This article on the use of an artificial intelligence alert system is not new but it was mentioned during the recent European Society of Cardiology CRT – Cardiovascular Round Table – on the them of AI in cardiovascular care, which took place on March 26-27, 2025 (link)
The primary clinical hypothesis of this randomised controlled trial was that the artificial intelligence electrocardiogram would identify human-unrecognized deteriorating signs and prompt early intervention to reduce mortality.
The study involved 39 physicians and 15,965 patients across multiple sites. When physicians received artificial intelligence-generated warnings about patients predicted to have high mortality risk, all-cause 90-day mortality decreased significantly from 4.3% (control) to 3.6% (intervention), with a hazard ratio of 0.83. The mortality reduction was most pronounced in patients with high-risk ECGs (HR = 0.69). Notably, in the high-risk group, cardiac death risk dropped dramatically from 2.4% to 0.2% (HR = 0.07). Patients flagged as high-risk received increased intensive care compared to controls.
The authors say that the study demonstrates that artificial intelligence-electrocardiogram alerts can effectively identify vulnerable patients, enabling timely interventions that reduce mortality, though the exact mechanisms require further investigation.
Read more at this link on Nature Medicine
Citation
Lin, CS., Liu, WT., Tsai, DJ. et al. AI-enabled electrocardiography alert intervention and all-cause mortality: a pragmatic randomized clinical trial. Nat Med 30, 1461–1470 (2024). https://doi.org/10.1038/s41591-024-02961-4