14471
clinical study

Evaluation of AI-Based Detection of Incidental Pulmonary Embolism in Cardiac CT Angiography

Accuracy, Pulmonary Embolism

Materials & Methods
This retrospective single-center study evaluated an FDA-cleared AI algorithm (Aidoc, Tel Aviv, Israel) for detecting incidental pulmonary embolism (PE) in 1,534 cardiac CT angiography (CCTA) scans performed between Feb. 2021 and Feb. 2023. Radiology reports were screened using a validated natural language processing (NLP) tool, and discrepancies between AI and radiologist interpretations were reviewed by a blinded cardiothoracic radiologist.

Results
The AI algorithm identified 27 positive scans (1.8%), with 22 confirmed true positives. Among these, 10 (45.5%) were missed in the original radiology reports, all located in segmental or subsegmental arteries (p < 0.05). The AI algorithm achieved 100% sensitivity, 99.6% specificity, and 99.6% accuracy, with an F1 score of 89.8%.

Conclusions
AI-based analysis of CCTA scans demonstrated excellent accuracy in detecting incidental pulmonary emboli, uncovering nearly half of missed cases in routine reporting. These findings support the integration of AI tools into cardiac CT workflows to improve detection of clinically relevant incidental findings.

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