scholarly journals Clinical and Genetic Associations of Deep Learning-Derived Cardiac Magnetic Resonance-Based Left Ventricular Mass

2022 ◽  
Author(s):  
Shaan Khurshid ◽  
Julieta Lazarte ◽  
James Pirruccello ◽  
Lu-Chen Weng ◽  
Seung Hoan Choi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Genome Wide Association Study ◽  
Learning Algorithm ◽  
Left Ventricular ◽  
Polygenic Risk Score ◽  
Uk Biobank ◽  
Genome Wide ◽  
A Genome

Increased left ventricular (LV) mass (LVM) and LV hypertrophy (LVH) are risk markers for adverse cardiovascular events, and may indicate an underlying cardiomyopathy. Cardiac magnetic resonance (CMR) is the gold standard for LVM estimation, but is challenging to obtain at scale, which has limited the power of prior genetic analyses. In the current study, we performed a genome-wide association study (GWAS) of CMR-derived LVM indexed to body surface area (LVMI) estimated using a deep learning algorithm within nearly 50,000 participants from the UK Biobank. We identified 12 independent associations (1 known at TTN and 11 novel) meeting genome-wide significance, implicating several candidate genes previously associated with cardiac contractility and cardiomyopathy. Greater CMR-derived LVMI was associated with higher risk of incident dilated (hazard ratio [HR] 2.58 per 1-SD increase, 95% CI 2.10-3.17) and hypertrophic (HR 2.62, 95% CI 2.09-3.30) cardiomyopathies. A polygenic risk score (PRS) for LVMI was also associated with incident hypertrophic cardiomyopathy within a separate set of UK Biobank participants (HR] 1.12, 95% CI 1.01-1.12) and among individuals in an external Mass General Brigham dataset (HR 1.18, 95% CI 1.01-1.37). In summary, using CMR-derived LVM available at scale, we have identified 12 common variants associated with LVMI (11 novel) and demonstrated that both CMR-derived and genetically determined LVMI are associated with risk of incident cardiomyopathy.

scholarly journals Deep Learning to Predict Cardiac Magnetic Resonance–Derived Left Ventricular Mass and Hypertrophy From 12-Lead ECGs

2021 ◽  
Vol 14 (6) ◽  
Author(s):  
Shaan Khurshid ◽  
Samuel Friedman ◽  
James P. Pirruccello ◽  
Paolo Di Achille ◽  
Nathaniel Diamant ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Left Ventricular Mass ◽  
Left Ventricular ◽  
Uk Biobank ◽  
C Statistic ◽  
Lv Mass ◽  
Test Sets ◽  
The Uk

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.

scholarly journals Variants in urate transporters, ADH1B, GCKR and MEPE genes associate with transition from asymptomatic hyperuricaemia to gout: results of the first gout versus asymptomatic hyperuricaemia GWAS in Caucasians using data from the UK Biobank

2021 ◽  
pp. annrheumdis-2020-219796
Author(s):  
Gabriela Sandoval-Plata ◽  
Kevin Morgan ◽  
Abhishek Abhishek
Keyword(s):  
Genome Wide Association Study ◽  
Predictive Ability ◽  
Serum Urate ◽  
Polygenic Risk Score ◽  
Nucleotide Polymorphisms ◽  
Uk Biobank ◽  
Genome Wide ◽  
A Genome ◽  
Using Data ◽  
The Uk

ObjectivesTo perform a genome-wide association study (GWAS) of gout cases versus asymptomatic hyperuricaemia (AH) controls, and gout cases versus normouricaemia controls, and to generate a polygenic risk score (PRS) to determine gout-case versus AH-control status.MethodsGout cases and AH controls (serum urate (SU) ≥6.0 mg/dL) from the UK Biobank were divided into discovery (4934 cases, 56 948 controls) and replication (2115 cases, 24 406 controls) cohorts. GWAS was conducted and PRS generated using summary statistics in discovery cohort as the base dataset and the replication cohort as the target dataset. The predictive ability of the model was evaluated. GWAS were performed to identify variants associated with gout compared with normouricaemic controls using SU <6.0 mg/dL and <7.0 mg/dL thresholds, respectively.ResultsThirteen independent single nucleotide polymorphisms (SNPs) in ABCG2, SLC2A9, SLC22A11, GCKR, MEPE, PPM1K-DT, LOC105377323 and ADH1B reached genome-wide significance and replicated as predictors of AH to gout transition. Twelve of 13 associations were novel for this transition, and rs1229984 (ADH1B) was identified as GWAS locus for gout for the first time. The best PRS model was generated from association data of 17 SNPs; and had predictive ability of 58.5% that increased to 69.2% on including demographic factors. Two novel SNPs rs760077(MTX1) and rs3800307(PRSS16) achieved GWAS significance for association with gout compared with normouricaemic controls using both SU thresholds.ConclusionThe association of urate transporters with gout supports the central role of hyperuricaemia in its pathogenesis. Larger GWAS are required to identify if variants in inflammatory pathways contribute to progression from AH to gout.

scholarly journals Deep Learning to Estimate Cardiac Magnetic Resonance-Derived Left Ventricular Mass

2020 ◽  
Author(s):  
Shaan Khurshid ◽  
Samuel Friedman ◽  
James P. Pirruccello ◽  
Paolo Di Achille ◽  
Nathaniel Diamant ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cardiac Magnetic Resonance ◽  
Magnetic Resonance ◽  
Open Source ◽  
Pearson Correlation ◽  
Absolute Error ◽  
Learning Model ◽  
Left Ventricular ◽  
Lv Mass ◽  
Deep Learning Model

ABSTRACTBackgroundCardiac magnetic resonance (CMR) is the gold standard for left ventricular hypertrophy (LVH) diagnosis. CMR-derived LV mass can be estimated using proprietary algorithms (e.g., inlineVF), but their accuracy and availability may be limited.ObjectiveTo develop an open-source deep learning model to estimate CMR-derived LV mass.MethodsWithin participants of the UK Biobank prospective cohort undergoing CMR, we trained two convolutional neural networks to estimate LV mass. The first (ML4Hreg) performed regression informed by manually labeled LV mass (available in 5,065 individuals), while the second (ML4Hseg) performed LV segmentation informed by inlineVF contours. We compared ML4Hreg, ML4Hseg, and inlineVF against manually labeled LV mass within an independent holdout set using Pearson correlation and mean absolute error (MAE). We assessed associations between CMR-derived LVH and prevalent cardiovascular disease using logistic regression adjusted for age and sex.ResultsWe generated CMR-derived LV mass estimates within 38,574 individuals. Among 891 individuals in the holdout set, ML4Hseg reproduced manually labeled LV mass more accurately (r=0.864, 95% CI 0.847-0.880; MAE 10.41g, 95% CI 9.82-10.99) than ML4Hreg (r=0.843, 95% CI 0.823-0.861; MAE 10.51, 95% CI 9.86-11.15, p=0.01) and inlineVF (r=0.795, 95% CI 0.770-0.818; MAE 14.30, 95% CI 13.46-11.01, p<0.01). LVH defined using ML4Hseg demonstrated the strongest associations with hypertension (odds ratio 2.76, 95% CI 2.51-3.04), atrial fibrillation (1.75, 95% CI 1.37-2.20), and heart failure (4.53, 95% CI 3.16-6.33).ConclusionsML4Hseg is an open-source deep learning model providing automated quantification of CMR-derived LV mass. Deep learning models characterizing cardiac structure may facilitate broad cardiovascular discovery.

Polygenic Risk Scores for Kidney Function and Their Associations with Circulating Proteome, and Incident Kidney Diseases

2021 ◽  
pp. ASN.2020111599
Author(s):  
Zhi Yu ◽  
Jin Jin ◽  
Adrienne Tin ◽  
Anna Köttgen ◽  
Bing Yu ◽  
...  
Keyword(s):  
Kidney Function ◽  
Kidney Diseases ◽  
Association Studies ◽  
Polygenic Risk Score ◽  
Genome Wide Association Studies ◽  
Plasma Proteome ◽  
Uk Biobank ◽  
Polygenic Risk ◽  
Genome Wide ◽  
A Genome

Background: Genome-wide association studies (GWAS) have revealed numerous loci for kidney function (estimated glomerular filtration rate, eGFR). The relationship of polygenic predictors of eGFR, risk of incident adverse kidney outcomes, and the plasma proteome is not known. Methods: We developed a genome-wide polygenic risk score (PRS) for eGFR by applying the LDpred algorithm to summary statistics generated from a multiethnic meta-analysis of CKDGen Consortium GWAS (N=765,348) and UK Biobank GWAS (90% of the cohort; N=451,508), followed by best parameter selection using the remaining 10% of UK Biobank (N=45,158). We then tested the association of the PRS in the Atherosclerosis Risk in Communities (ARIC) study (N=8,866) with incident chronic kidney disease, kidney failure, and acute kidney injury. We also examined associations between the PRS and 4,877 plasma proteins measured at at middle age and older adulthood and evaluated mediation of PRS associations by eGFR. Results: The developed PRS showed significant associations with all outcomes with hazard ratios (95% CI) per 1 SD lower PRS ranged from 1.06 (1.01, 1.11) to 1.33 (1.28, 1.37). The PRS was significantly associated with 132 proteins at both time points. The strongest associations were with cystatin-C, collagen alpha-1(XV) chain, and desmocollin-2. Most proteins were higher at lower kidney function, except for 5 proteins including testican-2. Most correlations of the genetic PRS with proteins were mediated by eGFR. Conclusions: A PRS for eGFR is now sufficiently strong to capture risk for a spectrum of incident kidney diseases and broadly influences the plasma proteome, primarily mediated by eGFR.

scholarly journals Genome-wide association study of alcohol consumption and genetic overlap with other health-related traits in UK Biobank (N=112,117)

2017 ◽  
Author(s):  
Toni-Kim Clarke ◽  
Mark J. Adams ◽  
Gail Davies ◽  
David M. Howard ◽  
Lynsey S. Hall ◽  
...  
Keyword(s):  
Alcohol Consumption ◽  
Association Study ◽  
Genome Wide Association Study ◽  
Hdl Cholesterol ◽  
Genome Wide Association ◽  
P Value ◽  
Uk Biobank ◽  
Genome Wide ◽  
A Genome ◽  
Genetic Overlap

AbstractAlcohol consumption has been linked to over 200 diseases and is responsible for over 5% of the global disease burden. Well known genetic variants in alcohol metabolizing genes, e.g. ALDH2, ADH1B, are strongly associated with alcohol consumption but have limited impact in European populations where they are found at low frequency. We performed a genome-wide association study (GWAS) of self-reported alcohol consumption in 112,117 individuals in the UK Biobank (UKB) sample of white British individuals. We report significant genome-wide associations at 8 independent loci. These include SNPs in alcohol metabolizing genes (ADH1B/ADH1C/ADH5) and 2 loci in KLB, a gene recently associated with alcohol consumption. We also identify SNPs at novel loci including GCKR, PXDN, CADM2 and TNFRSF11A. Gene-based analyses found significant associations with genes implicated in the neurobiology of substance use (CRHR1, DRD2), and genes previously associated with alcohol consumption (AUTS2). GCTA-GREML analyses found a significant SNP-based heritability of self-reported alcohol consumption of 13% (S.E.=0.01). Sex-specific analyses found largely overlapping GWAS loci and the genetic correlation between male and female alcohol consumption was 0.73 (S.E.=0.09, p-value = 1.37 x 10−16). Using LD score regression, genetic overlap was found between alcohol consumption and schizophrenia (rG=0.13, S.E=0.04), HDL cholesterol (rG=0.21, S.E=0.05), smoking (rG=0.49, S.E=0.06) and various anthropometric traits (e.g. Overweight, rG=-0.19, S.E.=0.05). This study replicates the association between alcohol consumption and alcohol metabolizing genes and KLB, and identifies 4 novel gene associations that should be the focus of future studies investigating the neurobiology of alcohol consumption.

