Dataset Information

Deep learning enables genetic analysis of the human thoracic aorta.

ABSTRACT: Enlargement or aneurysm of the aorta predisposes to dissection, an important cause of sudden death. We trained a deep learning model to evaluate the dimensions of the ascending and descending thoracic aorta in 4.6 million cardiac magnetic resonance images from the UK Biobank. We then conducted genome-wide association studies in 39,688 individuals, identifying 82 loci associated with ascending and 47 with descending thoracic aortic diameter, of which 14 loci overlapped. Transcriptome-wide analyses, rare-variant burden tests and human aortic single nucleus RNA sequencing prioritized genes including SVIL, which was strongly associated with descending aortic diameter. A polygenic score for ascending aortic diameter was associated with thoracic aortic aneurysm in 385,621 UK Biobank participants (hazard ratio = 1.43 per s.d., confidence interval 1.32-1.54, P = 3.3 × 10^-20). Our results illustrate the potential for rapidly defining quantitative traits with deep learning, an approach that can be broadly applied to biomedical images.

SUBMITTER: Pirruccello JP

PROVIDER: S-EPMC8758523 | biostudies-literature | 2022 Jan

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Deep learning enables genetic analysis of the human thoracic aorta.

Pirruccello James P JP Chaffin Mark D MD Chou Elizabeth L EL Fleming Stephen J SJ Lin Honghuang H Nekoui Mahan M Khurshid Shaan S Friedman Samuel F SF Bick Alexander G AG Arduini Alessandro A Weng Lu-Chen LC Choi Seung Hoan SH Akkad Amer-Denis AD Batra Puneet P Tucker Nathan R NR Hall Amelia W AW Roselli Carolina C Benjamin Emelia J EJ Vellarikkal Shamsudheen K SK Gupta Rajat M RM Stegmann Christian M CM Juric Dejan D Stone James R JR Vasan Ramachandran S RS Ho Jennifer E JE Hoffmann Udo U Lubitz Steven A SA Philippakis Anthony A AA Lindsay Mark E ME Ellinor Patrick T PT

Nature genetics 20211126 1

Enlargement or aneurysm of the aorta predisposes to dissection, an important cause of sudden death. We trained a deep learning model to evaluate the dimensions of the ascending and descending thoracic aorta in 4.6 million cardiac magnetic resonance images from the UK Biobank. We then conducted genome-wide association studies in 39,688 individuals, identifying 82 loci associated with ascending and 47 with descending thoracic aortic diameter, of which 14 loci overlapped. Transcriptome-wide analyse ...[more]

PMID: 34837083

Similar Datasets

Project description:Background/Objectives: In the presence of porcelain aorta (PA), transcatheter aortic valve replacement (TAVR) has become a class I therapeutic indication for the treatment of severe aortic valve stenosis. To date, few studies have analyzed the clinical outcomes of TAVR in PA patients. We aim to analyze the calcification patterns of the thoracic aorta in PA patients and to evaluate their clinical implications for TAVR procedures. Methods: This study included 161 patients who had PA confirmed through pre-operative CT and underwent TAVR between 11/2014 and 12/2022. The primary outcome was to perform a multi-slice CT (MSCT) analysis assessing the calcification in the proximal, middle, and distal thoracic aortic segments. Each segment was divided into quadrants for scoring calcifications on a scale from 1 (<25%) to 4 (>75%). The cohort was categorized into circular or noncircular calcification group. The secondary clinical outcomes were defined according to VARC-3 criteria. Results: The study cohort included 161 patients (median age, 77.2 years; IQR, 70.1-82.6 years). The median EuroSCORE II and STS predicted risk of mortality were 3.10% [1.80-5.58] and 2.70% [1.70-4.30], respectively. In 75% of patients (n = 121/161), TAVR was performed via transfemoral access. Circular calcifications were found in 8.1% of patients, while noncircular calcifications were present in 91.9%. Significant calcifications were primarily in the right quadrant of the proximal segment (33.54%), superior quadrant of the middle segment (39.75%), and left quadrant of the distal segment (73.29%). The 30-day mortality rate was 3.11% and periprocedural ischemic stroke rate 3.38%. Conclusions: Most TAVR patients with PA exhibited noncircular calcification. The most extensive calcifications were primarily in areas relevant to surgical manipulation. Patients with PA displayed low short-term mortality and relatively few stroke events. In view of these findings, TAVR constitutes a valid treatment option for patients with PA and aortic stenosis.

Dataset Information

Deep learning enables genetic analysis of the human thoracic aorta.

Publications

Deep learning enables genetic analysis of the human thoracic aorta.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets