Artificial intelligence in cardiac metabolism: the next frontier in cardiovascular health

Abstract

In this article, we aim to explore the rapidly developing role of artificial intelligence (AI) in cardiac metabolism research, highlighting its impact on biomarker discovery, precision medicine, and patient stratification. Cardiac metabolism, a key determinant of cardiovascular health, is often disrupted in cardiovascular diseases (CVDs) like heart failure and coronary artery disease. AI’s ability to process and analyze large-scale data offers new chances for understanding and addressing these metabolic dysfunctions. By integrating up-to-date technologies with molecular and clinical insights, AI enables the achievement of personalized treatments, more accurate diagnostics, and the discovery of potential novel therapeutic targets. The main challenges include ethical concerns around data privacy, algorithmic bias, and the need for representative datasets. Future directions focus on developing transparent, accountable, and collaborative AI models that integrate data and enable real-time monitoring, ensuring fairness and accessibility in healthcare. As AI continues to evolve, its role in advancing cardiovascular care is expected to grow, offering new trends in cardiovascular research.

Keywords

Artificial intelligence / cardiac metabolism / cardiovascular disease

References

[1] Haug CJ.Artificial intelligence and machine learning in clinical medicine, 2023.N Engl J Med2023;388:1201-8

[2] Takada S,Furihata T.Succinyl-CoA-based energy metabolism dysfunction in chronic heart failure.Proc Natl Acad Sci U S A2022;119:e2203628119 PMCID:PMC9564216

[3] Talmor-Barkan Y,Shaul AA.Metabolomic and microbiome profiling reveals personalized risk factors for coronary artery disease.Nat Med2022;28:295-302

[4] Xu Y,Liang Y.An atlas of genetic scores to predict multi-omic traits.Nature2023;616:123-31 PMCID:PMC10323211

[5] Poss AM,Cox JE.Machine learning reveals serum sphingolipids as cholesterol-independent biomarkers of coronary artery disease.J Clin Invest2020;130:1363-76 PMCID:PMC7269567

[6] Chen AT,Zhang J.Explainable machine learning and online calculators to predict heart failure mortality in intensive care units.ESC Heart Fail2024;Online ahead of print:

[7] Lee AM, Hu J, Xu Y, et al; CKD Biomarkers Consortium. Using machine learning to identify metabolomic signatures of pediatric chronic kidney disease etiology. J Am Soc Nephrol. 2022;33:375-86. PMCID:PMC8819986

[8] Shen X,Liang N.Serum metabolomics identifies dysregulated pathways and potential metabolic biomarkers for hyperuricemia and gout.Arthritis Rheumatol2021;73:1738-48

[9] Krittanawong C,Wang Z,Kitai T.Artificial intelligence in precision cardiovascular medicine.J Am Coll Cardiol2017;69:2657-64

[10] Michelhaugh SA.Using artificial intelligence to better predict and develop biomarkers.Heart Fail Clin2022;18:275-85

[11] Antoniades C,Vavlukis M.Perivascular adipose tissue as a source of therapeutic targets and clinical biomarkers.Eur Heart J2023;44:3827-44 PMCID:PMC10568001

[12] Pan J,Neubauer S.Phenotyping heart failure by cardiac magnetic resonance imaging of cardiac macro- and microscopic structure: state of the art review.Eur Heart J Cardiovasc Imaging2023;24:1302-17 PMCID:PMC10531211

[13] Jin X,Yin H.Identification of potential targets of stress cardiomyopathy by a machine learning algorithm.CVIA2024;9:27

[14] Zhou J,Bai J.Machine learning methods in real-world studies of cardiovascular disease.CVIA2023;7:25