Personalized diagnosis in suspected myocardial infarction

ARTemis Investigators, Johannes T Neumann , Raphael Twerenbold , Francisco M Ojeda, Sally J. Aldous, Brandon R. Allen, Fred S Apple, Hugo Babel, Robert H. Christenson, Louise Cullen , Eleonora Di Carluccio, Dimitrios Doudesis, Ulf Ekelund, Evangelos Giannitsis, Jaimi H Greenslade, Kenji Inoue, Tomas Jernberg, Peter A Kavsak, Till Keller, Kuan Ken LeeBertil Lindahl, Thiess Lorenz, Simon Mahler, Nicholas L Mills, Arash Mokhtari, William Parsonage, John W Pickering, Christopher J Pemberton, Christoph Reichetzeder, A Mark Richards, Yader Sandoval, Martin P Than , Betül Toprak, Richard W Troughton, Andrew Worster, Tanja Zeller, Andreas Ziegler, Stefan Blankenberg

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Background. In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays.
Methods. In 2,575 patients presenting to the emergency department with suspected MI, two ensembles of machine-learning models using single or serial concentrations of six different hs cTn assays were derived to estimate the individual MI probability (ARTEMIS model). Discriminative performance of the models was assessed using area under the receiver operating characteristic curve (AUC) and logLoss. Model performance was validated in an external cohort with 1,688 patients and tested for global generalizability in 13 international cohorts with 23,411 patients.
Results. Eleven routinely available variables including age, sex, cardiovascular risk factors, electrocardiography, and hs-cTn were included in the ARTEMIS models. In the validation and generalization cohorts, excellent discriminative performance was confirmed, superior to hs-cTn only. For the serial hs-cTn measurement model, AUC ranged from 0.92-0.98. Good calibration was observed. Using a single hs-cTn measurement, the ARTEMIS model allowed direct rule-out of MI with very high and similar safety but up to tripled efficiency compared to the guideline-recommended strategy.
Conclusion. We developed and validated diagnostic models to accurately estimate the individual probability of MI, which allow for variable hs-cTn use and flexible timing of resampling. Their digital application may provide rapid, safe and efficient personalized patient care.
Original languageEnglish
JournalClinical Research in Cardiology
Publication statusPublished - 2 May 2023

Keywords / Materials (for Non-textual outputs)

  • Acute myocardial infarction
  • biomarker
  • troponin
  • machine learning
  • probability
  • super learner
  • Validation


Dive into the research topics of 'Personalized diagnosis in suspected myocardial infarction'. Together they form a unique fingerprint.

Cite this