European heart journal
-
European heart journal · Jul 2019
ReviewDeep learning for cardiovascular medicine: a practical primer.
Deep learning (DL) is a branch of machine learning (ML) showing increasing promise in medicine, to assist in data classification, novel disease phenotyping and complex decision making. Deep learning is a form of ML typically implemented via multi-layered neural networks. Deep learning has accelerated by recent advances in computer hardware and algorithms and is increasingly applied in e-commerce, finance, and voice and image recognition to learn and classify complex datasets. ⋯ However, DL also has significant weaknesses including difficulties in interpreting its models (the 'black-box' criticism), its need for extensive adjudicated ('labelled') data in training, lack of standardization in design, lack of data-efficiency in training, limited applicability to clinical trials, and other factors. Thus, the optimal clinical application of DL requires careful formulation of solvable problems, selection of most appropriate DL algorithms and data, and balanced interpretation of results. This review synthesizes the current state of DL for cardiovascular clinicians and investigators, and provides technical context to appreciate the promise, pitfalls, near-term challenges, and opportunities for this exciting new area.
-
European heart journal · Jun 2019
Multicenter Study Clinical TrialIntegration of transthoracic focused cardiac ultrasound in the diagnostic algorithm for suspected acute aortic syndromes.
The diagnosis of acute aortic syndromes (AASs) is challenging and requires integrated strategies. Transthoracic focused cardiac ultrasound (FoCUS) is endorsed by guidelines as a first-line/triage tool allowing rapid bedside assessment of the aorta. However, the performance of FoCUS in the European Society of Cardiology-recommended workup of AASs awaits validation. ⋯ FoCUS has additive value in the workup of AASs. Direct FoCUS signs can rapidly identify patients requiring advanced imaging despite low clinical probability. In integrated bundles, negative FoCUS is useful for rule-out of AASs.
-
European heart journal · Jun 2019
Randomized Controlled Trial Multicenter StudyPlatelet reactivity and clinical outcomes in acute coronary syndrome patients treated with prasugrel and clopidogrel: a pre-specified exploratory analysis from the TROPICAL-ACS trial.
The value of platelet function testing (PFT) in predicting clinical outcomes and guiding P2Y12-inhibitor treatment is uncertain. In a pre-specified sub-study of the TROPICAL-ACS trial, we assessed ischaemic and bleeding risks according to high platelet reactivity (HPR) and low platelet reactivity (LPR) to ADP in patients receiving uniform prasugrel vs. PFT-guided clopidogrel or prasugrel. ⋯ Based on this substudy of a randomized trial, selecting prasugrel or clopidogrel based on PFT resulted in similar ischaemic outcomes as uniform prasugrel therapy without HPR. Although infrequent, HPR on prasugrel was associated with increased risk of ischaemic events. Low platelet reactivity was a strong and independent predictor of bleeding both on prasugrel and clopidogrel.
-
European heart journal · May 2019
Meta AnalysisEfficacy and safety of reduced-dose non-vitamin K antagonist oral anticoagulants in patients with atrial fibrillation: a meta-analysis of randomized controlled trials.
Non-vitamin K antagonist oral anticoagulants (NOACs) require dose reductions according to patient or clinical factors for patients with atrial fibrillation (AF). In this meta-analysis, we aimed to assess outcomes with reduced-dose NOACs when given as pre-specified in pivotal trials. ⋯ Patients eligible for reduced-dose NOACs were at elevated risk of thromboembolic and haemorrhagic complications when treated with anticoagulants. NOACs, when appropriately dose-adjusted, had an improved benefit-harm profile compared with warfarin. Our findings highlight the importance of prescribing reduced-dose NOACs for indicated patient populations.