Computed tomography-derived left atrial volume index, sex, and age to predict the presence and the extent of left atrial low-voltage zones in patients with atrial fibrillation: The ZAQ score

An artificial intelligence-enabled electrocardiogram algorithm for the prediction of left atrial low-voltage areas in persistent atrial fibrillation

OBJECTIVES

We aimed to construct an artificial intelligence-enabled electrocardiogram (ECG) algorithm that can accurately predict the presence of left atrial low-voltage areas (LVAs) in patients with persistent atrial fibrillation.

METHODS

The study included 587 patients with persistent atrial fibrillation who underwent catheter ablation procedures between March 2012 and December 2023 and 942 scanned images of 12-lead ECGs obtained before the ablation procedures were performed. Artificial intelligence-based algorithms were used to construct models for predicting the presence of LVAs. The DR-FLASH and APPLE clinical scores for LVA prediction were calculated. We used a receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis to evaluate model performance.

RESULTS

The data obtained from the participants were split into training (n = 469), validation (n = 58), and test sets (n = 60). LVAs were detected in 53.7% of all participants. Using ECG alone, the deep learning algorithm achieved an area under the ROC curve (AUROC) of 0.752, outperforming both the DR-FLASH score (AUROC = 0.610) and the APPLE score (AUROC = 0.510). The random forest classification model, which integrated a probabilistic deep learning model and clinical features, showed a maximum AUROC of 0.759. Moreover, the ECG-based deep learning algorithm for predicting extensive LVAs achieved an AUROC of 0.775, with a sensitivity of 0.816 and a specificity of 0.896. The random forest classification model for predicting extensive LVAs achieved an AUROC of 0.897, with a sensitivity of 0.862, and a specificity of 0.935.

CONCLUSION

The deep learning model based exclusively on ECG data and the machine learning model that combined a probabilistic deep learning model and clinical features both predicted the presence of LVAs with a higher degree of accuracy than the DR-FLASH and the APPLE risk scores.

Left Atrium Volume Measured with Multislice Computed Tomography as a Prognostic Predictor for Atrial Fibrillation Catheter Ablation Outcomes

Background: Current guidelines consider atrial fibrillation (AF) type as the prognostic factor for a recommendation of catheter ablation. We aimed to determine whether LA and LA appendage (LAA) volumes measured using multislice computed tomography (MSCT) were related to long-term outcomes in AF following radiofrequency catheter ablation (RFCA). Methods: We evaluated 152 consecutive patients with drug-refractory AF (median age, 55.8 ± 9.6 years), including 110 male patients, who underwent RFCA in a single center. All patients underwent MSCT imaging for anatomical assessment. The endpoint of this study was documented AF recurrence after RFCA. Results: The overall procedure success rate was 77.6% (n = 118) during a mean follow-up period of 12.6 months. The LA volume was significantly larger for those who experienced AF recurrence after RFCA than for the patients without recurrent AF after the procedure (153.8 ± 29.9 mL vs. 139.2 ± 34.1 mL, p = 0.025). However, LAA volumes were nearly equivalent between the patients with and without AF recurrence after RFCA (16.2 ± 6.3 mL and 14.7 ± 6.5 mL, respectively; p = 0.235). LA volume ≥ 153.2 mL was the optimal cutoff value for estimating AF recurrence after RFCA, with 94% sensitivity and 66% specificity. LA volume remained an independent predictor of both AF recurrence and permanent AF. Conclusions: LA volume as assessed by MSCT might be helpful for identifying patients likely to achieve successful AF ablation. LA volume ≥ 153.2 mL, but not LAA volume, showed good accuracy in predicting AF recurrence after RFCA.

Including hemoglobin levels and female sex provide the additional predictive value of the APPLE score for atrial fibrillation recurrence post-catheter ablation

OBJECTIVE

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

METHODS

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.

RESULTS

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.

CONCLUSION

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.

Using machine learning to enhance prediction of atrial fibrillation recurrence after catheter ablation

Background

Traditional risk scores for recurrent atrial fibrillation (AF) following catheter ablation utilize readily available clinical and echocardiographic variables and yet have limited discriminatory capacity. Use of data from cardiac imaging and deep learning may help improve accuracy and prediction of recurrent AF after ablation.

Methods

We evaluated patients with symptomatic, drug-refractory AF undergoing catheter ablation. All patients underwent pre-ablation cardiac computed tomography (cCT). LAVi was computed using a deep-learning algorithm. In a two-step analysis, random survival forest (RSF) was used to generate prognostic models with variables of highest importance, followed by Cox proportional hazard regression analysis of the selected variables. Events of interest included early and late recurrence.

