1
|
Ruzieh M, Bai C, Meisel E, Kramer EF, Frechette RR, Nassereddin AT, Smoot M, Edwards ES, Kurup V, Naccarelli GV, Naik D, Kimmel SE, Mardini MT. Predictors of left atrial appendage thrombus in atrial fibrillation patients undergoing cardioversion. J Interv Card Electrophysiol 2024:10.1007/s10840-024-01868-x. [PMID: 38995603 DOI: 10.1007/s10840-024-01868-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/27/2024] [Accepted: 06/28/2024] [Indexed: 07/13/2024]
Abstract
BACKGROUND Atrial fibrillation and atrial flutter represent the most prevalent clinically significant cardiac arrhythmias. While the CHA2DS2-VASc score is commonly used to inform anticoagulation therapy decisions for patients with these conditions, its predictive power is limited. Therefore, we sought to improve risk prediction for left atrial appendage thrombus (LAAT), a known risk factor for stroke in these patients. METHODS We developed and validated an explainable machine learning model using the eXtreme Gradient Boosting algorithm with 5 × 5 nested cross-validation. The primary outcome was to predict the probability of LAAT in patients with atrial fibrillation and atrial flutter who underwent transesophageal echocardiogram prior to cardioversion. Our algorithm used 37 demographic, comorbid, and transthoracic echocardiographic variables. RESULTS A total of 795 patients were included in our analysis. LAAT was present in 11.3% of the patients. The average age of patients was 63.3 years and 34.7% were women. Patients with LAAT had significantly lower left ventricular ejection fraction (29.9% vs 43.5%; p < 0.001), lower E' lateral velocity (5.7 cm vs. 7.9 cm; p < 0.001) and higher E/A ratio (2.6 vs 1.8; p = 0.002). Our machine learning model achieved a high AUC of 0.79, with a high specificity of 0.82, and modest sensitivity of 0.57. Left ventricular ejection fraction was the most important variable in predicting LAAT. Patients were split into 10 buckets based on the percentile of their predicted probability of having thrombus. The lower the percentile (e.g., 10%), the lower the probability of having thrombus. Using a cutoff point of 0.16 which includes 10.0% of the patients, we can rule out thrombus with 100% confidence. CONCLUSION Using machine learning, we refined the predictive power of predicting LAAT and explained the model. These results show promise in providing better guidance for anticoagulation therapy and cardioversion in AF and AFL patients.
Collapse
Affiliation(s)
- Mohammed Ruzieh
- Department of Medicine, Division of Cardiovascular Medicine, College of Medicine, University of Florida, 1600 SW Archer road, PO Box100288, Gainesville, FL, 32610, USA.
| | - Chen Bai
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL, USA
| | - Emily Meisel
- College of Medicine, University of Florida, Gainesville, FL, USA
| | - Ethan F Kramer
- College of Medicine, University of Florida, Gainesville, FL, USA
| | | | - Ali T Nassereddin
- Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA
| | - Madeline Smoot
- Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA
| | - Emily S Edwards
- Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA
| | - Varsha Kurup
- Department of Medicine, College of Medicine, University of Florida, Gainesville, FL, USA
| | - Gerald V Naccarelli
- Penn State Heart and Vascular Institute, Penn State University, Hershey, PA, USA
| | - Dhaval Naik
- Department of Medicine, Division of Cardiovascular Medicine, College of Medicine, University of Florida, 1600 SW Archer road, PO Box100288, Gainesville, FL, 32610, USA
| | - Stephen E Kimmel
- Department of Epidemiology, College of Public Health and Health Professions & College of Medicine, University of Florida, Gainesville, FL, USA
| | - Mamoun T Mardini
- Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, Gainesville, FL, USA
| |
Collapse
|
2
|
Wang Y, Li M, Zhong L, Ren S, Li H, Tang Y, Li Z, Fei H. Left Atrial Strain as Evaluated by Two-Dimensional Speckle Tracking Predicts Left Atrial Appendage Dysfunction in Chinese Patients with Atrial Fibrillation. Cardiol Res Pract 2020; 2020:5867617. [PMID: 32274210 PMCID: PMC7115138 DOI: 10.1155/2020/5867617] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/06/2019] [Revised: 01/27/2020] [Accepted: 02/15/2020] [Indexed: 02/05/2023] Open
