Dataset Information

Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation.

ABSTRACT: Identifying patients who would benefit from extensive catheter ablation along with pulmonary vein isolation (PVI) among those with persistent atrial fibrillation (AF) has been a subject of controversy. The objective of this study was to apply uplift modeling, a machine learning method for analyzing individual causal effect, to identify such patients in the EARNEST-PVI trial, a randomized trial in patients with persistent AF. We developed 16 uplift models using different machine learning algorithms, and determined that the best performing model was adaptive boosting using Qini coefficients. The optimal uplift score threshold was 0.0124. Among patients with an uplift score ≥ 0.0124, those who underwent extensive catheter ablation (PVI-plus) showed a significantly lower recurrence rate of AF compared to those who received only PVI (PVI-alone) (HR 0.40; 95% CI 0.19-0.84; P-value = 0.015). In contrast, among patients with an uplift score < 0.0124, recurrence of AF did not significantly differ between PVI-plus and PVI-alone (HR 1.17; 95% CI 0.57-2.39; P-value = 0.661). By employing uplift modeling, we could effectively identify a subset of patients with persistent AF who would benefit from PVI-plus. This model could be valuable in stratifying patients with persistent AF who need extensive catheter ablation before the procedure.

SUBMITTER: Sato T

PROVIDER: S-EPMC10834528 | biostudies-literature | 2024 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation.

Sato Taiki T Sotomi Yohei Y Hikoso Shungo S Kitamura Tetsuhisa T Nakatani Daisaku D Okada Katsuki K Dohi Tomoharu T Sunaga Akihiro A Kida Hirota H Matsuoka Yuki Y Tanaka Nobuaki N Watanabe Tetsuya T Makino Nobuhiko N Egami Yasuyuki Y Oka Takafumi T Minamiguchi Hitoshi H Miyoshi Miwa M Okada Masato M Kanda Takashi T Matsuda Yasuhiro Y Kawasaki Masato M Masuda Masaharu M Inoue Koichi K Sakata Yasushi Y

Scientific reports 20240201 1

Identifying patients who would benefit from extensive catheter ablation along with pulmonary vein isolation (PVI) among those with persistent atrial fibrillation (AF) has been a subject of controversy. The objective of this study was to apply uplift modeling, a machine learning method for analyzing individual causal effect, to identify such patients in the EARNEST-PVI trial, a randomized trial in patients with persistent AF. We developed 16 uplift models using different machine learning algorith ...[more]

PMID: 38302547

Similar Datasets

Project description:Background Modification of arrhythmogenic substrates with extensive ablation comprising linear and/or complex fractional atrial electrogram ablation in addition to pulmonary vein isolation (PVI-plus) can theoretically reduce the recurrence of atrial fibrillation. The DR-FLASH score (score based on diabetes mellitus, renal dysfunction, persistent form of atrial fibrillation, left atrialdiameter >45 mm, age >65 years, female sex, and hypertension) is reportedly useful for identifying patients with arrhythmogenic substrates. We hypothesized that, in patients with persistent atrial fibrillation, the DR-FLASH score can be used to classify patients into those who require PVI-plus and those for whom a PVI-only strategy is sufficient. Methods and Results This study is a post hoc subanalysis of the a multicenter, randomized controlled, noninferiority trial investigating efficacy and safety of pulmonary vein isolation alone for recurrence prevention compared with extensive ablation in patients with persistent atrial fibrillation (EARNEST-PVI trial). This analysis focuses on the relationship between DR-FLASH score and the efficacy of different ablation strategies. We divided the population into 2 groups based on a DR-FLASH score of 3 points. A total of 469 patients were analyzed. Among those with a DR-FLASH score >3 (N=279), the event rate of atrial arrhythmia recurrence was significantly lower in the PVI-plus arm than in the PVI-only arm (hazard ratio [HR], 0.45 [95% CI, 0.28-0.72]; P<0.001). In contrast, among patients with a DR-FLASH score ≤3 (N=217), no differences were observed in the event rate of atrial arrhythmia recurrence between the PVI-only arm and the PVI-plus arm (HR, 1.08 [95% CI, 0.61-1.89]; P=0.795). There was significant interaction between patients with a DR-FLASH score >3 and DR-FLASH score ≤3 (P value for interaction=0.020). Conclusions The DR-FLASH score is a useful tool for deciding the catheter ablation strategy for patients with persistent atrial fibrillation. Registration URL: https://clinicaltrials.gov; Unique identifier: NCT03514693.

Dataset Information

Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation.

Publications

Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets