We probed whether the addition of hemoglobin (HGB) or the female sex (SEX) as variables would provide additional prognostic value to the APPLE score.

An optimized APPLE score was used to evaluate the AF recurrence risk in the consecutive populations with AF post-catheter ablation including the development (n = 562) and validation (n = 239) cohorts.

In the populations of AF recurrence, most patients were female sex (103/164, 62.8%), and had the lower HGB levels. After adjusting for the APPLE score, HGB level (Odds Ratio [OR], 0.828; 95% Confidence Interval [CI], 0.749-0.915; P < 0.001) and female sex (OR, 1.596; 95% CI, 1.140-2.235; P = 0.006) independently predicted AF recurrence. Adjusting the APPLE score by HGB variable improved its predictive ability for AF recurrence (C-statistic value from 0.675 to 0.711, P = 0.010), which also increased the C-indexes in the external validation (from 0.653 to 0.725, p = 0.023). The female sex variable also enhanced the C-statistic value of the APPLE score for AF recurrence at both development and external validation (C-indices from 0.675 to 0.691, P = 0.004; C-indices from 0.653 to 0.704, p = 0.037, respectively). Decision curve analysis showed that the HGB plus APPLE score was better than the SEX plus APPLE score in predicting AF recurrence in two following AF populations.

The inclusion of HGB level and female sex variables improved the predictability and clinical usefulness of adjusted APPLE score. Adjustment of the APPLE score by HGB levels may provide better predictive value than inclusion of the female sex variable.

Radiofrequency catheter ablation (RFCA) has become an important strategy for treating atrial fibrillation (AF), and postoperative recurrence represents a significant and actively discussed clinical concern. The recurrence after RFCA is considered closely related to inflammation. Systemic immune inflammation index (SII) is a novel inflammation predictor based on neutrophils, platelets, and lymphocytes, and is considered a biomarker that comprehensively reflects the immune inflammatory status of the body.

To explore the predictive effect of the SII on AF recurrence after RFCA and its predictive value in combination with the existing APPLE score for AF recurrence after RFCA in patients with non-valvular AF (NVAF).

We retrospectively included 457 patients with NVAF first receiving RFCA and classified them into the recurrent or non-recurrent group. We also investigated the predictive role of SII on AF recurrence following RFCA. Finally, we explored and compared the additional predictive value of the SII after combining with the APPLE score.

After 12 months of follow-up, 113 (24.7%) patients experienced recurrence. High SII has been demonstrated to be an independent predictor for postoperative AF recurrence. Receiver operating characteristic and decision curve analysis (DCA), as well as net reclassification improvement (NRI) and integrated discrimination improvement (IDI) results, showed that SII combined with the APPLE score had higher predictive efficiency than using the SII or APPLE score alone. The area under the curve of the combined model (0.662, 95% confidence interval: 0.602-0.722) significantly increased compared with that of the SII and APPLE scores alone (P < 0.001). The combined model resulted in an NRI of 29.6% and 34.1% and IDI of 4.9% and 3.5% in predicting AF recurrence compared with the SII and APPLE scores alone, respectively (all P < 0.001). The SII, APPLE score, and their combination demonstrated greater clinical utility than did the treat-all and treat-none strategies over the 20-80% risk threshold according to the DCA.

The SII was a predictor of recurrence after RFCA of AF. Moreover, the SII enhanced the predictability of the APPLE score for post-RFCA AF recurrence, providing valuable insights for physicians to optimise patient selection and develop personalised treatment plans.

Catheter ablation is a common treatment for atrial fibrillation (AF), but recurrence rates remain variable. Predicting the success of catheter ablation is crucial for patient selection and management. This research seeks to create a machine learning model to forecast the early recurrence of atrial fibrillation following catheter ablation.

A prospective longitudinal study was conducted using data from the Iranian AF registry. The dataset included 402 consecutive AF patients who underwent radiofrequency catheter ablation. The primary outcome was early recurrence of AF within 3 months' post-ablation. Data preprocessing and feature selection were performed, followed by the development and evaluation of various machine learning models. The CatBoost model was selected as the best-performing model.