Abstract
Left atrial appendage (LAA) dysfunction identified by transesophageal echocardiography (TEE) is a powerful predictor of stroke in patients with atrial fibrillation (AF). The aim of our study is to assess if there is a correlation between the left atrial (LA) functional parameter and LAA dysfunction in the AF patients. This cross-sectional study included a total of 249 Chinese AF patients who did not have cardiac valvular diseases and were undergoing cardiac ablation. TEE was performed in all the patients who were categorized into two groups according to their left atrial appendage (LAA) function. A total of 120 of the 249 AF patients had LAA dysfunction. Univariate and multivariate logistic regression was conducted to assess the independent factors that correlated with the LAA dysfunction. Different predictive models for the LAA dysfunction were compared with the receiver operating characteristic (ROC) curve. The final ROC curve on the development and validation datasets was drawn based on the calculation of each area under the curves (AUC). Univariate and multivariate analysis showed that the peak left atrial strain (PLAS) was the most significant factor that correlated with the LAA dysfunction. PLAS did not show inferiority amongst all the models and revealed strong discrimination ability on both the development and validation datasets with AUC 0.818 and 0.817. Our study showed that a decrease in PLAS is independently associated with LAA dysfunction in the AF patients.
Collapse
Affiliation(s)
- Yu Wang
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
- Shantou University Medical College, Shantou, Guangdong 515000, China
| | - Mingqi Li
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
- Shantou University Medical College, Shantou, Guangdong 515000, China
| | - Lishan Zhong
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
| | - Siqi Ren
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
| | - Hezhi Li
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
| | - Yongwen Tang
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
| | - Zhilian Li
- Department of Medical Imaging, Guangzhou First People's Hospital, School of Medicine, South China University of Technology, Guangzhou, Guangdong 515000, China
| | - Hongwen Fei
- Department of Cardiology, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangdong Academy of Medical Sciences, Guangzhou, Guangdong 510100, China
| |
Collapse
|
3
|
Yingchoncharoen T, Jha S, Burchill LJ, Klein AL. Transesophageal Echocardiography in Atrial Fibrillation. Card Electrophysiol Clin 2016; 6:43-59. [PMID: 27063820 DOI: 10.1016/j.ccep.2013.11.006] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/20/2022]
Abstract
Transesophageal echocardiography (TEE) plays an important role in atrial fibrillation (AF), mainly to detect the presence of left atrial appendage (LAA) thrombus. It is useful in direct current cardioversion (DCC) guidance and for AF ablation and LAA occlusion. With the increasing number of patients affected by AF, the use of TEE will grow and become an important screening modality for LAA thrombus. Future direction includes broader multi-institutional use; further tools to risk stratify patients; and the use of a new spectrum of oral anticoagulants and their cost-effectiveness in patients with AF undergoing DCC, AF ablation, and LAA occlusion.
Collapse
Affiliation(s)
- Teerapat Yingchoncharoen
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Desk J1-5, Cleveland, OH 44195, USA
| | - Saurabh Jha
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Desk J1-5, Cleveland, OH 44195, USA
| | - Luke J Burchill
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Desk J1-5, Cleveland, OH 44195, USA
| | - Allan L Klein
- Department of Cardiovascular Medicine, Cleveland Clinic, 9500 Euclid Avenue, Desk J1-5, Cleveland, OH 44195, USA.
| |
Collapse
|
4
|
Efimova E, Ueberham L, Bode K, Arya A. A fortunate outcome after electrical cardioversion with a giant persistent left atrial thrombus. Is TOE-guided strategy more preferable in high risk patients? Int J Cardiol 2016; 208:1-3. [DOI: 10.1016/j.ijcard.2016.01.184] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/11/2016] [Accepted: 01/13/2016] [Indexed: 11/26/2022]
|
5
|
Fonseca R, Negishi K, Otahal P, Marwick TH. Temporal changes in appropriateness of cardiac imaging. J Am Coll Cardiol 2015; 65:763-773. [PMID: 25720619 DOI: 10.1016/j.jacc.2014.11.057] [Citation(s) in RCA: 67] [Impact Index Per Article: 7.4] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/28/2014] [Revised: 11/23/2014] [Accepted: 11/24/2014] [Indexed: 01/02/2023]
Abstract
BACKGROUND Appropriate use criteria (AUC) for cardiac imaging have been available for almost 10 years. The extent to which there has been a reported improvement in appropriate use is undefined. OBJECTIVES This study systematically reviewed published evidence to identify whether the promulgation of AUC has led to an improvement in the proportion of appropriate cardiac imaging requests. METHODS Electronic databases were systematically searched for English-language papers related to AUC and cardiovascular imaging. We found 59 reports involving 103,567 tests that were published from 2000 to 2012. The rate of appropriate testing over time was analyzed in a meta-regression. RESULTS New AUC were associated with apparent improvements in appropriateness for transthoracic echocardiography (TTE) (80% [95% confidence interval (CI): 0.75 to 0.84] vs. 85% [95% CI: 0.81 to 0.89]), transesophageal echocardiography (TEE) (89% [95% CI: 0.81 to 0.94] vs. 95% [95% CI: 0.93 to 0.96]) and computed tomography angiography (CTA) (37% [95% CI: 0.21 to 0.55] vs. 55% [95% CI: 0.44 to 0.65]) but not stress echocardiography (53% [95% CI: 0.45 to 0.61] vs. 52% [95% CI: 0.42 to 0.61]) or single-photon emission computed tomography (72% [95% CI: 0.66 to 0.77] vs. 68% [95% CI: 0.60 to 0.74]). Although there were no correlations between the proportion of appropriate TTEs and published year (p = 0.36) for 2007 AUC, there was a positive correlation between proportion of appropriateness and the year of publication (p = 0.01) for 2011 AUC. There was a significant decrease in the proportion of appropriateness over time using the 2007 TEE AUC (p = 0.03) and 2006 CT AUC (p = 0.02). There were no meaningful associations between appropriateness and publication year for stress echocardiography, CTA, or single-photon emission computed tomography. CONCLUSIONS Rates of reported appropriate use in imaging show improvements for TTE and CTA but not for stress imaging and TEE. The observed reductions in imaging studies are not matched by reported rates of appropriate use.
Collapse
Affiliation(s)
- Ricardo Fonseca
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Australia
| | - Kazuaki Negishi
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Australia
| | - Petr Otahal
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Australia
| | - Thomas H Marwick
- Menzies Institute for Medical Research, University of Tasmania, Hobart, Australia.
| |
Collapse
|
6
|
Fonseca R, Marwick TH. How I do it: judging appropriateness for TTE and TEE. Cardiovasc Ultrasound 2014; 12:22. [PMID: 24961689 PMCID: PMC4079626 DOI: 10.1186/1476-7120-12-22] [Citation(s) in RCA: 8] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/20/2014] [Accepted: 06/05/2014] [Indexed: 11/10/2022] Open
Abstract
The increasing cost of healthcare is a widespread international problem to which the cost of imaging has been an important contributor. Some imaging tests are ordered inappropriately and contribute to wasted use of resources. Appropriate use criteria have been developed in the USA in order to guide test selection, but there are a number of problems, including the evidence base for these criteria and the steps that can be taken to change physician practice. A restrictive approach to test ordering is difficult to fit to the nuances of clinical presentation and may compromise patient care. We propose an alternative approach to physician guidance based on the most common markers of inappropriate testing.
Collapse
Affiliation(s)
- Ricardo Fonseca
- Menzies Research Institute Tasmania, 17 Liverpool St, Hobart, Tasmania 7000, Australia
| | - Thomas H Marwick
- Menzies Research Institute Tasmania, 17 Liverpool St, Hobart, Tasmania 7000, Australia
| |
Collapse
|