A new study has found that a machine learning model can improve the diagnosis of myocardial infarction by incorporating cardiac troponin concentrations with clinical features. Researchers at the University of Edinburgh developed machine learning models that integrated cardiac troponin concentrations at presentation or on serial testing with clinical features and computed the Collaboration for the Diagnosis and Evaluation of Acute Coronary Syndrome (CoDE-ACS) score, which identifies the probability of myocardial infarction. The models were trained on data from 10,038 patients and were validated externally using data from 10,286 patients from seven cohorts. Compared to fixed cardiac troponin thresholds, CoDE-ACS identified more patients as having a low probability of having myocardial infarction at presentation and identified fewer patients as high probability of myocardial infarction. Adopting CoDE-ACS in practice could reduce time spent in emergency departments, prevent unnecessary hospital admissions, and improve the early treatment of myocardial infarction.
The study was led by Dimitrios Doudesis, Ph.D., from the University of Edinburgh in the United Kingdom, and involved several other researchers.
The study was not associated with any particular company or organization.