Researchers at the University of Edinburgh built CoDE-ACS, a machine learning tool that combines a single troponin blood test with age, sex, ECG findings and medical history to estimate the probability a patient is having a heart attack.
Tested on 10,286 patients from seven cohorts, CoDE-ACS safely ruled out a heart attack in 61 percent of patients at first presentation, more than double the share identified by standard fixed-threshold testing, while keeping a negative predictive value of 99.6 percent.
Patients cleared early by the tool could in principle skip the hours of monitoring and repeat blood draws current protocols require, easing pressure on crowded emergency departments. The results come from retrospective validation across varied hospital cohorts, so prospective trials inside live emergency rooms are the next step before it changes standard practice.
Read the original study
Doudesis et al., Nature Medicine, 2023 · doi.org/10.1038/s41591-023-02325-4
One blood test cleared twice as many people.
Source
- Doudesis, D., Lee, K. K., Boeddinghaus, J., Bularga, A., Ferry, A. V., Tuck, C., Lowry, M. T. H., Lopez-Ayala, P., Nestelberger, T., Koechlin, L., Bernabeu, M. O., Neubeck, L., Anand, A., Schulz, K., Apple, F. S., Parsonage, W., Greenslade, J. H., Cullen, L., Pickering, J. W., . . . CoDE-ACS Investigators (2023). Machine learning for diagnosis of myocardial infarction using cardiac troponin concentrations. Nature Medicine, 29(5), 1201–1210. https://doi.org/10.1038/s41591-023-02325-4