Genetic Pathways to Heart Shape: Advancing Cardiovascular Risk Assessment

Cardiovascular disease remains the leading cause of death worldwide, with early detection and diagnosis being critical for improving survival rates. Researchers from Queen Mary University of London, King’s College London, University of Zaragoza, University College London, and Complexo Hospitalario Universitario A Coruña in Spain have uncovered a groundbreaking method for assessing heart disease risk based on the genetically determined shape of the heart. 

Using advanced 3D imaging and machine learning, the team analyzed MRI scans of the hearts of 40,000 participants. They created detailed models of the right and left ventricles and identified 11 distinct heart shapes. Unlike prior studies that emphasized size and volume alone, this research explored how shape, along with structural variations, can reveal a person's genetic predisposition to heart disease. 

The study's genetic analysis pinpointed 45 areas in the human genome associated with heart shape, 14 of which were previously unknown to influence cardiovascular health. These findings provide valuable insights into the biological pathways linking heart structure to disease risk, offering a new dimension to cardiovascular diagnostics. 

This novel approach underscores the importance of integrating genetics with imaging technologies. By focusing on shape, clinicians can enhance early detection, paving the way for more precise interventions. These results hold promise for reshaping how we understand, diagnose, and treat heart disease. 

 

References: 

https://medicalxpress.com/news/2024-11-genetic-links-heart-cardiovascular-disease.html 

https://pmc.ncbi.nlm.nih.gov/articles/PMC7006335/ 

 

Using Artificial Intelligence to Impute Phenotypes on Population Scale Databases

 

    A report from UCLA details the usage of analyzing large scale databases to impute phenotypes in databases that lack data on phenotypes. Phenotypes in these databases are often missing in many of the individuals in the databases, limiting the utility that these databases have. The group created a new imputation method for phenotypes based off of the UK Biobank dataset. The accuracy of their imputation method, dubbed AutoComplete, outperformed the next best method, called SoftImpute, with the greatest improvements being in the psychiatric and cardiovascular phenotypes. 

    The significance of their imputer is centered around the fact that they take into consideration not only the relationships between phenotypes and the data available, but also the metadata of the database used. They took into account the "patterns of missingness" in the data, which are often structured due to the way that the data is gathered and placed into the databases.

    This report not only exemplifies the importance of having strong computational methods in genetics but also the significance of properly reporting data. Datasets that contain complete information not only make it easier to work with the data, but also provide more accurate results once the data is processed.

The Article

An, U., Pazokitoroudi, A., Alvarez, M. et al. Deep learning-based phenotype imputation on population-scale biobank data increases genetic discoveries. Nat Genet (2023). https://doi.org/10.1038/s41588-023-01558-w

Reference to SoftImpute

Hastie, T., Mazumder, R., Lee, J. D., & Zadeh, R. (2015). Matrix completion and low-rank SVD via fast alternating least squares. The Journal of Machine Learning Research, 16(1), 3367-3402.