Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation

Abstract Objective Left atrial thrombus (LAT) poses a significant risk for stroke and other thromboembolic complication in patients with atrial fibrillation (AF). This study aimed to evaluate the incidence and predictors of LAT in patients with paroxysmal AF, utilizing machine learning techniques ba...

Full description

Saved in:
Bibliographic Details
Main Authors: Wanli Xiong, Qiqi Cao, Lu Jia, Min Chen, Tao Liu, Qingyan Zhao, Yanhong Tang, Bo Yang, Li Li, Shaobo Shi, He Huang, Congxin Huang, China Atrial Fibrillation Center Project Team
Format: Article
Language:English
Published: BMC 2025-06-01
Series:BMC Cardiovascular Disorders
Subjects:
Online Access:https://doi.org/10.1186/s12872-025-04847-w
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725450600841216
author Wanli Xiong
Qiqi Cao
Lu Jia
Min Chen
Tao Liu
Qingyan Zhao
Yanhong Tang
Bo Yang
Li Li
Shaobo Shi
He Huang
Congxin Huang
China Atrial Fibrillation Center Project Team
author_facet Wanli Xiong
Qiqi Cao
Lu Jia
Min Chen
Tao Liu
Qingyan Zhao
Yanhong Tang
Bo Yang
Li Li
Shaobo Shi
He Huang
Congxin Huang
China Atrial Fibrillation Center Project Team
author_sort Wanli Xiong
collection DOAJ
description Abstract Objective Left atrial thrombus (LAT) poses a significant risk for stroke and other thromboembolic complication in patients with atrial fibrillation (AF). This study aimed to evaluate the incidence and predictors of LAT in patients with paroxysmal AF, utilizing machine learning techniques based on data from the Chinese Atrial Fibrillation study. Methods A large-scale multi-center retrospective study was conducted involving patients diagnosed with non-valvular paroxysmal AF. LAT incidence was assessed, and potential risk factors were analyzed. Machine learning algorithms, including decision tree, random forest, AdaBoost, k-Nearest Neighbor, and logistic regression, were employed to develop a predictive model for LAT. Results Of the 49,515 patients with paroxysmal AF, 1,058 patients (2.1%, 95% CI 2.0%-2.3%) were identified with LAT. Sixty-one variables were initially included to train machine learning models, with the random forest algorithm demonstrating the best predictive performance (AUC 0.833, 95%CI 0.730–0.924). The final model, refined to include nine essential features, achieved an AUC of 0.787 (95%CI 0.670–0.883). Calibration analysis indicated no significant difference between predicted and observed values (p = 0.181). The median predicted probabilities of LAT across quintiles were 2.3%, 7.0%, 11.8%, 16.6%, and 21.5%. Conclusion This simplified prediction model effectively identifies the risk of LAT in patients with paroxysmal AF, providing a valuable tool for clinical decision-making. Further studies are needed to explore AF management and risk stratification in other AF subtypes.
format Article
id doaj-art-0275576e50f34c03b2ea2280dd0e3a9a
institution DOAJ
issn 1471-2261
language English
publishDate 2025-06-01
publisher BMC
record_format Article
series BMC Cardiovascular Disorders
spelling doaj-art-0275576e50f34c03b2ea2280dd0e3a9a2025-08-20T03:10:28ZengBMCBMC Cardiovascular Disorders1471-22612025-06-0125111110.1186/s12872-025-04847-wMachine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillationWanli Xiong0Qiqi Cao1Lu Jia2Min Chen3Tao Liu4Qingyan Zhao5Yanhong Tang6Bo Yang7Li Li8Shaobo Shi9He Huang10Congxin Huang11China Atrial Fibrillation Center Project TeamDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceWuhan Shinall Technology CoDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceSchool of Electronic Information, Wuhan UniversityDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceDepartment of Cardiology, Renmin Hospital of Wuhan University, Hubei ProvinceAbstract Objective Left atrial thrombus (LAT) poses a significant risk for stroke and other thromboembolic complication in patients with atrial fibrillation (AF). This study aimed to evaluate the incidence and predictors of LAT in patients with paroxysmal AF, utilizing machine learning techniques based on data from the Chinese Atrial Fibrillation study. Methods A large-scale multi-center retrospective study was conducted involving patients diagnosed with non-valvular paroxysmal AF. LAT incidence was assessed, and potential risk factors were analyzed. Machine learning algorithms, including decision tree, random forest, AdaBoost, k-Nearest Neighbor, and logistic regression, were employed to develop a predictive model for LAT. Results Of the 49,515 patients with paroxysmal AF, 1,058 patients (2.1%, 95% CI 2.0%-2.3%) were identified with LAT. Sixty-one variables were initially included to train machine learning models, with the random forest algorithm demonstrating the best predictive performance (AUC 0.833, 95%CI 0.730–0.924). The final model, refined to include nine essential features, achieved an AUC of 0.787 (95%CI 0.670–0.883). Calibration analysis indicated no significant difference between predicted and observed values (p = 0.181). The median predicted probabilities of LAT across quintiles were 2.3%, 7.0%, 11.8%, 16.6%, and 21.5%. Conclusion This simplified prediction model effectively identifies the risk of LAT in patients with paroxysmal AF, providing a valuable tool for clinical decision-making. Further studies are needed to explore AF management and risk stratification in other AF subtypes.https://doi.org/10.1186/s12872-025-04847-wParoxysmal atrial fibrillationLeft atrial thrombusTransesophageal echocardiographyMachine-learning model
spellingShingle Wanli Xiong
Qiqi Cao
Lu Jia
Min Chen
Tao Liu
Qingyan Zhao
Yanhong Tang
Bo Yang
Li Li
Shaobo Shi
He Huang
Congxin Huang
China Atrial Fibrillation Center Project Team
Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
BMC Cardiovascular Disorders
Paroxysmal atrial fibrillation
Left atrial thrombus
Transesophageal echocardiography
Machine-learning model
title Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
title_full Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
title_fullStr Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
title_full_unstemmed Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
title_short Machine-learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
title_sort machine learning model for predicting left atrial thrombus in patients with paroxysmal atrial fibrillation
topic Paroxysmal atrial fibrillation
Left atrial thrombus
Transesophageal echocardiography
Machine-learning model
url https://doi.org/10.1186/s12872-025-04847-w
work_keys_str_mv AT wanlixiong machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT qiqicao machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT lujia machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT minchen machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT taoliu machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT qingyanzhao machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT yanhongtang machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT boyang machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT lili machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT shaoboshi machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT hehuang machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT congxinhuang machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation
AT chinaatrialfibrillationcenterprojectteam machinelearningmodelforpredictingleftatrialthrombusinpatientswithparoxysmalatrialfibrillation