The study population had a mean age of 57.30 ± 14.05 years, and 61.4% were male. AF recurrence occurred in 26.1% of patients. The CatBoost model, utilizing 35 features, achieved an accuracy of 92.5% in predicting AF recurrence. The model demonstrated high sensitivity (88.6%) and specificity (94.0%), with an area under the ROC curve of 0.96. Paroxysmal AF, BUN, Cr, age, mitral regurgitation, LA velocity, and mild valvular heart disease were among the most important predictive features.

Machine learning methods, particularly the CatBoost model, demonstrate high accuracy in predicting early catheter ablation outcomes in AF patients. The developed model has the potential to improve patient care and decision-making by identifying patients most likely to benefit from the procedure. Further studies with larger sample sizes and external validation are warranted to assess the generalizability of this method for catheter ablation outcome prediction in AF patients.

The benefits of rhythm control in early atrial fibrillation (AF) are increasingly recognized. This study aimed to investigate whether early AF ablation contributes to long-term sinus rhythm maintenance and to identify a suitable predictive score.

According to diagnosis-to-ablation time, this study prospectively enrolled 245 patients with very early AF, 262 with early AF, and 588 with late AF for radiofrequency ablation from June 2017 to December 2022. Clinical data, risk scores, and follow-up results were collected and analyzed.

Baseline characteristics were similar among the three cohorts. During a median follow-up period of 26 months, AF recurrence was observed in 61 (24.9%), 66 (25.2%), and 216 (36.7%) patients in the very early, early, and late AF cohorts, respectively. In the multivariable-adjusted model, very early and early AF were associated with a reduced risk of AF recurrence, with hazard ratios of 0.72 (95% confidence interval [CI] 0.52-0.99) and 0.57 (95% CI 0.41-0.78), respectively. The APPLE score demonstrated the highest predictive power for very early AF, with an area under the curve (AUC) of 0.74. However, its predictive power decreased with time from diagnosis, showing low predictive power for late AF (AUC = 0.58). In addition, the time-dependent concordance index showed consistent results. For very early AF, the Akaike information criterion and decision curve analysis showed that APPLE had the highest predictive value.

Very early AF ablation was associated with a lower recurrence rate, and the APPLE score provided a higher predictive value for these patients. (URL: https://www.chictr.org.cn/; Unique identifier: ChiCTR-OIN-17013021).

There has been a significant increase in the prevalence of atrial fibrillation (AF) over the past 30 years. Pulmonary vein isolation (PVI) is an effective treatment for AF, but research investigations have shown that AF recurrence still occurs in a significant number of patients after ablation. Heart rhythm outcomes following catheter ablation are correlated with numerous clinical factors, and researchers developed predictive models by integrating risk factors to predict the risk of recurrence of atrial fibrillation. The purpose of this article is to outline the risk scores for predicting cardiac rhythm outcomes after PVI and to discuss the modifiable factors that increase the risk of recurrence of AF, with the hope of further improving catheter ablation efficacy through preoperative identification of high-risk populations and postoperative management of modifiable risk factors.

Atrial fibrillation (AF) is a disease of high heterogeneity, and the association between AF phenotypes and the outcome of different catheter ablation strategies remains unclear. Conventional classification of AF (e.g. according to duration, atrial size, and thromboembolism risk) fails to provide reference for the optimal stratification of the prognostic risks or to guide individualized treatment plan. In recent years, research on machine learning has found that cluster analysis, an unsupervised data-driven approach, can uncover the intrinsic structure of data and identify clusters of patients with pathophysiological similarity. It has been demonstrated that cluster analysis helps improve the characterization of AF phenotypes and provide valuable prognostic information. In our cohort of AF inpatients undergoing radiofrequency catheter ablation, we used unsupervised cluster analysis to identify patient subgroups, to compare them with previous studies, and to evaluate their association with different suitable ablation patterns and outcomes.

