eduzhai > Applied Sciences > Engineering >

Artificial Intelligence to Assist in Exclusion of Coronary Atherosclerosis during CCTA Evaluation of Chest-Pain in the Emergency Department Preparing an Application for Real-World Use

  • king
  • (0) Download
  • 20210506
  • Save

... pages left unread,continue reading

Document pages: 13 pages

Abstract: Coronary Computed Tomography Angiography (CCTA) evaluation of chest-painpatients in an Emergency Department (ED) is considered appropriate. While anegative CCTA interpretation supports direct patient discharge from an ED,labor-intensive analyses are required, with accuracy in jeopardy fromdistractions. We describe the development of an Artificial Intelligence (AI)algorithm and workflow for assisting interpreting physicians in CCTA screeningfor the absence of coronary atherosclerosis. The two-phase approach consistedof (1) Phase 1 - focused on the development and preliminary testing of analgorithm for vessel-centerline extraction classification in a balanced studypopulation (n = 500 with 50 disease prevalence) derived by retrospectiverandom case selection; and (2) Phase 2 - concerned with simulated-clinicalTrialing of the developed algorithm on a per-case basis in a more real-worldstudy population (n = 100 with 28 disease prevalence) from an ED chest-painseries. This allowed pre-deployment evaluation of the AI-based CCTA screeningapplication which provides a vessel-by-vessel graphic display of algorithminference results integrated into a clinically capable viewer. Algorithmperformance evaluation used Area Under the Receiver-Operating-CharacteristicCurve (AUC-ROC); confusion matrices reflected ground-truth vs AIdeterminations. The vessel-based algorithm demonstrated strong performance withAUC-ROC = 0.96. In both Phase 1 and Phase 2, independent of disease prevalencedifferences, negative predictive values at the case level were very high at95 . The rate of completion of the algorithm workflow process (96 withinference results in 55-80 seconds) in Phase 2 depended on adequate imagequality. There is potential for this AI application to assist in CCTAinterpretation to help extricate atherosclerosis from chest-pain presentations.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×