Utility of a Cloud Based Lesion Data Collection Software to Record, Monitor, and Analyze an Ablation Strategy

Cardiovascular imaging techniques for electrophysiologists

Rapid technological advancements in noninvasive and invasive imaging including echocardiography, computed tomography, magnetic resonance imaging and positron emission tomography have allowed for improved anatomical visualization and precise measurement of cardiac structure and function. These imaging modalities allow for evaluation of how cardiac substrate changes, such as myocardial wall thickness, fibrosis, scarring and chamber enlargement and/or dilation, have an important role in arrhythmia initiation and perpetuation. Here, we review the various imaging techniques and modalities used by clinical and basic electrophysiologists to study cardiac arrhythmia mechanisms, periprocedural planning, risk stratification and precise delivery of ablation therapy. We also review the use of artificial intelligence and machine learning to improve identification of areas for triggered activity and isthmuses in reentrant arrhythmias, which may be favorable ablation targets.

Comparison of the characteristics between machine learning and deep learning algorithms for ablation site classification in a novel cloud-based system

BACKGROUND

CARTONET is a cloud-based system for the analysis of ablation procedures using the CARTO system. The current CARTONET R14 model employs deep learning, but its accuracy and positive predictive value (PPV) remain underevaluated.

OBJECTIVE

This study aimed to compare the characteristics of the CARTONET system between the R12.1 and the R14 models.

METHODS

Data from 396 atrial fibrillation ablation cases were analyzed. Using a CARTONET R14 model, the sensitivity and PPV of the automated anatomic location model were investigated. The distribution of potential reconnection sites and confidence level for each site were investigated. We also compared the difference in the data between the CARTONET R12.1, the previous CARTONET version, and the CARTONET R14 models.

RESULTS

We analyzed the overall tags of 39,169 points and the gap prediction of 625 segments using the CARTONET R14 model. The sensitivity and PPV of the R14 model significantly improved compared with the R12.1 model (R12.1 vs R14: sensitivity, 71.2% vs 77.5% [P < .0001]; PPV, 85.6% vs 86.2% [P = .0184]). The incidence of reconnections was highly observed in the posterior area of the right pulmonary veins (98/238 [41.2%]) and left pulmonary veins (190/387 [49.1%]). In contrast, the possibility of reconnection was highest in the roof area for the right pulmonary veins (14% [5.5%-41%]) and left pulmonary veins (16% [8%-22%]).

CONCLUSION

The R14 model significantly improved sensitivity and PPV compared with the R12.1 model. The tendency for predicting potential reconnection sites was similar to that of the previous version, the R12 model.

Validation of ablation site classification accuracy and trends in the prediction of potential reconnection sites for atrial fibrillation using the CARTONET® R12.1 model

Background

CARTONET® enables automatic ablation site classification and reconnection site prediction using machine learning. However, the accuracy of the site classification model and trends of the site prediction model for potential reconnection sites are uncertain.

Methods

We studied a total of 396 cases. About 313 patients underwent pulmonary vein isolation (PVI), including a cavotricuspid isthmus (CTI) ablation (PVI group) and 83 underwent PVI and additional ablation (i.e., box isolation) (PVI+ group). We investigated the sensitivity and positive predictive value (PPV) for automatic site classification in the total cohort and compared these metrics for PV lesions versus non-PV lesions. The distribution of potential reconnection sites and confidence level for each site was also investigated.

Results

A total of 29,422 points were analyzed (PV lesions [n = 22 418], non-PV lesions [n = 7004]). The sensitivity and PPV of the total cohort were 71.4% and 84.6%, respectively. The sensitivity and PPV of PV lesions were significantly higher than those of non-PV lesions (PV lesions vs. non-PV lesions, %; sensitivity, 75.3 vs. 67.5, p < .05; PPV, 91.2 vs. 67.9, p < .05). CTI and superior vena cava could not be recognized or analyzed. In the potential reconnection prediction model, the incidence of potential reconnections was highest in the posterior, while the confidence was the highest in the roof.

Conclusion

The automatic site classification of the CARTONET®R12.1 model demonstrates relatively high accuracy in pulmonary veins excluding the carina. The prediction of potential reconnection sites feature tends to anticipate areas with poor catheter stability as reconnection sites.

Consistency of ablations with trainee and increasing independence during fellowship training-Analysis of ablation data by CARTONET

INTRODUCTION

Training in clinical cardiac electrophysiology (CCEP) involves the development of catheter handling skills to safely deliver effective treatment. Objective data from analysis of ablation data for evaluating trainee of CCEP procedures has not previously been possible. Using the artificial intelligence cloud-based system (CARTONET), we assessed the impact of trainee progress through ablation procedural quality.

