首页|Chinese People's Liberation Army (PLA) General Hospital Reports Findings in Mach ine Learning (Radiomics prediction models of left atrial appendage hypercoagulab ility based on machine learning algorithms: an exploration about cardiac compute d ...)
Chinese People's Liberation Army (PLA) General Hospital Reports Findings in Mach ine Learning (Radiomics prediction models of left atrial appendage hypercoagulab ility based on machine learning algorithms: an exploration about cardiac compute d ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
2024 OCT 08 (NewsRx)-By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News-New research on Machine Learning is the subject o f a report. According to news originating from Beijing, People's Republic of Chi na, by NewsRx correspondents, research stated, "Transesophageal echocardiography (TEE) is the standard method for diagnosing left atrial appendage (LAA) hyperco agulability 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 an giography (CCTA) radiomics features were adopted to construct prediction models and explore a suitable approach for diagnosing LAA hypercoagulability and adjust ing anticoagulation." Our news journalists obtained a quote from the research from Chinese People's Li beration Army (PLA) General Hospital, "This study included 652 patients with non -valvular AF. The univariate analysis were used to select meaningful clinical ch aracteristics to predict LAA hypercoagulability. Then 3D Slicer software was ado pted to extract radiomics features from CCTA imaging. The radiomics score was ca lculated using the least absolute shrinkage and selection operator logistic regr ession analysis to predict LAA hypercoagulability. We then combined clinical cha racteristics 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 radiom ics score was 0.8449 in the training set and 0.7998 in the validation set. The n omogram model had a concordance index of 0.838. The final machine-learning based prediction models had good performances (best f1 score = 0.85). Radiomics featu res of long maximum diameter and high uniformity of Hounsfield unit in left atri al were significant predictors of the hypercoagulable state in LAA, with better predictive efficacy than clinical characteristics."
BeijingPeople's Republic of ChinaAsiaAlgorithmsAngiographyCardiologyCardiovascular Diagnostic TechniquesCo mputed TomographyCyborgsEmerging TechnologiesHealth and MedicineImaging TechnologyMachine LearningTechnology
NETL
NSTL
