Literature DB >> 32019371

Virtual genetic diagnosis for familial hypercholesterolemia powered by machine learning.

Ana Pina1,2,3, Saga Helgadottir4, Rosellina Margherita Mancina5, Chiara Pavanello6, Carlo Pirazzi7, Tiziana Montalcini8, Roberto Henriques9, Laura Calabresi6, Olov Wiklund5, M Paula Macedo1,2,3, Luca Valenti10, Giovanni Volpe4, Stefano Romeo5,7,8.   

Abstract

AIMS: Familial hypercholesterolemia (FH) is the most common genetic disorder of lipid metabolism. The gold standard for FH diagnosis is genetic testing, available, however, only in selected university hospitals. Clinical scores - for example, the Dutch Lipid Score - are often employed as alternative, more accessible, albeit less accurate FH diagnostic tools. The aim of this study is to obtain a more reliable approach to FH diagnosis by a "virtual" genetic test using machine-learning approaches. METHODS AND
RESULTS: We used three machine-learning algorithms (a classification tree (CT), a gradient boosting machine (GBM), a neural network (NN)) to predict the presence of FH-causative genetic mutations in two independent FH cohorts: the FH Gothenburg cohort (split into training data (N = 174) and internal test (N = 74)) and the FH-CEGP Milan cohort (external test, N = 364). By evaluating their area under the receiver operating characteristic (AUROC) curves, we found that the three machine-learning algorithms performed better (AUROC 0.79 (CT), 0.83 (GBM), and 0.83 (NN) on the Gothenburg cohort, and 0.70 (CT), 0.78 (GBM), and 0.76 (NN) on the Milan cohort) than the clinical Dutch Lipid Score (AUROC 0.68 and 0.64 on the Gothenburg and Milan cohorts, respectively) in predicting carriers of FH-causative mutations.
CONCLUSION: In the diagnosis of FH-causative genetic mutations, all three machine-learning approaches we have tested outperform the Dutch Lipid Score, which is the clinical standard. We expect these machine-learning algorithms to provide the tools to implement a virtual genetic test of FH. These tools might prove particularly important for lipid clinics without access to genetic testing.

Entities:  

Keywords:  Familial hypercholesterolemia; cardiovascular disease; dyslipidemia; machine learning; prediction model

Year:  2020        PMID: 32019371     DOI: 10.1177/2047487319898951

Source DB:  PubMed          Journal:  Eur J Prev Cardiol        ISSN: 2047-4873            Impact factor:   7.804


  8 in total

1.  DNA sequencing in familial hypercholesterolaemia: the next generation.

Authors:  Julieta Lazarte; Robert A Hegele
Journal:  Eur J Prev Cardiol       Date:  2021-07-23       Impact factor: 7.804

Review 2.  Applying implementation science to improve care for familial hypercholesterolemia.

Authors:  Laney K Jones; Ross C Brownson; Marc S Williams
Journal:  Curr Opin Endocrinol Diabetes Obes       Date:  2022-04-01       Impact factor: 3.243

3.  Developing a Hybrid Risk Assessment Tool for Familial Hypercholesterolemia: A Machine Learning Study of Chinese Arteriosclerotic Cardiovascular Disease Patients.

Authors:  Lei Wang; Jian Guo; Zhuang Tian; Samuel Seery; Ye Jin; Shuyang Zhang
Journal:  Front Cardiovasc Med       Date:  2022-08-03

4.  Comparative study on the performance of different classification algorithms, combined with pre- and post-processing techniques to handle imbalanced data, in the diagnosis of adult patients with familial hypercholesterolemia.

Authors:  João Albuquerque; Ana Margarida Medeiros; Ana Catarina Alves; Mafalda Bourbon; Marília Antunes
Journal:  PLoS One       Date:  2022-06-24       Impact factor: 3.752

5.  Machine Learning Methods for Hypercholesterolemia Long-Term Risk Prediction.

Authors:  Elias Dritsas; Maria Trigka
Journal:  Sensors (Basel)       Date:  2022-07-18       Impact factor: 3.847

Review 6.  Machine Learning and the Future of Cardiovascular Care: JACC State-of-the-Art Review.

Authors:  Giorgio Quer; Ramy Arnaout; Michael Henne; Rima Arnaout
Journal:  J Am Coll Cardiol       Date:  2021-01-26       Impact factor: 24.094

7.  Acceptability, Appropriateness, and Feasibility of Automated Screening Approaches and Family Communication Methods for Identification of Familial Hypercholesterolemia: Stakeholder Engagement Results from the IMPACT-FH Study.

Authors:  Laney K Jones; Nicole Walters; Andrew Brangan; Catherine D Ahmed; Michael Gatusky; Gemme Campbell-Salome; Ilene G Ladd; Amanda Sheldon; Samuel S Gidding; Mary P McGowan; Alanna K Rahm; Amy C Sturm
Journal:  J Pers Med       Date:  2021-06-21

8.  Replacing physical with virtual genetic tests: The importance of conscious methodological decisions.

Authors:  Wouter B van Dijk; Ewoud Schuit
Journal:  Eur J Prev Cardiol       Date:  2020-03-10       Impact factor: 7.804

  8 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.