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

Khurshid, Shaan; Lazarte, Julieta; Weng, Lu‐Chen; Choi, Seung Hoan; Hall, Amelia Weber; Wang, Xin; Friedman, Samuel; Nauffal, Victor; Biddinger, Kiran J; Aragam, Krishna; Batra, Puneet; Ho, Jennifer E.; Philippakis, Anthony; Ellinor, Patrick T.; Lubitz, Steven A.

doi:10.1101/2022.01.09.22268962

Cited by 6 publications

(7 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We sourced anaemia summary statistics from the FinnGen GWAS database. Data for heart failure and left ventricular and atrial parameters, encompassing left ventricular mass (LVM), left ventricular mass index (LVMI), left ventricular end‐diastolic volume (LVEDV), left ventricular end‐systolic volume (LVESV), left ventricular ejection fraction (LVEF), left atrial maximum volume (LAmax), left atrial minimum volume (LAmin), left atrial active emptying fraction (LAaEF), left atrial passive emptying fraction (LApEF), and left atrial total emptying fraction (LAtEF), were obtained from HERMES, 11 UK Biobank, 12,13 and FinnGen GWAS database. Table 1 provides a comprehensive overview of summary statistics for all exposure and outcome in this study.…”

Section: Methodsmentioning

confidence: 99%

Association of anaemia on heart failure and left ventricular function: A bidirectional Mendelian randomization study

Ying,

Ye,

Yuan

et al. 2023

ESC Heart Failure

View full text Add to dashboard Cite

AimsObservational studies have suggested that anaemia is associated with an increased risk of heart failure (HF). But the potential causal association is not clear. We aimed to investigate the association between anaemia and HF risk.Methods and resultsA Mendelian randomization (MR) analysis was performed to confirm the causal association of anaemia with the risk of HF and left ventricular structure and function. Furthermore, a reverse‐direction MR analyses was conducted to assess the causal effect of HF on anaemia. The MR analysis indicated that genetically predicted anaemia is associated with the increased risk of HF (meta: odd ratio (OR) = 1.12; 95% confidence interval (CI) [1.04, 1.20]; P = 0.002), and left ventricular mass index (β = 1.051; 95% CI [0.384, 1.718]; P = 0.002), left ventricular mass (β = 2.063; 95% CI [0.578, 3.547]; P = 0.006), left atrial minimum volume (β = 0.076; 95% CI [0.008, 0.143]; P = 0.028), and left atrial maximum volume (β = 0.090; 95% CI [0.023, 0.157]; P = 0.009). In the reverse‐direction MR analyses, we found that genetic susceptibility to HF was significantly associated with the increased risk of anaemia (meta: OR = 1.40; 95% CI [1.24, 1.59]; P = 1.79 × 10−7).ConclusionsThis MR study supports the genetic evidence that there is bidirectional causality between anaemia and the risk of HF as well as anaemia may cause left ventricular hypertrophy and enlargement of the left atrium. Considering the adverse causal effects between the two diseases, more attention should be paid to the prevention and treatment of anaemia in patients with HF.

show abstract

Section: Methodsmentioning

confidence: 99%

Association of anaemia on heart failure and left ventricular function: A bidirectional Mendelian randomization study

Ying,

Ye,

Yuan

et al. 2023

ESC Heart Failure

View full text Add to dashboard Cite

show abstract

“…Their interaction, however, does not appear to stem from this proximity. Indeed, the CCDC141 and TTN genes have been individually associated with LV mass 42,43 . Due to this proximity, previous studies 44,45 have assumed CCDC141 as a secondary gene that affects LV mass through the TTN gene expression.…”

Section: Loci Associated With Left Ventricular Mass Exhibit Regulator...mentioning

confidence: 99%

Epistasis regulates genetic control of cardiac hypertrophy

Wang,

Tang,

Youlton

et al. 2023

Preprint

View full text Add to dashboard Cite

The combinatorial effect of genetic variants is often assumed to be additive. Although genetic variation can clearly interact non-additively, methods to uncover epistatic relationships remain in their infancy. We develop low-signal signed iterative random forests to elucidate the complex genetic architecture of cardiac hypertrophy. We derive deep learning-based estimates of left ventricular mass from the cardiac MRI scans of 29,661 individuals enrolled in the UK Biobank. We report epistatic genetic variation including variants close toCCDC141,IGF1R,TTN, andTNKS.Several loci not prioritized by univariate genome-wide association analysis are identified. Functional genomic and integrative enrichment analyses reveal a complex gene regulatory network in which genes mapped from these loci share biological processes and myogenic regulatory factors. Through a network analysis of transcriptomic data from 313 explanted human hearts, we show that these interactions are preserved at the level of the cardiac transcriptome. We assess causality of epistatic effects via RNA silencing of gene-gene interactions in human induced pluripotent stem cell-derived cardiomyocytes. Finally, single-cell morphology analysis using a novel high-throughput microfluidic system shows that cardiomyocyte hypertrophy is non-additively modifiable by specific pairwise interactions betweenCCDC141and bothTTNandIGF1R. Our results expand the scope of genetic regulation of cardiac structure to epistasis.

show abstract

“…With high fidelity imaging with CMR, deep learning can precisely and reproducibly evaluate imaging structures 10,12 . Previous studies have already evaluated LV wall thickness and mass 9,13,14 , finding strong associations with TTN and CDKN1A among other variants. In this work, we sought to build upon this foundation to evaluate the impact of focal hypertrophy.…”

Section: Introductionmentioning

confidence: 99%

“…Deep learning-enabled high throughput evaluation of cardiac imaging opens an avenue for largescale studies of cardiac phenotypes 9,10,11 . The ability to precisely phenotype cardiac imaging 12 and combining underlying genetic information allows for the interrogation of a wide range of phenotypes and clinically meaningful traits.…”

Section: Introductionmentioning

confidence: 99%

Clinical and genetic associations of asymmetric apical and septal left ventricular hypertrophy

Yuan,

Vukadinovic,

Kwan

et al. 2023

Preprint

View full text Add to dashboard Cite

Increased left ventricular mass has been associated with adverse cardiovascular outcomes including incident cardiomyopathy and atrial fibrillation. Such associations have been studied in relation to total left ventricular hypertrophy, while the regional distribution of myocardial hypertrophy is extremely variable and the clinical significant and genetic associations of such variability requires further study. Here, we use deep learning derived phenotypes of disproportionate patterns of hypertrophy, such as apical hypertrophy and septal hypertrophy, to study genome-wide and clinical associations in addition to and independent from total left ventricular mass within 35,268 UK Biobank participants. Adjusting for total left ventricular mass, apical hypertrophy is associated with elevated risk for cardiomyopathy and atrial fibrillation, and the risk for cardiomyopathy was increased for subjects with increased apical or septal mass even in the absence of global hypertrophy. We identified seventeen genome-wide associations for left ventricular mass, three unique associations with increased apical mass, and three additional unique associations with increased septal mass. Further studies are needed in multi-ethnic cohorts.

show abstract

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

Cited by 6 publications

References 52 publications

Association of anaemia on heart failure and left ventricular function: A bidirectional Mendelian randomization study

Association of anaemia on heart failure and left ventricular function: A bidirectional Mendelian randomization study

Epistasis regulates genetic control of cardiac hypertrophy

Clinical and genetic associations of asymmetric apical and septal left ventricular hypertrophy

Contact Info

Product

Resources

About