New research suggests the Viz Aortic Dissection Algorithm has a 94.2 percent sensitivity rate for detecting aortic dissection on computed tomography (CT) angiography.
Acute aortic dissection is reportedly misdiagnosed in 57 to 85 percent of cases with a mortality rate approaching 50 percent within 48 hours of onset.1 However, emerging research, presented at the recent VEITHSymposium, suggests the use of artificial intelligence (AI) algorithm may enhance the detection of aortic dissection on computed tomography (CT) angiography.
In a retrospective review of 1,303 chest and thoraco-abdominal CT angiography scans, researchers compared the Viz Aortic Dissection Algorithm (Viz.ai), a deep learning, AI-based software application, to ground truth consensus of three board-certified radiologists. According to the study, the data set was comprised of 137 CT angiography exams positive for aortic dissection and 1,166 dissection-negative exams.2
The study authors found that the Viz Aortic Dissection Algorithm had a 94.2 percent sensitivity rate and a 97.3 percent specificity rate. The algorithm also had a positive predictive value of 80.1 percent and a negative predictive value of 99.3 percent, according to the research.2
The researchers suggested the algorithm could enhance patient triage with earlier diagnosis and accelerated care coordination possibly leading to more timely interventions and improved outcomes.
“The application of this aortic algorithm into the workflow has the potential to move the needle for care teams treating this deadly disease,” noted study co-author Peter D. Chang, M.D., co-director of the Center for Artificial Intelligence in Diagnostic Medicine at the University of California-Irvine (UC-Irvine).
References
1. Levy D, Goyal A, Grigorova Y, Farci F, Le JK. Aortic Dissection. StatPearls. Available at: https://www.ncbi.nlm.nih.gov/books/NBK441963/ . Updated May 2, 2022. Accessed November 21, 2022.
2. Viz.ai. Viz.ai announces positive new data from large aortic dissection AI real-world study at the 2022 VEITHSymposium. Business Wire. Available at: https://www.businesswire.com/news/home/20221118005105/en/Viz.ai%E2%84%A2-Announces-Positive-New-Data-From-Large-Aortic-Dissection-AI-Real-World-Study-at-the-2022-VEITHsymposium%E2%84%A2 . Published November 18, 2022. Accessed November 23, 2022.
CT Study: AI Algorithm Comparable to Radiologists in Differentiating Small Renal Masses
May 14th 2024An emerging deep learning algorithm had a lower AUC and sensitivity than urological radiologists for differentiating between small renal masses on computed tomography (CT) scans but had a 21 percent higher sensitivity rate than non-urological radiologists, according to new research.
What a New Meta-Analysis Reveals About Fractional Flow Reserve Assessment with Computed Tomography
May 13th 2024While acknowledging variable accuracy overall with CT-derived fractional flow reserve (FFR-CT) values, researchers found that the accuracy rate increased to 90 percent for FFR-CT values greater > 0.90 and < 0.49.
MRI-Based Deep Learning Algorithm Shows Comparable Detection of csPCa to Radiologists
May 8th 2024In a study involving over 1,000 visible prostate lesions on biparametric MRI, a deep learning algorithm detected 96 percent of clinically significant prostate cancer (csPCa) in comparison to a 98 percent detection rate for an expert genitourinary radiologist.