European Heart Journal

doi: 10.1093/eurheartj/ehae596pmid: 39222018

Background and AimsThe optimal antithrombotic therapy in patients with device-detected atrial fibrillation (DDAF) is unknown. Concomitant vascular disease can modify the benefits and risks of anticoagulation.MethodsThese pre-specified analyses of the NOAH-AFNET 6 (n = 2534 patients) and ARTESiA (n = 4012 patients) trials compared anticoagulation with no anticoagulation in patients with DDAF with or without vascular disease, defined as prior stroke/transient ischaemic attack, coronary or peripheral artery disease. Efficacy outcomes were the primary outcomes of both trials, a composite of stroke, systemic arterial embolism (SE), myocardial infarction, pulmonary embolism or cardiovascular death, and stroke or SE. Safety outcomes were major bleeding or major bleeding and death.ResultsIn patients with vascular disease (NOAH-AFNET 6, 56%; ARTESiA, 46%), stroke, myocardial infarction, systemic or pulmonary embolism, or cardiovascular death occurred at 3.9%/patient-year with and 5.0%/patient-year without anticoagulation (NOAH-AFNET 6), and 3.2%/patient-year with and 4.4%/patient-year without anticoagulation (ARTESiA). Without vascular disease, outcomes were equal with and without anticoagulation (NOAH-AFNET 6, 2.7%/patient-year; ARTESiA, 2.3%/patient-year in both randomized groups). Meta-analysis found consistent results across both trials (I2heterogeneity = 6%) with a trend for interaction with randomized therapy (pinteraction = .08). Stroke/SE behaved similarly. Anticoagulation equally increased major bleeding in vascular disease patients [edoxaban, 2.1%/patient-year; no anticoagulation, 1.3%/patient-year; apixaban, 1.7%/patient-years; no anticoagulation, 1.1%/patient-year; incidence rate ratio 1.55 (1.10–2.20)] and without vascular disease [edoxaban, 2.2%/patient-year; no anticoagulation, 0.6%/patient-year; apixaban, 1.4%/patient-year; no anticoagulation, 1.1%/patient-year; incidence rate ratio 1.93 (0.72–5.20)].ConclusionsPatients with DDAF and vascular disease are at higher risk of stroke and cardiovascular events and may derive a greater benefit from anticoagulation than patients with DDAF without vascular disease.

doi: 10.1093/eurheartj/ehae595pmid: 39217446

Background and AimsDeep learning applied to electrocardiograms (ECG-AI) is an emerging approach for predicting atrial fibrillation or flutter (AF). This study introduces an ECG-AI model developed and tested at a tertiary cardiac centre, comparing its performance with clinical models and AF polygenic score (PGS).MethodsElectrocardiograms in sinus rhythm from the Montreal Heart Institute were analysed, excluding those from patients with pre-existing AF. The primary outcome was incident AF at 5 years. An ECG-AI model was developed by splitting patients into non-overlapping data sets: 70% for training, 10% for validation, and 20% for testing. The performance of ECG-AI, clinical models, and PGS was assessed in the test data set. The ECG-AI model was externally validated in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) hospital data set.ResultsA total of 669 782 ECGs from 145 323 patients were included. Mean age was 61 ± 15 years, and 58% were male. The primary outcome was observed in 15% of patients, and the ECG-AI model showed an area under the receiver operating characteristic (AUC-ROC) curve of .78. In time-to-event analysis including the first ECG, ECG-AI inference of high risk identified 26% of the population with a 4.3-fold increased risk of incident AF (95% confidence interval: 4.02–4.57). In a subgroup analysis of 2301 patients, ECG-AI outperformed CHARGE-AF (AUC-ROC = .62) and PGS (AUC-ROC = .59). Adding PGS and CHARGE-AF to ECG-AI improved goodness of fit (likelihood ratio test P < .001), with minimal changes to the AUC-ROC (.76–.77). In the external validation cohort (mean age 59 ± 18 years, 47% male, median follow-up 1.1 year), ECG-AI model performance remained consistent (AUC-ROC = .77).ConclusionsECG-AI provides an accurate tool to predict new-onset AF in a tertiary cardiac centre, surpassing clinical and PGS.