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
PMID: 39317823

Abstract

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.

Authors

  • Hongsen Wang
    Department of Cardiology, The Sixth Medical Center, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
  • Lan Ge
    Department of Cardiology, The Sixth Medical Center, Chinese PLA General Hospital, 28 Fuxing Road, Haidian District, Beijing, 100853, China.
  • Hang Zhou
    Institute of Image Processing and Pattern Recognition, Shanghai Jiao Tong University, Ministry of Education of China, Shanghai, China.
  • Xu Lu
    Department of Computer Science, Guangdong Polytechnic Normal University, Guangzhou, 510006, China. Electronic address: bruda@126.com.
  • Zhe Yu
    Department of Pharmacology and Physiology, George Washington University, Washington, DC.
  • Peng Peng
    School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, 214122, Jiangsu, China.
  • Xinyan Wang
    Institute of Medical Intelligence, School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China.
  • Ao Liu
    Department of Thoracic Surgery, The Affiliated Hospital of Qingdao University, Qingdao, China.
  • Tao Chen
    School of Automation, Northwestern Polytechnical University, Xi'an, 710072, Shaanxi, China.
  • Jun Guo
    Department of Oncology, Dongfeng Hospital, Hubei University of Medicine, Shiyan, Hubei 442008, P.R. China.
  • Yundai Chen
    Department of Pulmonary Vessel and Thrombotic Disease, Sixth Medical Center, Chinese PLA General Hospital, Beijing, China.

Keywords

External Resources

Popular Topics
Recent Journals