Results

Among 653 patients undergoing AF ablation, the most important factors associated with late recurrence by RSF analysis at 24 (+/-18) months follow-up included LAVi and early recurrence. In total, 5 covariates were identified as independent predictors of late recurrence: LAVi (HR per mL/m2 1.01 [1.01-1.02]; p < .001), early recurrence (HR 2.42 [1.90-3.09]; p < .001), statin use (HR 1.38 [1.09-1.75]; p = .007), beta-blocker use (HR 1.29 [1.01-1.65]; p = .043), and adjunctive cavotricuspid isthmus ablation [HR 0.74 (0.57-0.96); p = .02]. Survival analysis demonstrated that patients with both LAVi >66.7 mL/m2 and early recurrence had the highest risk of late recurrence risk compared with those with LAVi <66.7 mL/m2 and no early recurrence (HR 4.52 [3.36-6.08], p < .001).

Conclusions

Machine learning-derived, full volumetric LAVi from cCT is the most important pre-procedural risk factor for late AF recurrence following catheter ablation. The combination of increased LAVi and early recurrence confers more than a four-fold increased risk of late recurrence.

Role of advanced imaging with cardiac computed tomography and MRI in atrial and ventricular ablation

PURPOSE OF REVIEW

Increasing evidence supports the use of advanced imaging with cardiac computed tomography (CCT) and cardiac magnetic resonance (CMR) in the work-up of patients with arrythmias being considered for ablation.

RECENT FINDINGS

Advances in imaging technology and postprocessing are facilitating the use of advanced imaging before, during and after ablation in patients with both atrial and ventricular arrhythmias.In atrial arrythmias, quantitative assessment of left atrial wall thickness on CCT and quantification of late gadolinium enhancement (LGE) on CMR identify patients more likely to develop recurrent atrial arrythmias following ablation. In addition, in patients with recurrent arrythmia post ablation, LGE CMR can potentially identify targets for repeat ablation.In ventricular arrythmias, qualitative assessment of LGE can aide in determining the optimal ablation approach and predicts likelihood of ventricular arrythmias inducibility. Quantitative assessment of LGE can identify conduction channels that can be targeted for ablation. On CCT, quantitative assessment of left ventricular wall thickness can demonstrate myocardial ridges associated with re-entrant circuits for ablation.

SUMMARY

This review focuses on the utility of CCT and CMR in identifying key anatomical components and arrhythmogenic substrate contributing to both atrial and ventricular arrhythmias in patients being considered for ablation. Advanced imaging has the potential to improve procedural outcomes, decrease complications and shorten procedural time.

Early diagnosis and better rhythm management to improve outcomes in patients with atrial fibrillation: the 8th AFNET/EHRA consensus conference

Despite marked progress in the management of atrial fibrillation (AF), detecting AF remains difficult and AF-related complications cause unacceptable morbidity and mortality even on optimal current therapy. This document summarizes the key outcomes of the 8th AFNET/EHRA Consensus Conference of the Atrial Fibrillation NETwork (AFNET) and the European Heart Rhythm Association (EHRA). Eighty-three international experts met in Hamburg for 2 days in October 2021. Results of the interdisciplinary, hybrid discussions in breakout groups and the plenary based on recently published and unpublished observations are summarized in this consensus paper to support improved care for patients with AF by guiding prevention, individualized management, and research strategies. The main outcomes are (i) new evidence supports a simple, scalable, and pragmatic population-based AF screening pathway; (ii) rhythm management is evolving from therapy aimed at improving symptoms to an integrated domain in the prevention of AF-related outcomes, especially in patients with recently diagnosed AF; (iii) improved characterization of atrial cardiomyopathy may help to identify patients in need for therapy; (iv) standardized assessment of cognitive function in patients with AF could lead to improvement in patient outcomes; and (v) artificial intelligence (AI) can support all of the above aims, but requires advanced interdisciplinary knowledge and collaboration as well as a better medico-legal framework. Implementation of new evidence-based approaches to AF screening and rhythm management can improve outcomes in patients with AF. Additional benefits are possible with further efforts to identify and target atrial cardiomyopathy and cognitive impairment, which can be facilitated by AI.

Extensive Left Atrial Low-Voltage Area During Initial Ablation is Associated with A Poor Clinical Outcome Even Following Multiple Procedures

Background

Some patients fail to respond to persistent atrial fibrillation (PeAF) catheter ablation in spite of multiple procedures and ablation strategies, including low voltage area (LVA)-guided, linear, and complex fractionated atrial electrogram (CFAE)-guided ablation procedures. We hypothesized that LVA extent could predict non-responseto Pe AF catheter ablation in spite of multiple procedures.

