Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr 2;149(14):1090-1101.
doi: 10.1161/CIRCULATIONAHA.123.066917. Epub 2024 Feb 12.

Machine Learning for Myocardial Infarction Compared With Guideline-Recommended Diagnostic Pathways

Jasper Boeddinghaus #  1   2 , Dimitrios Doudesis #  2   3 , Pedro Lopez-Ayala #  1 , Kuan Ken Lee  2   3 , Luca Koechlin  1   4 , Karin Wildi  1   5 , Thomas Nestelberger  1 , Raphael Borer  1 , Òscar Miró  6 , F Javier Martin-Sanchez  7 , Ivo Strebel  1 , Maria Rubini Giménez  1 , Dagmar I Keller  8 , Michael Christ  9 , Anda Bularga  2 , Ziwen Li  2 , Amy V Ferry  2 , Chris Tuck  2 , Atul Anand  2 , Alasdair Gray  3   10 , Nicholas L Mills #  2   3 , Christian Mueller #  1 ; CoDE-ACS and APACE Investigators
Collaborators, Affiliations

Machine Learning for Myocardial Infarction Compared With Guideline-Recommended Diagnostic Pathways

Jasper Boeddinghaus et al. Circulation. .

Abstract

Background: Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome (CoDE-ACS) is a validated clinical decision support tool that uses machine learning with or without serial cardiac troponin measurements at a flexible time point to calculate the probability of myocardial infarction (MI). How CoDE-ACS performs at different time points for serial measurement and compares with guideline-recommended diagnostic pathways that rely on fixed thresholds and time points is uncertain.

Methods: Patients with possible MI without ST-segment-elevation were enrolled at 12 sites in 5 countries and underwent serial high-sensitivity cardiac troponin I concentration measurement at 0, 1, and 2 hours. Diagnostic performance of the CoDE-ACS model at each time point was determined for index type 1 MI and the effectiveness of previously validated low- and high-probability scores compared with guideline-recommended European Society of Cardiology (ESC) 0/1-hour, ESC 0/2-hour, and High-STEACS (High-Sensitivity Troponin in the Evaluation of Patients With Suspected Acute Coronary Syndrome) pathways.

Results: In total, 4105 patients (mean age, 61 years [interquartile range, 50-74]; 32% women) were included, among whom 575 (14%) had type 1 MI. At presentation, CoDE-ACS identified 56% of patients as low probability, with a negative predictive value and sensitivity of 99.7% (95% CI, 99.5%-99.9%) and 99.0% (98.6%-99.2%), ruling out more patients than the ESC 0-hour and High-STEACS (25% and 35%) pathways. Incorporating a second cardiac troponin measurement, CoDE-ACS identified 65% or 68% of patients as low probability at 1 or 2 hours, for an identical negative predictive value of 99.7% (99.5%-99.9%); 19% or 18% as high probability, with a positive predictive value of 64.9% (63.5%-66.4%) and 68.8% (67.3%-70.1%); and 16% or 14% as intermediate probability. In comparison, after serial measurements, the ESC 0/1-hour, ESC 0/2-hour, and High-STEACS pathways identified 49%, 53%, and 71% of patients as low risk, with a negative predictive value of 100% (99.9%-100%), 100% (99.9%-100%), and 99.7% (99.5%-99.8%); and 20%, 19%, or 29% as high risk, with a positive predictive value of 61.5% (60.0%-63.0%), 65.8% (64.3%-67.2%), and 48.3% (46.8%-49.8%), resulting in 31%, 28%, or 0%, who require further observation in the emergency department, respectively.

Conclusions: CoDE-ACS performs consistently irrespective of the timing of serial cardiac troponin measurement, identifying more patients as low probability with comparable performance to guideline-recommended pathways for MI. Whether care guided by probabilities can improve the early diagnosis of MI requires prospective evaluation.

Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT00470587.

Keywords: machine learning; myocardial infarction; troponin.

PubMed Disclaimer

Conflict of interest statement

Disclosures Dr Boeddinghaus has received honoraria from Siemens, Roche Diagnostics, Ortho Clinical Diagnostics, Quidel Corporation, and Beckman Coulter, and travel support from Medtronic, all outside the submitted work. Dr Lopez-Ayala has received speaker honoraria or consultancy from Quidel, paid to the institution, outside the submitted work. Dr Lee has received honoraria from Abbott Diagnostics, outside the submitted work. Dr Koechlin received a research grant from the University of Basel, the Swiss Heart Foundation, the SAMW, and the Freiwillige Akademische Gesellschaft, as well as speaker honoraria from Roche Diagnostics, Siemens Healthineers, and Abbott Diagnostics, outside the submitted work. Dr Wildi has received research support from the Wesley Research Institute, the University of Queensland, Brisbane, Australia, and the University of Basel. Dr Nestelberger has received research support from the Swiss National Science Foundation (grant P400PM_191037/1), the Prof Dr Max Cloëtta Foundation, the Margarete und Walter Lichtenstein-Stiftung (grant 3MS1038), and the University Hospital Basel, as well as speaker or consulting honoraria from Siemens, Beckman Coulter, Bayer, Ortho Clinical Diagnostics, and Orion Pharma, outside the submitted work. Dr Mills has received research grants to the University of Edinburgh and honoraria or consultancy from Abbott Diagnostics, Roche Diagnostics, Siemens Healthineers, and LumiraDx. Dr Mueller has received research support from Abbott Diagnostics, Beckman Coulter, bioMérieux, Idorsia, Novartis, Ortho Clinical Diagnostics, Quidel, Roche, Siemens, Singulex, and Sphingotec, as well as speaker honoraria or consulting honoraria from Acon, Amgen, Astra Zeneca, Boehringer Ingelheim, Bayer, BMS, Idorsia, Novartis, Osler, Roche, and Sanofi, outside of the submitted work. The cardiac troponin assay was donated by Abbott Diagnostics, which had no role in the study design, data analysis, manuscript preparation, or the decision to submit the manuscript for publication. Drs Mills, Boeddinghaus, Doudesis, Lee, Bularga, Ferry, Tuck, Anand, and Gray are employees of the University of Edinburgh, which has filed for a patent on the CoDE-ACS algorithm. The other authors have reported no relationships relevant to the contents of this article to disclose.

Publication types

Associated data