14465
>
clinical study

Cardiac Computed Tomography Measurements in Pulmonary Embolism Associated with Clinical Deterioration

Pulmonary Embolism

Materials & Methods
This retrospective multicenter study analyzed 1,809 patients with CT-confirmed pulmonary embolism (PE) across eight emergency departments. An FDA-cleared AI algorithm (Aidoc, Tel Aviv, Israel) automatically measured right ventricle-to-left ventricle (RV/LV) ratios on CT pulmonary angiograms (CTPAs). The primary outcome was PE-related clinical deterioration; the secondary was the need for advanced interventions.

Results
AI successfully analyzed 1,660 CTPAs (97.4%) with 88% agreement with radiologists (κ = 0.36). Clinical deterioration occurred in 11.6% and advanced intervention in 19.2% of patients. Mean RV/LV ratios were higher in deteriorated patients (1.50 ± 0.39) than in stable ones (1.30 ± 0.32, p < 0.001). An AI-derived RV/LV cutoff of 1.54 predicted deterioration (OR = 2.50, 95% CI: 1.85–3.45, AUC = 0.70).

Conclusions
AI-derived CTPA cardiac measurements correlated with in-hospital deterioration and intervention needs in PE. Integrating AI-driven RV/LV analysis into PE workflows may improve early risk stratification and guide timely management.

VIEW PAPER

Explore the Latest AI Insights, Trends and Research

Follow a manual added link

Webinars

Aidoc experts, customers and industry leaders share the latest in AI benefits and adoption.

Follow a manual added link

eBooks

Explore how clinical AI can transform your health system with insights rooted in real-world experiences.

Follow a manual added link

AI Strategy

Learn how to go beyond the algorithm to develop a scalable AI strategy and implementation plan.

Follow a manual added link

Solutions

Explore how Aidoc can help increase hospital efficiency, improve outcomes and demonstrate ROI.

From Our Blog

View all

© Copyright 2026 Aidoc