METHODS

Lesion- and procedure-level data from all de novo atrial fibrillation (AF) and cavotricuspid isthmus (CTI) ablations involving first-year (Y1) or second-year (Y2) fellows across a full year of fellowship was curated within Cartonet. Lesions were automatically assigned to anatomic locations.

RESULTS

Lesion characteristics, including contact force, catheter stability, impedance drop, ablation index value, and interlesion time/distance were similar over each training year. Anatomic location and supervising operator significantly affected catheter stability. The proportion of lesion sets delivered independently and of lesions delivered by the trainee increased steadily from the first quartile of Y1 to the last quartile of Y2. Trainee perception of difficult regions did not correspond to objective measures.

CONCLUSION

Objective ablation data from Cartonet showed that the progression of trainees through CCEP training does not impact lesion-level measures of treatment efficacy (i.e., catheter stability, impedance drop). Data demonstrates increasing independence over a training fellowship. Analyses like these could be useful to inform individualized training programs and to track trainee's progress. It may also be a useful quality assurance tool for ensuring ongoing consistency of treatment delivered within training institutions.

Does radiofrequency ablation procedural data improve the accuracy of identifying atrial fibrillation recurrence?

Radiofrequency ablation (RFA) using the CARTO 3D mapping system is a common approach for pulmonary vein isolation to treat atrial fibrillation (AF). Linkage between CARTO procedural data and patients' electronical health records (EHR) provides an opportunity to identify the ablation-related parameters that would predict AF recurrence. The objective of this study is to assess the incremental accuracy of RFA procedural data to predict post-ablation AF recurrence using machine learning model. Procedural data generated during RFA procedure were downloaded from CARTONET and linked to deidentified Mercy Health EHR data. Data were divided into train (70%) and test (30%) data for model development and validation. Automate machine learning (AutoML) was used to predict 1 year AF recurrence, defined as a composite of repeat ablation, electrical cardioversion, and AF hospitalization. At first, AutoML model only included Patients' demographic and clinical characteristics. Second, an AutoML model with procedural variables and demographical/clinical variables was developed. Area under receiver operating characteristic curve (AUROC) and net reclassification improvement (NRI) were used to compare model performances using test data. Among 306 patients, 67 (21.9%) patients experienced 1-year AF recurrence. AUROC increased from 0.66 to 0.78 after adding procedural data in the AutoML model based on test data. For patients with AF recurrence, NRI was 32% for model with procedural data. Nine of 10 important predictive features were CARTO procedural data. From CARTO procedural data, patients with lower contact force in right inferior site, long ablation duration, and low number of left inferior and right roof lesions had a higher risk of AF recurrence. Patients with persistent AF were more likely to have AF recurrence. The machine learning model with procedural data better predicted 1-year AF recurrence than the model without procedural data. The model could be used for identification of patients with high risk of AF recurrence post ablation.

Predictive utility of the impedance drop on AF recurrence using digital intraprocedural data linked to electronic health record data

Background

Local impedance drop in cardiac tissue during catheter ablation may be a valuable measure to guide atrial fibrillation (AF) ablation procedures for greater effectiveness.

Objective

The study sought to assess whether local impedance drop during catheter ablation to treat AF predicts 1-year AF recurrence and what threshold of impedance drop is most predictive.

Methods

We identified patients with AF undergoing catheter ablation in the Mercy healthcare system. We downloaded AF ablation procedural data recorded by the CARTO system from a cloud-based analytical tool (CARTONET) and linked them to individual patient electronic health records. Average impedance drops in anatomical region of right and left pulmonary veins were calculated. Effectiveness was measured by a composite outcome of repeat ablation, AF rehospitalization, direct current cardioversion, or initialization of a new antiarrhythmic drug post-blanking period. The association between impedance drop and 1-year AF recurrence was assessed by logistic regression adjusting for demographics, clinical, and ablation characteristics. Bootstrapping was used to determine the most predictive threshold for impedance drop based on the Youden index.

Results

Among 242 patients, 23.6% (n = 57) experienced 1-year AF recurrence. Patients in the lower third vs upper third of average impedance drop had a 5.9-fold (95% confidence interval [CI] 1.81-21.8) higher risk of recurrence (37.0% vs 12.5%). The threshold of 7.2 Ω (95% CI 5.75-7.7 Ω) impedance drop best predicted AF recurrence, with sensitivity of 0.73 and positive predictive value of 0.33. Patients with impedance drop ≤7.2 Ω had 3.5-fold (95% CI 1.39-9.50) higher risk of recurrence than patients with impedance drop >7.2 Ω, and there was no statistical difference in adverse events between the 2 groups of patients. Sensitivity analysis on right and left wide antral circumferential ablation impedance drop was consistent.

Conclusion

Average impedance drop is a strong predictor of clinical success in reducing AF recurrence but as a single criterion for predicting recurrence only reached 73% sensitivity and 33% positive predictive value.