Left Atrial Strain Predicts Stroke Recurrence and Death in Patients With Cryptogenic Stroke

Vera, Alberto; Cecconi, Alberto; Ximénez-Carrillo, Álvaro; Ramos, Carmen; Martínez-Vives, Pablo; Lopez-Melgar, Beatriz; Sanz-García, Ancor; Ortega, Guillermo; Aguirre, Clara; Montes, Álvaro; Vivancos, José; Jiménez-Borreguero, Luis Jesús; Alfonso, Fernando

doi:10.1016/j.amjcard.2023.10.001

Cited by 5 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…21,28 Using left atrial strain may improve risk stratification and decision-making in patients with cardio embolism, particularly in long-term rhythm monitoring and/or empirical anticoagulant therapy. 29 Our research also indicated that PALS assessed by speckle tracking echocardiography can identify left atrial dysfunction, closely related to thrombosis risk and independent of other cardiovascular risk factors. AF can cause hemodynamic changes in the atrium, increasing the risk of stroke and other thromboembolic events.…”

Section: Resultssupporting

confidence: 59%

Machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients based on multimodal echocardiographic parameters

Zeng,

Chang,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND: This study sought to develop a robust machine learning (ML)-based predictive model that synthesizes multimodal echocardiographic data and clinical risk factors to assess thrombosis risk in patients with non-valvular atrial fibrillation (NVAF). METHODS AND RESULTS: A total of 402 NVAF patients scheduled for AF radiofrequency ablation and/or left atrial appendage closure at the First Affiliated Hospital of Guangxi Medical University from January 2020 to December 2023 were prospectively collected. Among them, there were 289 males (71.9%) and 113 females (28.1%), with a mean age of 59.7 years. There were 142 patients (35.3%) with left atrial thrombus/spontaneous echocardiographic contrast (LAT/SEC) and 260 patients (64.7%) without LAT/SEC. We constructed seven ML models from the collected clinical data, biochemical markers, and multimodal echocardiographic parameters. Models were evaluated via ROC curves; SHAP values were employed for feature importance analysis.The integration of multimodal echocardiographic parameters with clinical risk factors based on sophisticated ML algorithms significantly improved the precision of thrombus risk prediction in patients with NVAF. Specifically, the XGBoost model (AUC 0.959, 95% CI 0.925?0.993) slightly outperformed the traditional Logistic regression model (AUC 0.949, 95% CI: 0.911-0.987) in predicting thrombus formation risk in NVAF patients, and showed superior predictive ability compared to other ML algorithms. Additionally, XGBoost offered greater clinical net benefit within a threshold probability range of 0.1 to 1.0. SHAP analysis revealed that left atrial structure (left atrial volume index, three-dimensional sphericity index), hemodynamic parameters (left atrial acceleration factor and S/D ratio), and functional parameters (peak atrial longitudinal strain) were important features in predicting the risk of thrombus formation in NVAF patients, with reduced peak atrial longitudinal strain being the most important risk factor for predicting thrombus. Conclusion: Developing a predictive model utilizing ML techniques that incorporate multimodal echocardiographic parameters in conjunction with clinical risk factors has the potential to enhance the predictive accuracy of the thrombosis risk in individuals with NVAF. The XGBoost model shows that decreased PALS, hemodynamic abnormalities and left atrium spherical remodeling are significant factors correlated with increased risk of thrombus in NVAF.

show abstract

Section: Resultssupporting

confidence: 59%

Machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients based on multimodal echocardiographic parameters

Zeng,

Chang,

Zhang

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…A consensus reached through a meta-analysis of a large number of healthy control subjects has established a normal reference range (Table S2) [32]. LA-Sr values of ≤25.8% [47,48] have been documented as indicators for identifying AF after cryptogenic strokes, and an elevated risk of stroke recurrence and mortality [11]. In the general population, other authors found that LA-Sr < 23% and 2D-LAEF < 55% were independently associated with an increased risk of cardiac events and new-onset AF [44].…”

Section: Relationship Between Reduced La-sr < 26% and The Rest Of Tte...mentioning

confidence: 99%

“…Among them, 36% exhibited an LA-Sr value of <26%, but this specific condition did not show associations with age, sex, or traditional cardiovascular risk factors, including diabetes, hypertension, or chronic kidney disease, nor did it correlate with a history of heart failure or ischemic cardiopathy (Table 1). Not even the CHA2DS2-VASc score revealed differences among patients with an LA-Sr < 26%, emphasizing the potential limitations in discerning thrombogenic risk based on the evidence in the literature regarding the predictive power of ECG and TTE data [10][11][12][13][14][15][16][17][18]29,30,[45][46][47][48].…”

Section: Relationship Between Reduced La-sr < 26% and The Rest Of Tte...mentioning

confidence: 99%

See 1 more Smart Citation

Echocardiography and Electrocardiography in Detecting Atrial Cardiomyopathy: A Promising Path to Predicting Cardioembolic Strokes and Atrial Fibrillation

Gentille-Lorente,

Hernández-Pinilla,

Satue-Gracia

et al. 2023

JCM

View full text Add to dashboard Cite

(1) Background: Atrial cardiomyopathy constitutes an intrinsically prothrombotic atrial substrate that may promote atrial fibrillation and thromboembolic events, especially stroke, independently of the arrhythmia. Atrial reservoir strain is the echocardiography marker with the most robust evidence supporting its prognostic utility. The main aim of this study is to identify atrial cardiomyopathy by investigating the association between left atrial dysfunction in echocardiography and P-wave abnormalities in the surface electrocardiogram. (2) Methods: This is a community-based, multicenter, prospective cohort study. A randomized sample of 100 patients at a high risk of developing atrial fibrillation were evaluated using diverse echocardiography imaging techniques, and a standard electrocardiogram. (3) Results: Significant left atrial dysfunction, expressed by a left atrial reservoir strain < 26%, showed a relationship with the dilation of the left atrium (p < 0.001), the left atrial ejection fraction < 50% (p < 0.001), the presence of advanced interatrial block (p = 0.032), P-wave voltage in lead I < 0.1 mV (p = 0.008), and MVP ECG score (p = 0.036). (4) Conclusions: A significant relationship was observed between left atrial dysfunction and the presence of left atrial enlargement and other electrocardiography markers; all of them are non-invasive biomarkers of atrial cardiomyopathy.

show abstract

Mitral regurgitation, the left atrium and atrial fibrillation:unlikely bedfellows or natural kindreds?

Coisne,

Lancellotti,

Vannan

2024

European Heart Journal - Cardiovascular Imaging

View full text Add to dashboard Cite

Left Atrial Strain Predicts Stroke Recurrence and Death in Patients With Cryptogenic Stroke

Cited by 5 publications

References 21 publications

Machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients based on multimodal echocardiographic parameters

Machine learning model for predicting left atrial thrombus or spontaneous echo contrast in non-valvular atrial fibrillation patients based on multimodal echocardiographic parameters

Echocardiography and Electrocardiography in Detecting Atrial Cardiomyopathy: A Promising Path to Predicting Cardioembolic Strokes and Atrial Fibrillation

Mitral regurgitation, the left atrium and atrial fibrillation:unlikely bedfellows or natural kindreds?

Contact Info

Product

Resources

About