Stroke care may shift with Mount Sinai AI model

New York City-based Mount Sinai Health System has developed an artificial intelligence model that helps determine which atrial fibrillation patients benefit from blood thinners to prevent stroke. 

The model was trained on EHRs from 1.8 million patients across 21 million visits, 82 million notes and 1.2 billion data points, according to a Sept. 1 news release. It was internally validated on 38,642 Mount Sinai patients and externally validated on 12,817 patients from Stanford (Calif.) University datasets.

Researchers said the AI tool accurately assessed stroke and bleeding risks at the individual level and recommended against anticoagulation in up to 50% of patients who would otherwise have received it under current guidelines. These findings suggest a potential shift toward more personalized, risk-balanced decision-making in AF care.

The post Stroke care may shift with Mount Sinai AI model appeared first on Becker’s Hospital Review | Healthcare News & Analysis.