ao and Chen, Tao and Guo, Jun and Chen, Yundai},
title = {Radiomics prediction models of left atrial appendage hypercoagulability based on machine learning algorithms: an exploration about cardiac computed tomography angiography imaging},
journal = {The International Journal of Cardiovascular Imaging},
year = {2024},
doi = {10.1007/s10554-024-03248-y}
}
EUVIMED