Dataset Information

Clinical and genetic associations of deep learning-derived cardiac magnetic resonance-based left ventricular mass.

ABSTRACT: Left ventricular mass is a risk marker for cardiovascular events, and may indicate an underlying cardiomyopathy. Cardiac magnetic resonance is the gold-standard for left ventricular mass estimation, but is challenging to obtain at scale. Here, we use deep learning to enable genome-wide association study of cardiac magnetic resonance-derived left ventricular mass indexed to body surface area within 43,230 UK Biobank participants. We identify 12 genome-wide associations (1 known at TTN and 11 novel for left ventricular mass), implicating genes previously associated with cardiac contractility and cardiomyopathy. Cardiac magnetic resonance-derived indexed left ventricular mass is associated with incident dilated and hypertrophic cardiomyopathies, and implantable cardioverter-defibrillator implant. An indexed left ventricular mass polygenic risk score ≥90^th percentile is also associated with incident implantable cardioverter-defibrillator implant in separate UK Biobank (hazard ratio 1.22, 95% CI 1.05-1.44) and Mass General Brigham (hazard ratio 1.75, 95% CI 1.12-2.74) samples. Here, we perform a genome-wide association study of cardiac magnetic resonance-derived indexed left ventricular mass to identify 11 novel variants and demonstrate that cardiac magnetic resonance-derived and genetically predicted indexed left ventricular mass are associated with incident cardiomyopathy.

SUBMITTER: Khurshid S

PROVIDER: S-EPMC10030590 | biostudies-literature | 2023 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Clinical and genetic associations of deep learning-derived cardiac magnetic resonance-based left ventricular mass.

Khurshid Shaan S Lazarte Julieta J Pirruccello James P JP Weng Lu-Chen LC Choi Seung Hoan SH Hall Amelia W AW Wang Xin X Friedman Samuel F SF Nauffal Victor V Biddinger Kiran J KJ Aragam Krishna G KG Batra Puneet P Ho Jennifer E JE Philippakis Anthony A AA Ellinor Patrick T PT Lubitz Steven A SA

Nature communications 20230321 1

Left ventricular mass is a risk marker for cardiovascular events, and may indicate an underlying cardiomyopathy. Cardiac magnetic resonance is the gold-standard for left ventricular mass estimation, but is challenging to obtain at scale. Here, we use deep learning to enable genome-wide association study of cardiac magnetic resonance-derived left ventricular mass indexed to body surface area within 43,230 UK Biobank participants. We identify 12 genome-wide associations (1 known at TTN and 11 nove ...[more]

PMID: 36944631

Similar Datasets

Project description:BackgroundAlthough there are many studies on the prognostic factors of left ventricular myocardial noncompaction (LVNC), the determinants are varied and not entirely consistent. This study aimed to build predictive models using radiomics features and machine learning to predict major adverse cardiovascular events (MACEs) in patients with LVNC.MethodsIn total, 96 patients with LVNC were included and randomly divided into training and test cohorts. A total of 105 cine cardiac magnetic resonance (CMR)-derived radiomics features and 35 clinical characteristics were extracted. Five different oversampling algorithms were compared for selection of the optimal imbalanced processing. Feature importance was assessed with extreme gradient boosting (XGBoost). We compared the performance of 5 machine learning classification methods with different sample:feature ratios to determine the optimal hybrid classification strategy. Subsequently, radiomics, clinical, and combined radiomics-clinical models were developed and compared.ResultsThe machine learning pipeline included an adaptive synthetic (ADASYN) algorithm for imbalanced processing, XGBoost feature selection with a sample:feature ratio of 10, and support vector machine (SVM) modeling. The areas under the receiver operating characteristic curves (AUCs) of the radiomics model, clinical model, and combined model in the validation cohort were 0.87 (sensitivity 83.33%, specificity 64.29%), 0.65 (sensitivity 16.67%, specificity 78.57%), and 0.92 (specificity 33.33%, sensitivity 100.00%), respectively. The radiomics model performed similarly to the clinical and combined models (P=0.124 and P=0.621, respectively). The performance of the combined model was significantly better than that of the clinical model (P=0.003).ConclusionsThe machine learning-based cine CMR radiomics model performed well at predicting MACEs in patients with LVNC. Adding radiomics features offered incremental prognostic value over clinical factors alone.

Project description:BackgroundCardiac magnetic resonance (CMR) has been used to diagnose and risk-stratify patients with left ventricular noncompaction (LVNC). The prognostic value of CMR parameters for LVNC, especially feature tracking (CMR-FT), is not well known in LVNC patients with left ventricular dysfunction. The present study aimed to investigate whether the combination of CMR-FT with traditional CMR parameters can increase the prognostic value of CMR for LVNC patients with reduced left ventricular ejection fraction (LVEF).MethodsA total of 123 candidates were retrospectively included in this multicenter study and 55 LVNC patients (mean age, 45.7 ± 16.2 years; 61.8% men) remained after applying the exclusion criteria. Clinical features, left ventricular (LV) function parameters, global and segment myocardial strain, and late gadolinium enhancement (LGE) were evaluated. The outcomes include the composite events of cardiovascular death, heart transplantation, hospitalization for heart failure, thromboembolic events, and ventricular arrhythmias.ResultsAfter a median follow-up of 5.17 years (interquartile range: 0.17 to 10.58 years), 24 (36.8%) patients experienced at least one major adverse cardiovascular event (MACE). The myocardial strain parameters of patients with events were lower than those of patients without events. In the univariable Cox analysis, LVEF, the presence of LGE, global longitudinal strain (GLS) and segmental strains, including longitudinal strain at the apical level and radial and circumferential strain at the basal level, were significantly associated with MACEs. In the multivariate analysis, LGE (hazard ratio (HR) 3.452, 95% CI 1.133 to 10.518, p = 0.029) was a strong predictor of MACEs and significantly improved the predictive value (chi-square of the model after adding LGE: 7.51 vs. 13.47, p = 0.009). However, myocardial strain parameters were not statistically significant for the prediction of MACEs after adjusting for age, body mass index, LVEF and the presence of LGE and did not increase the prognostic value (chi-square of the model after adding GLS: 13.47 vs. 14.14, p = 0.411) in the multivariate model.ConclusionsThe combination of CMR-FT with traditional CMR parameters may not increase the prognostic value of CMR in LVNC patients with reduced LVEF, while the presence of LGE was a strong independent predictor of MACEs and significantly improved the predictive value.

Dataset Information

Clinical and genetic associations of deep learning-derived cardiac magnetic resonance-based left ventricular mass.

Publications

Clinical and genetic associations of deep learning-derived cardiac magnetic resonance-based left ventricular mass.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets