Validating Artificial Intelligence Guidance for Ultrasound Acquisition and Remote Interpretation
Authors
Affiliations (1)
Affiliations (1)
- NYU Langone Health
Abstract
Diagnostic pathways for deep vein thrombosis (DVT) requiring ultrasound are limited by availability and prolonged time-to-imaging. This multicenter, double-blinded, prospective, nonrandomized study evaluated the performance of an AI-guidance system (ThinkSono Guidance, ThinkSono, GmbH) enabling non-ultrasound-trained operators to acquire proximal lower extremity compression ultrasounds for remote clinician interpretation. Patients underwent AI-guided ultrasound(s) and imaging specialist-performed ultrasound(s). Primary and secondary endpoints were image quality, sensitivity/specificity for proximal DVT, and prioritization specificity (effectiveness in identifying patients requiring further ultrasound after AI-guided scan). Of 634 recruited subjects, 594 subjects (700 scans) with 67 DVTs were analyzed. 86.83% of AI-guided scans achieved diagnostic image quality; triage sensitivity was 92.86%, triage specificity 39.12%, prioritization specificity 97.96%. Imaging specialist-performed ultrasounds could be avoided in 35.32% of patients. Median AI-guided scan and review time was 7.57 minutes. These findings suggest AI-guided, clinician-reviewed ultrasound may be a scalable triage strategy to expand DVT evaluation access, particularly in resource-constrained and after-hours settings.