Objectives: To assess the prevalence of reported and unreported incidental pulmonary embolism (iPE) in patients with cancer, and to evaluate an artificial intelligence (AI) algorithm for automatic detection of iPE.
Methods: Retrospective cohort study on patients with cancer with an elective CT study including the chest between 2018-07-01 and 2019-06-30. All study reports and images were reviewed to identify reported and unreported iPE and were processed by the AI algorithm.
Results: One thousand sixty-nine patients (1892 studies) were included. Per study, iPE was present in 75 studies (4.0%), of which 16 (21.3%) were reported. Unreported iPE had a significantly lower number of involved vessels compared to reported iPE, with a median of 2 (interquartile range, IQR, 1-4) versus 5 (IQR 3-9.75), p < 0.001. There were no significant differences in age, cancer type, or attenuation of the main pulmonary artery. The AI algorithm correctly identified 68 of 75 iPE, with 3 false positives (sensitivity 90.7%, specificity 99.8%, PPV 95.6%, NPV 99.6%). False negatives occurred in cases with 1-3 involved vessels. Of the unreported iPE, 32/59 (54.2%) were proximal to the subsegmental arteries.
Conclusion: In patients with cancer, the prevalence of iPE was 4.0%, of which only 21% were reported. Greater than 50% of unreported iPE were proximal to the subsegmental arteries. The AI algorithm had a very high sensitivity and specificity with only three false positives, with the potential to increase the detection rate of iPE.
Key points: • 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 a very high sensitivity and specificity, so has the potential to increase the detection rate of iPE.
Keywords: Artificial intelligence; Neoplasms; Pulmonary embolism; Retrospective studies; Venous thromboembolism.
© 2022. The Author(s).