Identification of patients with atrial fibrillation: a big data exploratory analysis of the UK Biobank

• Published in: Physiological measurement Vol. 41; no. 2; pp. 25001 - 25011
• Main Authors: Oster, Julien, Hopewell, Jemma C, Ziberna, Klemen, Wijesurendra, Rohan, Camm, Christian F, Casadei, Barbara, Tarassenko, Lionel
• Format: Journal Article
• Language: English
• Published: England IOP Publishing 06.03.2020
• Subjects: atrial fibrillation; Atrial Fibrillation - diagnosis; Big Data; biobank; Bioengineering; Biological Specimen Banks; Computer Science; electrocardiogram; Electrocardiography; Human health and pathology; Humans; Life Sciences; machine learning; Medical Imaging; Medical Informatics - methods; Nuclear medicine; signal processing; Signal Processing, Computer-Assisted; Support Vector Machine; United Kingdom; United Kingdom
• ISSN: 0967-3334; 1361-6579; 1361-6579
• DOI: 10.1088/1361-6579/ab6f9a

Objective: Atrial fibrillation (AF) is the most common cardiac arrhythmia, with an estimated prevalence of around 1.6% in the adult population. The analysis of the electrocardiogram (ECG) data acquired in the UK Biobank represents an opportunity to screen for AF in a large sub-population in the UK. The main objective of this paper is to assess ten machine-learning methods for automated detection of subjects with AF in the UK Biobank dataset. Approach: Six classical machine-learning methods based on support vector machines are proposed and compared with state-of-the-art techniques (including a deep-learning algorithm), and finally a combination of a classical machine-learning and deep learning approaches. Evaluation is carried out on a subset of the UK Biobank dataset, manually annotated by human experts. Main results: The combined classical machine-learning and deep learning method achieved an F1 score of 84.8% on the test subset, and a Cohen's kappa coefficient of 0.83, which is similar to the inter-observer agreement of two human experts. Significance: The level of performance indicates that the automated detection of AF in patients whose data have been stored in a large database, such as the UK Biobank, is possible. Such automated identification of AF patients would enable further investigations aimed at identifying the different phenotypes associated with AF.