Abstract
Pulmonary embolism (PE) is a common emergency department (ED) diagnosis with a greater than 4% mortality rate, resulting in frequent over-testing via computed tomography PE (CT-PE) and exposing patients to the harms of ionizing radiation, iodinated contrasts, and increased costs. Clinical decision rules incorporating D-dimer testing are used to identify patients whose PE risk is below a CT-PE imaging threshold, but are subject to high rates of false positives and inconsistent use. We hypothesized that an artificial intelligence (AI) algorithm would augment existing D-dimer-based risk stratification and identify patients who are unlikely to benefit from imaging.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have