Differentiating Type 1 and Type 2 myocardial infarction using a machine learning algorithm and biomarkers
Adding NT-proBNP and Gal-3 to the MI<sup>3</sup> machine learning algorithm shows promise in differentiating type 1 from type 2 MI.
Authors
- Simon A. Mahler (ORCID: https://orcid.org/0000-0003-2199-4078)
- Anna C. Snavely (ORCID: https://orcid.org/0000-0001-6916-4255)
- Chadwick D. Miller (ORCID: https://orcid.org/0000-0002-4362-4409)
- Christian J. Hunter (ORCID: https://orcid.org/0000-0003-4744-463X)
- Robert H. Christenson (ORCID: https://orcid.org/0000-0003-2612-9083)
- Laurel Jackson (ORCID: https://orcid.org/0000-0002-0491-9079)
- Jason P. Stopyra (ORCID: https://orcid.org/0000-0001-7457-3969)
- Michael Supples (ORCID: https://orcid.org/0000-0001-5999-4554)
- Gillian Murtagh (ORCID: https://orcid.org/0009-0001-4900-3080)
- Nicklaus P. Ashburn (ORCID: https://orcid.org/0000-0002-3466-8813)
Institutions
- University of Maryland, Baltimore (US)
- Abbott Fund (US)
- Wake Forest University (US)
Publication Details
- Journal
- The American Journal of Emergency Medicine
- Published
- 2025-08-11
- DOI
- https://doi.org/10.1016/j.ajem.2025.08.019
- Citations
- 2
- Primary Topic
- Cardiovascular Function and Risk Factors
- Type
- article
- Field-Weighted Citation Impact
- 2.78
Funders
- Abbott Laboratories
- National Heart, Lung, and Blood Institute