AI could help identify incidental PE in conventional chest CT

TUESDAY, Aug. 2, 2022 (HealthDay News) — An artificial intelligence (AI) algorithm may help identify incidental pulmonary embolism (iPE) in conventional contrast-enhanced chest CT exams, according to a study published online July 13 in the American Journal of X-rays.

Kiran Batra, MD, of the University of Texas Southwestern Medical Center at Dallas, and colleagues examined the diagnostic performance of an AI algorithm for iPE detection in 2,555 patients with 3,003 conventional contrast-enhanced chest CT examinations performed between September 2019 and February 2020. All studies positive by AI or a natural language processing algorithm applied to the clinical reports underwent a multi-reader review process to establish a reference standard for iPE.

The researchers found that the frequency of iPE was 1.3 percent based on the review process. AI detected four iPEs that missed clinical reports, while clinical reports identified seven iPEs that were missed by AI. Compared to clinical reports, AI showed significantly lower specificity (92.7 vs. 99.8 percent) and positive predictive value (86.8 vs. 97.3 percent), but differences in sensitivity (82.5 vs. 90.0 percent) and negative predictive value (99.8 and 99.9 percent) were not significant. Neither sensitivity nor specificity varied significantly with regard to age, gender, study site, or cancer-related clinical scenario for AI.

“Potential clinical applications of the AI ​​tool include serving as a second reader to help detect additional iPEs missed by radiologists, or as a worklist triage and prioritization tool to enable earlier iPE detection and intervention,” write the authors.

Summary/Full Text (subscription or payment may be required)

Copyright © 2022 Health Day. All rights reserved.

Leave a Comment