The participants were AF patients undergoing radiofrequency catheter ablation at West China Hospital between October 2015 and December 2017. All participants were aged 18 years or older. They underwent radiofrequency catheter ablation during their hospitalization. They completed the follow-up process under explicit informed consent. Patients with AF of a reversible cause, severe mitral stenosis or prosthetic heart valve, congenital heart disease, new-onset acute coronary syndrome within three months prior to the surgery, or a life expectancy less than 12 months were excluded according to the exclusion criteria. The cohort consisted of 1102 participants with paroxysmal or persistent/long-standing persistent AF. Data on 59 variables representing demographics, AF type, comorbidities, therapeutic history, vital signs, electrocardiographic and echocardiographic findings, and laboratory findings were collected. Overall, data for the variables were rarely missing (<5%), and multiple imputation was used for correction of missing data. Follow-up surveys were conducted through outpatient clinic visits or by telephone. Patients were scheduled for follow-up with 12-lead resting electrocardiography and 24-hours Holter monitoring at 3 months and 6 months after the ablation procedure. Early ablation success was defined as the absence of documented AF, atrial flutter, or atrial tachycardia >30 seconds at 6-month follow-up. Hierarchical clustering was performed on the 59 baseline variables. All characteristic variables were standardized to have a mean of zero and a standard deviation of one. Initially, each patient was regarded as a separate cluster, and the distance between these clusters was calculated. Then, the Ward minimum variance method of clustering was used to merge the pair of clusters with the minimum total variance. This process continued until all patients formed one whole cluster. The "NbClust" package in R software, capable of calculating various statistical indices, including pseudo t2 index, cubic clustering criterion, silhouette index etc, was applied to determine the optimal number of clusters. The most frequently chosen number of clusters by these indices was selected. A heatmap was generated to illustrate the clinical features of clusters, while a tree diagram was used to depict the clustering process and the heterogeneity among clusters. Ablation strategies were compared within each cluster regarding ablation efficacy.

Five statistically driven clusters were identified: 1) the younger age cluster (n=404), characterized by the lowest prevalence of cardiovascular and cerebrovascular comorbidities but the highest prevalence of obstructive sleep apnea syndrome (14.4%); 2) a cluster of elderly adults with chronic diseases (n=438), the largest cluster, showing relatively higher rates of hypertension, diabetes, stroke, and chronic obstructive pulmonary disease; 3) a cluster with high prevalence of sinus node dysfunction (n=160), with patients showing the highest prevalence of sick sinus syndrome and pacemaker implantation; 4) the heart failure cluster (n=80), with the highest prevalence of heart failure (58.8%) and persistent/long-standing persistent AF (73.7%); 5) prior coronary artery revascularization cluster (n=20), with patients of the most advanced age (median: 69.0 years old) and predominantly male patients, all of whom had prior myocardial infarction and coronary artery revascularization. Patients in cluster 2 achieved higher early ablation success with pulmonary veins isolation alone compared to extensive ablation strategies (79.6% vs. 66.5%; odds ratio [OR]=1.97, 95% confidence interval [CI]: 1.28-3.03). Although extensive ablation strategies had a slightly higher success rate in the heart failure group, the difference was not statistically significant.

This study provided a unique classification of AF patients undergoing catheter ablation by cluster analysis. Age, chronic disease, sinus node dysfunction, heart failure and history of coronary artery revascularization contributed to the formation of the five clinically relevant subtypes. These subtypes showed differences in ablation success rates, highlighting the potential of cluster analysis in guiding individualized risk stratification and treatment decisions for AF patients.

