DOI 10.1080/14796678.2026.2722829
Clinical applicability of artificial intelligence electrocardiogram interpretation in Brugada syndrome: a diagnostic accuracy meta-analysis.
Аннотация
INTRODUCTION
Artificial intelligence electrocardiogram (AI-ECG) interpretation has emerged as a promising approach to identify Brugada syndrome (BrS). This review sought to investigate diagnostic viability and clinical applicability of AI-ECG interpretation models for detecting BrS.
METHODS
A systematic search (PubMed, Scopus, and ScienceDirect) was conducted in November 2025. STATA/BE (v17.0) was used to pool the overall metrics of the quantitative diagnostic test accuracy meta-analysis.
RESULTS
Seven studies comprising 15 AI-model analyses were included. AI-ECG interpretation yielded a pooled sensitivity of 0.82 [0.77-0.87], specificity of 0.81 [0.73-0.87], negative likelihood ratio of 0.22 [0.16-0.29], positive likelihood ratio of 4.31 [2.94-6.33], and area under the curve of 0.88 [0.85-0.91]. Clinical applicability assessed using Fagan's nomogram showed minimal diagnostic value for general population screening (pretest probability 0.05%). However, in case-finding (5%) and high-risk scenarios (20%), positive results substantially increased posttest probability (to 18% and 52%, respectively), while negative results reduced it to 1% and 5%. Overall, the Fagan plot indicated a beneficial trend toward rule-in utility rather than rule-out utility.
CONCLUSION
AI-ECG interpretation demonstrated a good overall diagnostic performance for detecting BrS and may serve as valuable decision-support assisting clinicians in clinically suspected or high-risk populations.
PROTOCOL REGISTRATION: www.crd.york.ac.uk/prospero identifier is CRD420261298566.
Предметные рубрики MeSH
Подготовка и перевод публикации
Обработка статьи · этапы, ошибки и управление
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Тип публикации указан по данным источника. Уровень доказательности автоматически не присваивается.