학술논문
Uplift modeling to identify patients who require extensive catheter ablation procedures among patients with persistent atrial fibrillation
Document Type
article
Author
Taiki Sato; Yohei Sotomi; Shungo Hikoso; Tetsuhisa Kitamura; Daisaku Nakatani; Katsuki Okada; Tomoharu Dohi; Akihiro Sunaga; Hirota Kida; Yuki Matsuoka; Nobuaki Tanaka; Tetsuya Watanabe; Nobuhiko Makino; Yasuyuki Egami; Takafumi Oka; Hitoshi Minamiguchi; Miwa Miyoshi; Masato Okada; Takashi Kanda; Yasuhiro Matsuda; Masato Kawasaki; Masaharu Masuda; Koichi Inoue; Yasushi Sakata; the OCVC-Arrhythmia Investigators
Source
Scientific Reports, Vol 14, Iss 1, Pp 1-13 (2024)
Subject
Language
English
ISSN
2045-2322
Abstract
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