Materials & Methods
A retrospective cohort study assessing the prevalence of reported and unreported incidental pulmonary embolism (iPE) in patients with cancer were identified through automatic detection with an AI algorithm. All patients with cancer with an elective CT (chest and/or abdo) study, including the chest, between July 1, 2018 to June 30, 2019 were included and study reports and images were reviewed and processed by the AI algorithm.
Results
1,892 CT studies were included. Per study, iPE was present in 4.0% of the oncology population. 80% miss rate (53/65) showed a >400% enhanced detection rate by AI (53/12). Of those 58% (31/53) of the misses where lobar or segmental and 59% (13/22) of the subsegmental findings involved multiple vessels (i.e.: higher clinical significance than a solitary sub-seg finding). The sensitivity 90.7%, specificity 99.8%, PPV 95.6%, NPV 99.6%.
Conclusions
In a retrospective single-center study on patients with cancer, unreported iPE were common, with the majority lying proximal to the subsegmental arteries. The evaluated AI algorithm had very high sensitivity and specificity, so it has the potential to increase the detection rate of iPE.
Aidoc experts, customers and industry leaders share the latest in AI benefits and adoption.
Explore how clinical AI can transform your health system with insights rooted in real-world experiences.
Learn how to go beyond the algorithm to develop a scalable AI strategy and implementation plan.
Explore how Aidoc can help increase hospital efficiency, improve outcomes and demonstrate ROI.