scholarly journals Brain age prediction using deep learning uncovers associated sequence variants

2019 ◽  
Vol 10 (1) ◽  
Author(s):  
B. A. Jonsson ◽  
G. Bjornsdottir ◽  
T. E. Thorgeirsson ◽  
L. M. Ellingsen ◽  
G. Bragi Walters ◽  
...  
Keyword(s):  
Deep Learning ◽  
Genome Wide Association Study ◽  
Structural Mri ◽  
Machine Learning Algorithms ◽  
Age Difference ◽  
Sequence Variants ◽  
Uk Biobank ◽  
A Genome ◽  
The Uk ◽  
Brain Age

AbstractMachine learning algorithms can be trained to estimate age from brain structural MRI. The difference between an individual’s predicted and chronological age, predicted age difference (PAD), is a phenotype of relevance to aging and brain disease. Here, we present a new deep learning approach to predict brain age from a T1-weighted MRI. The method was trained on a dataset of healthy Icelanders and tested on two datasets, IXI and UK Biobank, utilizing transfer learning to improve accuracy on new sites. A genome-wide association study (GWAS) of PAD in the UK Biobank data (discovery set: $$N=12378$$N=12378, replication set: $$N=4456$$N=4456) yielded two sequence variants, rs1452628-T ($$\beta =-0.08$$β=−0.08, $$P=1.15\times{10}^{-9}$$P=1.15×10−9) and rs2435204-G ($$\beta =0.102$$β=0.102, $$P=9.73\times 1{0}^{-12}$$P=9.73×10−12). The former is near KCNK2 and correlates with reduced sulcal width, whereas the latter correlates with reduced white matter surface area and tags a well-known inversion at 17q21.31 (H2).

scholarly journals A novel variant in GLIS3 is associated with osteoarthritis

2018 ◽  
Vol 77 (4) ◽  
pp. 620-623 ◽  
Author(s):  
Elisabetta Casalone ◽  
Ioanna Tachmazidou ◽  
Eleni Zengini ◽  
Konstantinos Hatzikotoulas ◽  
Sophie Hackinger ◽  
...  
Keyword(s):  
Complex Disease ◽  
Genome Wide Association Study ◽  
Total Joint Replacement ◽  
Population Based ◽  
Uk Biobank ◽  
Proteomics Data ◽  
Glucose Levels ◽  
Genome Wide ◽  
A Genome ◽  
The Uk

ObjectivesOsteoarthritis (OA) is a complex disease, but its genetic aetiology remains poorly characterised. To identify novel susceptibility loci for OA, we carried out a genome-wide association study (GWAS) in individuals from the largest UK-based OA collections to date.MethodsWe carried out a discovery GWAS in 5414 OA individuals with knee and/or hip total joint replacement (TJR) and 9939 population-based controls. We followed-up prioritised variants in OA subjects from the interim release of the UK Biobank resource (up to 12 658 cases and 50 898 controls) and our lead finding in operated OA subjects from the full release of UK Biobank (17 894 cases and 89 470 controls). We investigated its functional implications in methylation, gene expression and proteomics data in primary chondrocytes from 12 pairs of intact and degraded cartilage samples from patients undergoing TJR.ResultsWe detect a genome-wide significant association at rs10116772 with TJR (P=3.7×10−8; for allele A: OR (95% CI) 0.97 (0.96 to 0.98)), an intronic variant in GLIS3, which is expressed in cartilage. Variants in strong correlation with rs10116772 have been associated with elevated plasma glucose levels and diabetes.ConclusionsWe identify a novel susceptibility locus for OA that has been previously implicated in diabetes and glycaemic traits.

Sign in / Sign up

Export Citation Format

Share Document