A5055242814- ECG Monitoring and Analysis
- Cardiac electrophysiology and arrhythmias
- Cardiac Arrhythmias and Treatments
- Atrial Fibrillation Management and Outcomes
- Cardiovascular Function and Risk Factors
- Heart Rate Variability and Autonomic Control
- Cardiomyopathy and Myosin Studies
- Cardiovascular Disease and Adiposity
- Blood Pressure and Hypertension Studies
- Cardiac Imaging and Diagnostics
- Cardiovascular Syncope and Autonomic Disorders
- Cardiovascular Effects of Exercise
- Artificial Intelligence in Healthcare
- Machine Learning in Healthcare
- Cardiovascular Health and Risk Factors
- Health, Environment, Cognitive Aging
- Cardiac pacing and defibrillation studies
- Neurological disorders and treatments
- EEG and Brain-Computer Interfaces
- Functional Brain Connectivity Studies
- Medical Image Segmentation Techniques
- Parkinson's Disease Mechanisms and Treatments
- Explainable Artificial Intelligence (XAI)
- Health Systems, Economic Evaluations, Quality of Life
- Computational Drug Discovery Methods
Imperial College London
2014-2025
Imperial College Healthcare NHS Trust
2017-2025
Lung Institute
2013-2025
Hammersmith Hospital
2022-2024
National Health Service
2024
NIHR Imperial Biomedical Research Centre
2022
National Institute for Health Research
2022
Royal Brompton Hospital
2015
Imperial Valley College
2014
Importance Hypertension underpins significant global morbidity and mortality. Early lifestyle intervention treatment are effective in reducing adverse outcomes. Artificial intelligence–enhanced electrocardiography (AI-ECG) has been shown to identify a broad spectrum of subclinical disease may be useful for predicting incident hypertension. Objective To develop an AI-ECG risk estimator (AIRE) predict hypertension (AIRE-HTN) stratify hypertension-associated Design, Setting, Participants This...
Abstract The electrocardiogram (ECG) can capture obesity-related cardiac changes. Artificial intelligence-enhanced ECG (AI-ECG) identify subclinical disease. We trained an AI-ECG model to predict body mass index (BMI) from the alone. Developed 512,950 12-lead ECGs Beth Israel Deaconess Medical Center (BIDMC), a secondary care cohort, and validated on UK Biobank (UKB) ( n = 42,386), achieved Pearson correlation coefficient (r) of 0.65 0.62, R 2 0.43 0.39 in BIDMC cohort Biobank, respectively...
Catheter ablation of Atrial Fibrillation (AF) consists a one-size-fits-all treatment with limited success in persistent AF. This may be due to our inability map the dynamics AF resolution and coverage provided by sequential contact mapping catheters, preventing effective patient phenotyping for personalised, targeted ablation. Here we introduce FibMap, graph recurrent neural network model that reconstructs global from sparse measurements. Trained validated on 51 non-contact whole atria...
Abstract Aims Many research databases with anonymised patient data contain electrocardiograms (ECGs) from which traditional identifiers have been removed. We evaluated the ability of artificial intelligence (AI) methods to determine similarity between ECGs and assessed whether they potential be misused re-identify individuals datasets. Methods results utilised a convolutional Siamese neural network (SNN) architecture, derives Euclidean distance metric two input ECGs. A secondary care dataset...
There is increasing focus on applying deep learning methods to electrocardiograms (ECGs), with recent studies showing that neural networks (NNs) can predict future heart failure or atrial fibrillation from the ECG alone. However, large numbers of ECGs are needed train NNs, and many currently only in paper format, which not suitable for NN training. We developed a fully-automated online digitisation tool convert scanned into digital signals. Using automated horizontal vertical anchor point...
BackgroundAccurately determining arrhythmia mechanism from a 12-lead electrocardiogram (ECG) of supraventricular tachycardia can be challenging. We hypothesized convolutional neural network (CNN) trained to classify atrioventricular re-entrant (AVRT) vs nodal (AVNRT) the ECG, when using findings invasive electrophysiology (EP) study as gold standard.MethodsWe CNN on data 124 patients undergoing EP studies with final diagnosis AVRT or AVNRT. A total 4962 5-second ECG segments were used for...
### Key messages > Artificial intelligence has the potential to completely change way that physicians use electrocardiogram, but caution must be applied, explain Sau and Ng (AI) as a field had exponential growth interest in past 10 years. Clinicians have
ABSTRACT Background While sex differences in right heart phenotypes have been observed, the molecular drivers remain unknown. We used common genetic variation to provide biological insights into structure and function of ventricle (RV). Methods RV were obtained from cardiac magnetic resonance imaging 18,156 women 16,171 men UK Biobank, based on a deep-learning approach, including end-diastolic, end-systolic, stroke volumes, as well ejection fraction. Observational analyses sex-stratified...
Abstract Cardiac trabeculae form a network of muscular strands that line the inner surfaces heart. Their development depends on multiscale morphogenetic processes and, while highly conserved across vertebrate evolution, their role in pathophysiology mature heart is not fully understood. We report variant associations allele frequency spectrum for trabecular morphology 47,803 participants UK Biobank using fractal dimension analysis cardiac imaging. identified an association between...
While sex differences in right heart phenotypes have been observed, the molecular drivers remain unknown.
BACKGROUND: Subtle, prognostically important ECG features may not be apparent to physicians. In the course of supervised machine learning, thousands are identified. These limited conventional parameters and morphology. We aimed investigate whether neural network–derived could used predict future cardiovascular disease mortality have phenotypic genotypic associations. METHODS: extracted 5120 from an artificial intelligence–enabled model trained for 6 simple diagnoses applied unsupervised...
Accurately determining atrial arrhythmia mechanisms from a 12-lead electrocardiogram (ECG) can be challenging. Given the high success rate of cavotricuspid isthmus (CTI) ablation, identification CTI-dependent typical flutter (AFL) is important for treatment decisions and procedure planning. We sought to train convolutional neural network (CNN) classify AFL vs. non-CTI dependent tachycardia (AT), using data invasive electrophysiology (EP) study as gold standard.We trained CNN on 231 patients...
The aim of this study was to describe the head-up tilt (HUT) test and carotid sinus massage (CSM) responses, occurrence syncope with coughing during HUT in a large cohort patients.A total 5133 were retrospectively analysed identify patients cough syncope. Head-up followed by CSM performed. Patients made on two separate occasions an attempt reproduce typical clinical symptoms HUT. compared 29 age-matched control unrelated coughing. A (26 male, age 49 ± 14 years) identified. Coughing...