Background: Catheter ablation (CA) is an important treatment strategy to reduce the burden and complications of atrial fibrillation (AF). This study aims to predict the risk of recurrence in patients with paroxysmal AF (pAF) after CA by an artificial intelligence (AI)-enabled electrocardiography (ECG) algorithm. Methods and Results: 1618 ≥ 18 years old patients with pAF who underwent CA in Guangdong Provincial People's Hospital from 1 January 2012 to 31 May 2019 were enrolled in this study. All patients underwent pulmonary vein isolation (PVI) by experienced operators. Baseline clinical features were recorded in detail before the operation and standard follow-up (≥12 months) was conducted. The convolutional neural network (CNN) was trained and validated by 12-lead ECGs within 30 days before CA to predict the risk of recurrence. A receiver operating characteristic curve (ROC) was created for the testing and validation sets, and the predictive performance of AI-enabled ECG was assessed by the area under the curve (AUC). After training and internal validation, the AUC of the AI algorithm was 0.84 (95% CI: 0.78-0.89), with a sensitivity, specificity, accuracy, precision and balanced F Score (F1 score) of 72.3%, 95.0%, 92.0%, 69.1% and 0.707, respectively. Compared with current prognostic models (APPLE, BASE-AF2, CAAP-AF, DR-FLASH and MB-LATER), the performance of the AI algorithm was better (p < 0.01). Conclusions: The AI-enabled ECG algorithm seemed to be an effective method to predict the risk of recurrence in patients with pAF after CA. This is of great clinical significance in decision-making for personalized ablation strategies and postoperative treatment plans in patients with pAF.

Several models have been developed to predict the risk of atrial fibrillation (AF) recurrence after radiofrequency catheter ablation (RFCA). However, these models are of poor quality from the start. We, therefore, aimed to develop and validate a predictive model for post-operative recurrence of AF.

In a study including 433 patients undergoing the first circumferential pulmonary vein isolation (CPVI) procedure, independent predictors of AF recurrence were retrospectively identified. Using the Cox regression of designated variables, a risk model was developed in a random sample of 70% of the patients (development cohort) and validated in the remaining (validation cohort) 30%. The accuracy and discriminative power of the predictive models were evaluated in both cohorts.

During the established 12 months follow-up, 134 patients (31%) recurred. Six variables were identified in the model including age, coronary artery disease (CAD), heart failure (HF), hypertension, transient ischemic attack (TIA) or cerebrovascular accident (CVA), and left atrial diameter (LAD). The model showed good discriminative power in the development cohort, with an AUC of 0.77 (95% confidence interval [CI], 0.69-0.86). Furthermore, the model shows good agreement between actual and predicted probabilities in the calibration curve. The above results were confirmed in the validation cohort. Meanwhile, decision curve analysis (DCA) for this model also demonstrates the advantages of clinical application.

A simple risk model to predict AF recurrence after ablation was developed and validated, showing good discriminative power and calibration.

As AF-associated morbidity and mortality are increasing, there is an acute need for improved surveillance and prevention strategies to reduce the impact of AF and related strokes. Specific echocardiographic parameters that can best predict future onset of AF within 3 months are lacking.

Twenty patients with AF, as identified by presence of ICD-9 diagnosis code, were compared with a control group of twenty age- and sex-matched patients selected from the same clinic population but without a diagnosis of AF. Transthoracic echocardiograms (TTE) obtained within 90 days prior to first documented AF episode (study group) or obtained closest to first clinic visit (control) were selected for review.

Baseline characteristics, including age, BMI, presence of hypertension, hyperlipidemia, diabetes, and heart failure were comparable. Increased left atrial (LA) size (end systolic major axis in 2-chamber view: AF 4.62±0.03 vs control 3.79±0.21, P =0.03), increased mitral inflow (E/A ratio: AF 1.35±0.15 vs control 1.06±0.07, P =0.04), and reduced LA global longitudinal strain (AF -2.69±0.26 vs control - 3.59±0.31, P =0.04) were most closely associated with AF compared with the control group. Multivariate logistic regression was used to develop predictive models for AF onset. A combination of imaging and traditional clinical risk factors was the best AF prediction model with AUC of 0.94, which greatly exceeds the current best predictors published. From these parameters, we developed the SMASH2 scoring system for 90- day AF risk estimation.

Risk factors for AF and early features of atrial cardiomyopathy including male sex, hypertension, LA enlargement, reduced mitral inflow, and reduced LA strain are powerful predictors of AF onset within 90 days, and may be used to prognosticate future AF risk.

