| Application: | 7089, Exome Sequencing of All Premature Coronary Artery Disease Participants in UK Biobank |
| Title: | Deep Learning to Predict Cardiac Magnetic Resonance-Derived Left Ventricular Mass and Hypertrophy From 12-Lead ECGs |
| Size: | 246200 B |
| Archived: | 2 Aug 2021 |
| Stability: | Complete |
| Personal: | Contains individual-level data |
Return 3725
WARNING: the interactive features of this website use CSS3, which your browser does not support. To use the full features of this website, please update your browser.
Notes
Background:Classical methods for detecting left ventricular (LV) hypertrophy (LVH) using 12-lead ECGs are insensitive. Deep learning models using ECG to infer cardiac magnetic resonance (CMR)-derived LV mass may improve LVH detection.
Methods:
Within 32 239 individuals of the UK Biobank prospective cohort who underwent CMR and 12-lead ECG, we trained a convolutional neural network to predict CMR-derived LV mass using 12-lead ECGs (left ventricular mass-artificial intelligence [LVM-AI]). In independent test sets (UK Biobank [n=4903] and Mass General Brigham [MGB, n=1371]), we assessed correlation between LVM-AI predicted and CMR-derived LV mass and compared LVH discrimination using LVM-AI versus traditional ECG-based rules (ie, Sokolow-Lyon, Cornell, lead aVL rule, or any ECG rule). In the UK Biobank and an ambulatory MGB cohort (MGB outcomes, n=28 612), we assessed associations between LVM-AI predicted LVH and incident cardiovascular outcomes using age- and sex-adjusted Cox regression.
Results:
LVM-AI predicted LV mass correlated with CMR-derived LV mass in both test sets, although correlation was greater in the UK Biobank (r=0.79) versus MGB (r=0.60, P<0.001 for both). When compared with any ECG rule, LVM-AI demonstrated similar LVH discrimination in the UK Biobank (LVM-AI c-statistic 0.653 [95% CI, 0.608 -0.698] versus any ECG rule c-statistic 0.618 [95% CI, 0.574 -0.663], P=0.11) and superior discrimination in MGB (0.621; 95% CI, 0.592 -0.649 versus 0.588; 95% CI, 0.564 -0.611, P=0.02). LVM-AI-predicted LVH was associated with incident atrial fibrillation, myocardial infarction, heart failure, and ventricular arrhythmias.
Conclusions:
Deep learning-inferred LV mass estimates from 12-lead ECGs correlate with CMR-derived LV mass, associate with incident cardiovascular disease, and may improve LVH discrimination compared to traditional ECG rules.
Application 7089
Exome Sequencing of All Premature Coronary Artery Disease Participants in UK Biobank
Coronary artery disease (CAD) is the leading cause of death in the UK. When CAD occurs prematurely, the role for inheritance is greater. DNA sequencing of the protein-coding portions of the human genome ('the exome') can identify genes responsible for CAD. Here, we seek to: 1) identify all individuals in the UK Biobank with premature CAD (mean=55y, women=65y); 2) identify controls free of CAD; 3) perform whole exome sequencing on cases and controls; 4) compare sequences to discover genes responsible for CAD; 5) perform a comprehensive phenotypic scan to understand the spectrum of consequences from CAD genes. A stated purpose of UK Biobank is to improve the prevention, diagnosis and treatment of a wide range of serious and life-threatening illnesses. We have secured funding to exome sequence up to 20,000 UK Biobank participants with and without CAD. Successful completion of this study should result in the identification of novel genetic causes for MI, the leading cause of death in the UK. Genomic variation discovered in the UK Biobank associated with MI may prove useful to target preventive strategies, understand the biology of MI in humans, and to identify novel molecular targets for therapy. We propose to: 1) identify all individuals in the UK Biobank with CAD at an early age (=55 years old in men and =65 years old in women); 2) identify controls free of CAD; 3) perform whole exome sequencing on all cases and controls; 4) compare sequences of cases with controls to discover genes responsible for CAD; and 5) understand the range of phenotypic effects from genes associated with CAD. We have secured funding to exome sequence up to 20,000 UK Biobank participants. Of note, we have secured funding to exome sequence up to 20,000 UK Biobank participants. We seek to identify all individuals in the UK Biobank with CAD at an early age (=55 years old in men and =65 years old in women). In the latest data release, there are 10,450 participants with any diagnosis code for ischemic heart disease. Further work will be required to confirm this diagnosis and restrict to CAD onset at an early age.
| Lead investigator: | Dr Pradeep Natarajan |
| Lead institution: | Broad Institute |
5 related Returns
| Return ID | App ID | Description | Archive Date |
|---|---|---|---|
| 3454 | 7089 | Analysis of cardiac magnetic resonance imaging in 36,000 individuals yields genetic insights into dilated cardiomyopathy | 26 May 2021 |
| 3723 | 7089 | Clinical Utility of Lipoprotein(a) and LPA Genetic Risk Score in Risk Prediction of Incident Atherosclerotic Cardiovascular Disease. | 2 Aug 2021 |
| 3290 | 7089 | Deep learning to estimate cardiac magnetic resonance-derived left ventricular mass | 9 Apr 2021 |
| 3380 | 7089 | Genetic Association of Albuminuria with Cardiometabolic Disease and Blood Pressure | 26 Apr 2021 |
| 3361 | 7089 | Polygenic background modifies penetrance of monogenic variants for tier 1 genomic conditions | 21 Apr 2021 |
1 Publication
| Pub ID | Title | Author(s) | Year | Journal |
|---|---|---|---|---|
| 3726 | Deep Learning to Predict Cardiac Magnetic Resonance-Derived Left Ventricular Mass and Hypertrophy From 12-Lead ECGs | Khurshid S et al. | 2021 | Circ Cardiovasc Imaging |
Enabling scientific discoveries that improve human health