Coagulation Biomarkers and Clinical Outcomes in Elderly Patients With Nonvalvular Atrial Fibrillation: ANAFIE Subcohort Study

Machine learning-based model to predict composite thromboembolic events among Chinese elderly patients with atrial fibrillation

OBJECTIVE

Accurate prediction of survival prognosis is helpful to guide clinical decision-making. The aim of this study was to develop a model using machine learning techniques to predict the occurrence of composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation(AF). These events encompass newly diagnosed cerebral ischemia events, cardiovascular events, pulmonary embolism, and lower extremity arterial embolism.

METHODS

This retrospective study included 6,079 elderly hospitalized patients (≥ 75 years old) with AF admitted to the People's Liberation Army General Hospital in China from January 2010 to June 2022. Random forest imputation was used for handling missing data. In the descriptive statistics section, patients were divided into two groups based on the occurrence of CTEs, and differences between the two groups were analyzed using chi-square tests for categorical variables and rank-sum tests for continuous variables. In the machine learning section, the patients were randomly divided into a training dataset (n = 4,225) and a validation dataset (n = 1,824) in a 7:3 ratio. Four machine learning models (logistic regression, decision tree, random forest, XGBoost) were trained on the training dataset and validated on the validation dataset.

RESULTS

The incidence of composite thromboembolic events was 19.53%. The Least Absolute Shrinkage and Selection Operator (LASSO) method, using 5-fold cross-validation, was applied to the training dataset and identified a total of 18 features that exhibited a significant association with the occurrence of CTEs. The random forest model outperformed other models in terms of area under the curve (ACC: 0.9144, SEN: 0.7725, SPE: 0.9489, AUC: 0.927, 95% CI: 0.9105-0.9443). The random forest model also showed good clinical validity based on the clinical decision curve. The Shapley Additive exPlanations (SHAP) showed that the top five features associated with the model were history of ischemic stroke, high triglyceride (TG), high total cholesterol (TC), high plasma D-dimer, age.

CONCLUSIONS

This study proposes an accurate model to stratify patients with a high risk of CTEs. The random forest model has good performance. History of ischemic stroke, age, high TG, high TC and high plasma D-Dimer may be correlated with CTEs.

Asymmetric dimethylarginine correlates with indicators of prethrombotic state in patients with nonvalvular atrial fibrillation

OBJECTIVE

The mechanism of asymmetric dimethylarginine (ADMA) in thrombosis in patients with nonvalvular atrial fibrillation (NVAF) is still unclear. Our aim was to investigate the relationship between ADMA and indicators of prethrombotic state in NVAF patients and to analyze the predictive role of ADMA in NVAF thrombosis.

METHODS

A total of 192 NVAF patients were continuously selected from January 2023 to October 2023. Plasma ADMA levels were measured by high-performance liquid chromatography. P-selectin (P-sel), von Willebrand factor (vWF), D-dimer (D-D), and plasminogen activator inhibitor-1 (PAI-1) levels were measured by enzyme-linked immunosorbent assay (ELISA). Nitric oxide (NO) levels were measured by the nitrate reductase assay for plasma nitrite/nitrate, then the Griess method (Shanghai Hailian Biotechnology Co., Shanghai, China) was used to calculate plasma NO levels.

RESULTS

In our study, ADMA levels were significantly elevated and positively correlated with P-sel, vWF, D-D, and PAI-1, whereas NO levels were significantly negatively correlated with these prethrombotic factors in NVAF. Furthermore, multifactorial logistic regression analysis showed that ADMA and LA diameter were independent predictors of high thrombosis risk (CHA2DS2-VASc ≥2 score) in patients with NVAF.

CONCLUSIONS

Our findings suggested that ADMA correlated with the prethrombotic state in NVAF and that reduction of ADMA levels in NVAF patients may be a novel therapeutic strategy for thrombosis risk reduction.

Association Between Atrial Fibrillation Symptoms and Clinical Outcomes: A Prospective Multicenter Registry Study

The presence of symptoms plays an important role in determining whether to focus on rhythm control or rate control when treating atrial fibrillation (AF). Previous comparative studies on the clinical outcomes of symptomatic and asymptomatic AF have yielded inconsistent results, and a link between AF symptoms and left atrial (LA) remodeling is not established. Patients selected from the COmparison study of Drugs for symptom control and complication prEvention of AF (CODE-AF) registry, which is a prospective, multicenter study consisting of patients with non-valvular AF, were grouped into 2 groups: symptomatic and asymptomatic. The primary outcome was a composite of the following cardiovascular outcomes: all-cause death, ischemic stroke, transient ischemic attack, systemic embolism, myocardial infarction, and heart failure hospitalization. Of 10,210 patients with AF, 4,327 (42%) had symptomatic AF. The asymptomatic group had an older mean age, more men, and more patients with hypertension and diabetes mellitus than the symptomatic group. The asymptomatic group had a larger left atrium (LA) diameter (43.6 vs 42.2 mm, p <0.001) than the symptomatic group. During a median follow-up of 32.9 (29.5 to 36.4) months, the asymptomatic and symptomatic groups showed similar incidences of the primary outcome (1.44 vs 1.45 per 100 person-years; log-rank, p = 0.8). In conclusion, the absence of AF symptoms is associated with increased LA. However, symptomatic and asymptomatic patients with AF have a similar risk of cardiovascular outcomes. This suggests that beneficial treatment for AF may be considered regardless of whether patients have symptomatic or asymptomatic AF.

Characterization of Biomarkers of Thrombo-Inflammation in Patients with First-Diagnosed Atrial Fibrillation

Patients with first-diagnosed atrial fibrillation (FDAF) exhibit major adverse cardiovascular events (MACEs) during follow-up. Preclinical models have demonstrated that thrombo-inflammation mediates adverse cardiac remodeling and atherothrombotic events. We have hypothesized that thrombin activity (FIIa) links coagulation with inflammation and cardiac fibrosis/dysfunction. Surrogate markers of the thrombo-inflammatory response in plasma have not been characterized in FDAF. In this prospective longitudinal study, patients presenting with FDAF (n = 80), and 20 matched controls, were included. FIIa generation and activity in plasma were increased in the patients with early AF compared to the patients with chronic cardiovascular disease without AF (controls; p < 0.0001). This increase was accompanied by elevated biomarkers (ELISA) of platelet and endothelial activation in plasma. Pro-inflammatory peripheral immune cells (TNF-α+ or IL-6+) that expressed FIIa-activated protease-activated receptor 1 (PAR1) (flow cytometry) circulated more frequently in patients with FDAF compared to the controls (p < 0.0001). FIIa activity correlated with cardiac fibrosis (collagen turnover) and cardiac dysfunction (NT-pro ANP/NT-pro BNP) surrogate markers. FIIa activity in plasma was higher in patients with FDAF who experienced MACE. Signaling via FIIa might be a presumed link between the coagulation system (tissue factor-FXa/FIIa-PAR1 axis), inflammation, and pro-fibrotic pathways (thrombo-inflammation) in FDAF.