The aim of this study is to assess serum human epididymis protein 4 (HE-4) levels as a biomarker for predicting the recurrence of atrial fibrillation (AF) after catheter ablation. This was a prospective observational study that enrolled one hundred eighty-four consecutive nonvalvular AF patients (65 persistent, 119 paroxysmal) who were eligible for their first ablation. Multiple Cox proportional hazards models and Kaplan-Meier curve analyses were used to test the association between serum HE-4 levels and AF recurrence after catheter ablation. During the 12-month follow-up, we observed that 47 patients (25.5%) experienced AF recurrence. Patients were divided into tertiles of HE-4 level (T1: < 50 pmol/L; T2: ≥ 50 pmol/L). The AF recurrence rate of higher serum HE-4 level patients was significantly increased (34.6% vs 13.8%, P < 0.001). Generalized additive models were used to visually assess functional relationships between the serum HE-4 levels and the risk of AF recurrence. When stratified with serum levels as the cut-off value, Kaplan-Meier analysis showed that patients with serum HE-4 levels (> 50 pmol/L) had a significantly increased risk of AF recurrence. In addition, multivariate Cox proportional hazard modelling revealed that HE-4 (≥ 50 pmol/L) (HR 2.65; 95% CI 1.34, 5.27, P = 0.005) was independent predictors of AF recurrence. Serum HE-4 levels in patients with AF are associated with postoperative recurrence of AF, and high HE-4 levels are an independent predictor of AF recurrence after ablation.

We assessed the performance of modelsf (risk scores) for predicting recurrence of atrial fibrillation (AF) in patients who have undergone catheter ablation.

Systematic searches of bibliographic databases were conducted (November 2018). Studies were eligible for inclusion if they reported the development, validation, or impact assessment of a model for predicting AF recurrence after ablation. Model performance (discrimination and calibration) measures were extracted. The Prediction Study Risk of Bias Assessment Tool (PROBAST) was used to assess risk of bias. Meta-analysis was not feasible due to clinical and methodological differences between studies, but c-statistics were presented in forest plots. Thirty-three studies developing or validating 13 models were included; eight studies compared two or more models. Common model variables were left atrial parameters, type of AF, and age. Model discriminatory ability was highly variable and no model had consistently poor or good performance. Most studies did not assess model calibration. The main risk of bias concern was the lack of internal validation which may have resulted in overly optimistic and/or biased model performance estimates. No model impact studies were identified.

Our systematic review suggests that clinical risk prediction of AF after ablation has potential, but there remains a need for robust evaluation of risk factors and development of risk scores.

Chronic kidney disease (CKD) has been associated with incident atrial fibrillation (AF) and its complications, but data from Asian cohorts are limited.

To explore the relationship of AF recurrence after catheter ablation (CA) with eGFR as a continuous variable, and with different renal function categories (normal: estimated glomerular filtration rate [eGFR] ≥90mL/min/1.73 m²; mild CKD: eGFR 60-89mL/min/1.73 m²; moderate CKD: eGFR 45-59mL/min/1.73 m²; severe CKD: <45mL/min/1.73 m²), using data from the Guangzhou Atrial Fibrillation Ablation Registry.

We studied consecutive symptomatic adult patients with non-valvular AF, refractory to at least one antiarrhythmic drug and eligible for CA, in Guangdong General Hospital between June 2011 and August 2015.

Data were available from 1407 consecutive patients (mean age 57.3±11.5 years; 68% men) with non-valvular AF undergoing radiofrequency or cryoballoon ablation. During a mean follow-up of 20.7±8.8 months, 18.6% of patients with paroxysmal AF and 50.5% with non-paroxysmal AF had AF recurrence. On multivariable analysis, eGFR (hazard ratio [HR] 0.97, 95% confidence interval [CI] 0.96-0.97) was an independent risk factor for AF recurrence, with a good predictive value (area under the curve 0.74, 95% CI 0.72-0.77; P<0.01). In the normal renal function, and mild, moderate and severe CKD categories, AF recurrence rates were 11.5%, 29.3%, 72.0% and 93.3%, respectively. Compared with normal renal function, there were stepwise increased risks of AF recurrence with mild CKD (HR 3.30, 95% CI 2.55-4.26; P<0.01), moderate CKD (HR 9.43, 95% CI 6.76-13.16; P<0.01) and severe CKD (HR 12.35, 95% CI 6.93-21.99; P<0.01).

