A Scoping Review of the Use of Artificial Intelligence in the Identification and Diagnosis of Atrial Fibrillation
Open Access
- 24 October 2024
- journal article
- review article
- Published by MDPI AG in Journal of Personalized Medicine
- Vol. 14 (11) , 1069
Abstract
Background/Objective: Atrial fibrillation [AF] is the most common arrhythmia encountered in clinical practice and significantly increases the risk of stroke, peripheral embolism, and mortality. With the rapid advancement in artificial intelligence [AI] technologies, there is growing potential to enhance the tools used in AF detection and diagnosis. This scoping review aimed to synthesize the current knowledge on the application of AI, particularly machine learning [ML], in identifying and diagnosing AF in clinical settings. Methods: Following the PRISMA ScR guidelines, a comprehensive search was conducted using the MEDLINE, PubMed, SCOPUS, and EMBASE databases, targeting studies involving AI, cardiology, and diagnostic tools. Precisely 2635 articles were initially identified. After duplicate removal and detailed evaluation of titles, abstracts, and full texts, 30 studies were selected for review. Additional relevant studies were included to enrich the analysis. Results: AI models, especially ML-based models, are increasingly used to optimize AF diagnosis. Deep learning, a subset of ML, has demonstrated superior performance by automatically extracting features from large datasets without manual intervention. Self-learning algorithms have been trained using diverse data, such as signals from 12-lead and single-lead electrocardiograms, and photoplethysmography, providing accurate AF detection across various modalities. Conclusions: AI-based models, particularly those utilizing deep learning, offer faster and more accurate diagnostic capabilities than traditional methods with equal or superior reliability. Ongoing research is further enhancing these algorithms using larger datasets to improve AF detection and management in clinical practice. These advancements hold promise for significantly improving the early diagnosis and treatment of AF.Keywords
This publication has 53 references indexed in Scilit:
- An intelligent computer-aided diagnosis method for paroxysmal atrial fibrillation patients with nondiagnostic ECG signalsBiomedical Signal Processing and Control, 2023
- Machine Learning-Based Prediction of Atrial Fibrillation Risk Using Electronic Medical Records in Older Aged PatientsThe American Journal of Cardiology, 2023
- Diagnosis of atrial fibrillation using self-complementary attentional convolutional neural networkComputer Methods and Programs in Biomedicine, 2023
- Artificial intelligence for the detection, prediction, and management of atrial fibrillationHerzschrittmachertherapie + Elektrophysiologie, 2022
- A new smart wristband equipped with an artificial intelligence algorithm to detect atrial fibrillationHeart Rhythm, 2020
- An incremental learning system for atrial fibrillation detection based on transfer learning and active learningComputer Methods and Programs in Biomedicine, 2020
- Rationale and design of a large-scale, app-based study to identify cardiac arrhythmias using a smartwatch: The Apple Heart StudyAmerican Heart Journal, 2019
- A Validation Study of Automated Atrial Fibrillation Detection Using Alerte Digital Health's Artificial Intelligence SystemHeart, Lung and Circulation, 2017
- Reversal of Cardiogenic Shock After Bilateral Renal Artery StentingCanadian Journal of Cardiology, 2013
- Independent Risk Factors for Atrial Fibrillation in a Population-Based CohortJAMA, 1994