Methods

This study included 510 patients undergoing initial ablation procedures for PeAF. LVAs were defined as regions with bipolar peak-to-peak voltages of <0.50 mV after PVI during sinus rhythm. Patients were categorized by LVA size into groups A(0-5 cm²), B (5-20 cm²), and C (over 20 cm²). The primary endpoint was AF-free survival after the last procedure.

Results

During a median follow-up of 25 (17, 36) months, AF recurrence was observed in 101 (20%) patients after 1.4±0.6 ablation procedures (maximum 4). Comparison of clinical outcomes after multiple procedures in the three groups showed that the results depended on the extent of LVA. Multivariate analysis of AF-free survival after the last procedure showed that LVAs > 20 cm2 was an independent factor associated with AF recurrence after the final procedure(Hazard ratio, 7.94; 95% confidence interval, 2.91 to 21.67, P <0.001).

Conclusions

Extensive LVA after initial PVI was associated with poor clinical benefit despite multiple catheter based ablations.

Cardiac Computed Tomography-Derived Left Atrial Volume Index as a Predictor of Long-Term Success of Cryo-Ablation in Patients With Atrial Fibrillation

Patients with symptomatic, drug-refractory atrial fibrillation (AF) are frequently treated with catheter ablation. Cryo-ablation has been established as an alternative to radiofrequency ablation but long-term outcome data are still limited. This study aimed at elucidating the influence of the left atrial volume index (LAVI), derived from cardiac computed tomography (cCT) data, on the long-term outcome of ablation-naïve AF patients, after their first cryo-ablation. 415 patients (n = 290 [69.90%] male, 60.00 [IQR: 53.00 to 68.00] years old) who underwent a cCT and subsequent cryo-ablation index procedure were included in this single centre retrospective data analysis. A composite end point was defined (AF on electrocardiogram and/or electric cardioversion and/or re-do). Patients were closely followed for a year and then contacted for long-term follow-up after a median of 53.00 months (IQR: 34.50 to 73.00). Statistical analyses of the outcome and predictors of AF recurrence were conducted. In 224 patients (53.98%) no evidence of AF recurrence could be found. LAVI differed significantly between the positive and adverse (AF recurrence) outcome group (49.96 vs 56.07 ml/m², p < 0.001). Cox regression analyses revealed cCT LAVI (HR: 1.022, 95% CI: 1.013 to 1.031, p < 0.001), BMI (HR: 1.044, 95% CI: 1.005 to 1.084, p < 0.05) and the type of AF (HR: 1.838 for nonparoxysmal AF, 95% CI: 1.214 to 2.781, p < 0.01) to be effective predictors of AF recurrence. A prognostic cCT LAVI cut-off value of 51.99 ml/m² was calculated and must be validated in future prospective studies. In conclusion, LAVI is an accurate, yet underutilized predictor of AF recurrence after pulmonary vein isolation with cryo-energy and scores for calculating AF recurrence or progression risks might underemphasize the importance of CT-derived LAVI as a predictive factor.

The coronary artery calcium score correlates with left atrial low-voltage area: Sex differences

INTRODUCTION

In patients with coronary artery disease, a high coronary artery calcium score (CACS) correlates with atrial fibrillation (AF); however, the association between left atrial (LA) remodeling progression and coronary arteriosclerosis is unclear. This study aimed to evaluate the relationship between LA remodeling progression and the CACS.

METHODS

This retrospective study enrolled 148 patients with AF (paroxysmal AF, n = 94) who underwent catheter ablation. Voltage mapping for the left atrium and coronary computed tomography for CACS calculations were performed. The ratio of the LA low-voltage area (LA-LVA), defined by values less than 0.5 mV divided by the total LA surface without pulmonary veins, was calculated. Patients with LA-LVA (<0.5 mV) >5% and ≤5% were classified as the LVA (n = 30) and non-LVA (n = 118) groups, respectively. Patient characteristics and CACS values were compared between the two groups.

RESULTS

LA volume, age, CHA₂ DS₂ VASc score, and percentage of female patients were significantly higher, and the estimated glomerular filtration rate was lower in the LVA group than in the non-LVA group. The CACS was significantly higher in the LVA group (248.4 vs. 13.2; p = .001). Multivariate analysis identified the LA volume index and CACS as independent predictors of LA-LVA (<0.5 mV) greater than 5%. The areas under the receiver operating characteristic curves for predicting LA-LVA (<0.5 mV) greater than 5% with CACS were 0.695 in the entire population, 0.782 in men, and 0.587 in women.

CONCLUSION

Progression of LA remodeling and coronary artery calcification may occur in parallel. A high CACS may indicate advanced LA remodeling, especially in men.