In a large cohort of Asian patients with AF, renal dysfunction increased the risk of AF recurrence after CA. AF recurrence gradually increased with worsening kidney function in this cohort.

Catheter ablation has become an effective treatment modality for atrial fibrillation (AF). However, the relationship between common pulmonary vein (PV) and recurrent atrial tachyarrhythmia (ATA) after PV isolation (PVI) remains controversial. This study aimed to explore the function of common PV on the risk of recurrent ATA after PVI.

We identified a total of 191 patients who received radiofrequency catheter ablation for paroxysmal AF at our hospital between July 2010 and December 2017 for retrospective chart review. We collected the following data for analysis: results of preprocedural computed tomography, including the anatomy of PV and left atrial (LA) volume; the incidence of early- and late-onset recurrence of ATA. We compared these characteristics between the two groups defined by the presence or absence of the late-onset recurrence of ATA.

Compared to the no ATA recurrence group, the ATA recurrence group had larger LA size, larger LA end-diastolic and systolic volumes, larger maximal diameter of PV, higher prevalence of common PV, and higher incidence of early-onset recurrence of ATA. In multivariate logistic regression analyses, presence of common PV and early-onset recurrence were independently associated with late-onset recurrence of ATA. Compared to patients without common PV, patients with common PV had larger diameter of PV and higher incidence of late-onset recurrent ATA.

In patients with paroxysmal AF, early-onset recurrence of ATA and the presence of common PV were independently associated with late-onset recurrent ATA after radiofrequency catheter ablation.

Female sex has been linked with worse prognosis in patients with atrial fibrillation (AF). Clinical risk stratification of women with AF may help decision-making before catheter ablation (CA).

To evaluate arrhythmia outcomes and the predictive value of clinical scores for arrhythmia recurrence in a large cohort of Chinese patients with AF undergoing CA.

A total 1410 of patients (68.1% men) who underwent AF ablation with scheduled follow-up were analysed retrospectively. Baseline characteristics and ablation outcome were compared between men and women. The predictive values of risk scoring systems for AF recurrence were assessed in women.

Recurrence, early recurrence and complications after CA were similar in women and men over similar follow-up periods (20.7±8.0 vs 20.7±9.1 months; P>0.05). Compared with men, women with AF recurrence were older and had a larger left atrial diameter (LAD), less paroxysmal AF, lower left ventricular ejection fraction, lower estimated glomerular filtration rate (eGFR) and higher serum concentrations of B-type natriuretic peptide (BNP) and C-reactive protein (CRP) (all P<0.01). Multivariable analysis showed that age, non-paroxysmal AF, body mass index, coronary artery disease, LAD, early recurrence, eGFR, BNP and CRP were independent risk factors with sex differences (all P<0.05) in the whole cohort. In women, only non-paroxysmal AF, early recurrence, BNP, CRP (all P<0.01) and history of stroke/transient ischaemic attack (P=0.016) were independent risk factors. Of the clinical scoring systems tested, MB-LATER, APPLE, CAAP-AF and BASE-AF₂ scores (C-indexes 0.73, 0.72, 0.68 and 0.72, respectively; all P<0.01) had a modest predictive value for AF recurrence after CA in women.

CA for AF has similar recurrence risks in women and men, but there are sex differences in the clinical characteristics and risk factors associated with AF recurrence.

Atrial fibrillation (AF) is the most prevalent sustained cardiac arrhythmia in adults. Catheter ablation (CA) is one of the most important management strategies to reduce AF burden and AF-associated complications. In order to stratify the risk of adverse events and to predict treatment success in AF patients undergoing CA, several risk stratification scores had been developed during the last decade. The aim of this review is to provide an overview of the most important clinical risk scores predicting rhythm outcomes, electro-anatomical substrate and mortality in AF.