Application of a machine learning-driven, multibiomarker panel for prediction of incident cardiovascular events in patients with suspected myocardial infarction

Biomark Med. 2020 Jun;14(9):775-784. doi: 10.2217/bmm-2019-0584. Epub 2020 May 28.

Abstract

Background: In patients with suspected myocardial infarction (MI), we sought to validate a machine learning-driven, multibiomarker panel for prediction of incident major adverse cardiovascular events (MACE). Methodology & results: A previously described prognostic panel for MACE consisting of four biomarkers was measured in 748 patients with suspected MI. The investigated end point was incident MACE within 1 year. The prognostic value of a continuous score and an optimal cut-off was investigated. The area under the curve was 0.86 for the overall model. Using the optimal cut-off resulted in a negative predictive value of 99.4% for incident MACE. Patients with an elevated prognostic score were at high risk for MACE. Conclusion: Among patients with suspected MI, we validated a multibiomarker panel for predicting 1-year MACE. Clinical Trial Registration: NCT02355457 (ClinicalTrials.gov).

Keywords: ACS; artificial intelligence; biomarkers; machine learning; major adverse cardiac events; myocardial infarction; noninvasive risk assessment; outcome; prediction.

Publication types

  • Clinical Trial

MeSH terms

  • Aged
  • Biomarkers* / blood
  • Cardiovascular Diseases / diagnosis
  • Female
  • Humans
  • Machine Learning*
  • Male
  • Middle Aged
  • Myocardial Infarction* / blood
  • Myocardial Infarction* / diagnosis
  • Prognosis

Substances

  • Biomarkers

Associated data

  • ClinicalTrials.gov/NCT02355457