What is the clinical evidence from this study?

Study design: Cohort. Population: Atrioventricular nodal reentrant tachycardia (AVNRT) (n=94). Intervention: Machine-learning modeling (XGBoost classifier). Primary outcome: Classification of lesion outcome (Accuracy 82.3%, 95% CI 72.6-90.3).

What question did this study set out to answer?

Characterize the geometric distribution and lesion parameters of successful versus non-successful ablation sites in AVNRT using CARTONET data.

June 27, 2026EP EuropaceOpen Access

Modeling the optimal ablation site and lesion characteristics in AVNRT using the cloud-based CARTONET platform

View Full Paper

Ask AI

Bookmark

Key result

Machine learning classifies AVNRT ablation lesion outcomes with ~82% accuracy using geometric and biophysical inputs.

Accuracy 82.3%
95% CI 72.6-90.3
n=94

Why the study?

The optimal site and biophysical parameters for radiofrequency delivery in AVNRT catheter ablation remain poorly standardized.

What are the geometric and biophysical characteristics of successful versus non-successful ablation sites in AVNRT, and can they predict lesion outcome?

Population

94 consecutive AVNRT ablation procedures (310 ablation points) recorded in CARTONET

Comparison

Successful (slow junctional rhythm) vs non-successful (fast junctional rhythm or AV block) ablation sites

Design

Prospective observational cohort study

Authors

NMN M MignotInstitute Mutualiste Montsouris RBR B BourghoudInstitute Mutualiste Montsouris MMM M MiledInstitute Mutualiste Montsouris

Discussion

Member takes

Implication

May assist lesion outcome classification in EP; hypothesis-generating pending prospective validation.

Key Points

Characterize the geometric distribution and lesion parameters of successful versus non-successful ablation sites in AVNRT using CARTONET data.
Prospectively analyzed 94 AVNRT ablation procedures over a 10-year period using CARTONET.
Compared spatial position and biophysical metrics of SJR, FJR, and AV block relative to a His centroid.
Applied XGBoost machine-learning model to predict ablation outcomes based on geometric and biophysical inputs.
Mean distance from the His centroid was 18.3 mm for SJR, 17.9 mm for FJR, and 15.9 mm for AV block.
Successful lesions (SJR) showed higher mean power (40 W), greater impedance drop (~11Ω), and longer duration (28 s) compared to non-successful sites.
The machine-learning model classified lesion outcomes with 82.3% accuracy (95% CI 72.6–90.3).

Study Design

Type

Cohort (n=94)

Structured PICO

What are the geometric and biophysical characteristics of successful versus non-successful ablation sites in AVNRT, and can they predict lesion outcome?

Population

94 consecutive AVNRT ablation procedures (yielding 310 ablation points) recorded in CARTONET over a 10-year period.

Exposure

Successful ablation sites (defined as slow junctional rhythm [SJR])

Comparator

Non-successful ablation sites (defined as fast junctional rhythm [FJR] or AV block)

Outcome

Spatial position relative to the His cloud and biophysical metrics (impedance, power, temperature, duration, stability)surrogate

Main Result

Effect estimate: Accuracy 82.3% (95% CI 72.6-90.3)

Cloud-based spatial normalization and biophysical modeling can identify features of effective AVNRT ablation lesions and predict successful outcomes with over 80% accuracy.

Cite This Study

Mignot et al. (2026) conducted a cohort in Atrioventricular nodal reentrant tachycardia (AVNRT) (n=94). Machine-learning modeling (XGBoost classifier) was evaluated on Classification of lesion outcome (Accuracy 82.3%, 95% CI 72.6-90.3). A machine-learning model using geometric and biophysical inputs achieved an accuracy of 82.3% (95% CI 72.6-90.3) in classifying AVNRT ablation lesion outcomes.

synapsesocial.com/papers/6a3f97ce125782b61d8659ca https://doi.org/10.1093/europace/euag105.133

View Full Paper

Ask AI

Bookmark

Modeling the optimal ablation site and lesion characteristics in AVNRT using the cloud-based CARTONET platform

Discussion

Member takes

Implication

Key Points

Study Design

Structured PICO

Main Result

Cite This Study

Modeling the optimal ablation site and lesion characteristics in AVNRT using the cloud-based CARTONET platform

Discussion

Member takes

Implication

Key Points

Study Design

Structured PICO

Main Result

Cite This Study

Also Consider

Also Consider