Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Research Briefing
  • Published:

Improving the diagnosis of myocardial infarction with machine learning

Machine learning models that integrate cardiac troponin concentrations and clinical features to compute the probability of myocardial infarction outperform current care pathways that use fixed troponin thresholds or risk scores. Adoption of these models could reduce inequalities, prevent unnecessary admissions, and accelerate the diagnosis and treatment of patients with myocardial infarction.

This is a preview of subscription content, access via your institution

Access options

Buy this article

Prices may be subject to local taxes which are calculated during checkout

Fig. 1: External validation of the performance of CoDE-ACS in 10,286 patients with possible myocardial infarction.

References

  1. Thygesen, K. et al. Fourth universal definition of myocardial infarction. Circulation 138, e618–e651 (2018). An international consensus statement that provides recommendations for the diagnosis of myocardial infarction.

    Article  PubMed  Google Scholar 

  2. Lowry, M. T. H., Anand, A. & Mills, N. L. Implementing an early rule-out pathway for acute myocardial infarction in clinical practice. Heart 107, 1912–1919 (2021). A review that describes the strengths and limitations of current diagnostic pathways used in clinical practice.

    Article  PubMed  Google Scholar 

  3. Shah, A. S. V. et al. High-sensitivity troponin in the evaluation of patients with suspected acute coronary syndrome: a stepped-wedge, cluster-randomised controlled trial. Lancet 392, 919–928 (2018). An article that presents findings from a randomized trial of patients with possible myocardial infarction evaluated before and after implementation of high-sensitivity cardiac troponin testing.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  4. Anand, A. et al. High-sensitivity cardiac troponin on presentation to rule out myocardial infarction: a stepped-wedge cluster randomized controlled trial. Circulation 143, 2214–2224 (2021). An article that describes the performance of current guideline recommended pathways for patients with possible myocardial infarction.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  5. Lee, K. K. et al. Development and validation of a decision support tool for the diagnosis of acute heart failure: systematic review, meta-analysis, and modelling study. Br. Med. J. 377, e068424 (2022). An article that presents findings from a meta-analysis and modeling study using natriuretic peptides for the diagnosis of acute heart failure.

    Article  Google Scholar 

Download references

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

This is a summary of: Doudesis, D. et al. Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations. Nat. Med. https://doi.org/10.1038/s41591-023-02325-4 (2023).

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Improving the diagnosis of myocardial infarction with machine learning. Nat Med 29, 1070–1071 (2023). https://doi.org/10.1038/s41591-023-02331-6

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1038/s41591-023-02331-6

Search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing