Research Article | DOI: https://doi.org/-

Early Prediction of Subclinical Cardiac Dysfunction Using Integrated Biomarker and AI-Based Risk Modelling: A Prospective Cohort Study

Early Prediction of Subclinical Cardiac Dysfunction Using Integrated Biomarker and AI-Based Risk Modelling: A Prospective Cohort Study

  • Dr. Alexander Hughes *

Department of Cardiovascular Medicine, University of Oxford, United Kingdom

*Corresponding Author: Dr. Alexander Hughes

Citation: Alexander Hughes, Department of Cardiovascular Medicine, University of Oxford, United Kingdom, Journal of Cardiology and Cardiovascular Diseases, ACP Publishers, 1(1)

Copyright : © Alexander Hughes, this is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited

Received: 10 September 2026 | Accepted: 10 September 2026 | Published: 18 September 2026

Keywords: Cardiology, artificial intelligence, biomarkers, cardiovascular disease, early diagnosis, predictive modelling, heart dysfunction

Dr. Early Prediction of Subclinical Cardiac Dysfunction Using Integrated Biomarker and AI-Based Risk Modelling: A Prospective Cohort Study

Early detection of subclinical cardiac dysfunction remains a major challenge in preventive cardiology. This study aimed to evaluate the effectiveness of an integrated model combining circulating biomarkers and artificial intelligence (AI)-based predictive analytics in identifying individuals at risk of developing cardiovascular disease (CVD). A prospective cohort of 1,200 asymptomatic adults was followed over a period of three years. Biomarkers including high-sensitivity troponin, NT-pro BNP, and inflammatory markers were analysed alongside clinical and lifestyle variables. Machine learning algorithms were applied to develop a predictive model. The integrated approach demonstrated significantly higher predictive accuracy compared to traditional risk assessment tools. These findings highlight the potential of combining biological and computational methods for early cardiovascular risk stratification

Keywords:
Cardiology, artificial intelligence, biomarkers, cardiovascular disease, early diagnosis, predictive modelling, heart dysfunction

References

1. World Health Organization. (2023). Cardiovascular diseases (CVDs).
📘 View at Publisher 🎓 View at Google Scholar
1. Braunwald E. Heart disease: a textbook of cardiovascular medicine. 2020.
📘 View at Publisher 🎓 View at Google Scholar
1.   Libby P. Inflammation in atherosclerosis. (2021). Nature.
📘 View at Publisher 🎓 View at Google Scholar
1. McCarthy CP et al. (2019). High-sensitivity troponin in clinical practice. JAMA.
📘 View at Publisher 🎓 View at Google Scholar
1.    Yancy CW et al. (2017). Heart failure guidelines. Circulation.
📘 View at Publisher 🎓 View at Google Scholar
1. Krittanawong C et al. (2020). AI in cardiovascular medicine. Eur Heart J.
📘 View at Publisher 🎓 View at Google Scholar
1.    Deo RC. (2015). Machine learning in medicine. Circulation.
📘 View at Publisher 🎓 View at Google Scholar
1. Topol EJ. (2019). Deep medicine: AI in healthcare. Nat Med.
📘 View at Publisher 🎓 View at Google Scholar
1. Omland T et al. (2018). NT-proBNP in risk prediction. J Am Coll Cardiology.
📘 View at Publisher 🎓 View at Google Scholar
1. Attia ZI et al. (2019). AI-enabled ECG analysis. Lancet.
📘 View at Publisher 🎓 View at Google Scholar
Share this
Submit Research Paper Join as Reviewer
Article Access
Download View
41 Views