2025_01
Multicenter Double-Blind Study Evaluating AI-Driven Detection of Proximal Deep Vein Thrombosis.
Curry et al.
https://ai.nejm.org/doi/full/10.1056/AIoa2400741?query=ai_wu#ap3
Highlights
This prospective, double-blind, test accuracy study was designed to test whether an artificial intelligence (AI)–guided software device (AutoDVT) could support nonradiology specialists to diagnose proximal DVT. The negative predictive value for AutoDVT was 95% (95% CI, 92 to 98%), with a positive predictive value of 28% (95% CI, 19 to 40%). Though AI-guided ultrasound use can detect proximal DVT, test accuracy was not sufficient for this device to be used safely.