Related Experiment Video
Updated: Sep 19, 2025
Four-Dimensional Computed Tomography-Guided Valve Sizing for Transcatheter Pulmonary Valve Replacement
Published on: January 20, 2022
Roadmap analysis for coronary artery stenosis detection and percutaneous coronary intervention prediction in cardiac
Hidesato Fujito1, Hasan Jilaihawi2, Donghee Han3
1Department of Imaging, Medicine, and Biomedical Sciences, Cedars-Sinai Medical Center, Los Angeles, CA, United States; Department of Cardiology, Nihon University Itabashi Hospital, Tokyo, Japan.
Insights
Artificial intelligence software Roadmap shows promise as a supportive tool for CT specialists evaluating coronary artery stenosis in TAVR patients. While not sufficient alone, it enhances diagnostic accuracy and workflow efficiency with excellent negative predictive value.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Evaluating coronary artery stenosis is crucial for transcatheter aortic valve replacement (TAVR) candidates.
- Cardiac computed tomography (CT) is increasingly used for pre-procedural assessment.
- Artificial intelligence (AI) software may aid in interpreting cardiac CT findings.
Purpose of the Study:
- To assess the efficacy of AI software, Roadmap, in evaluating coronary artery stenosis for TAVR.
- To compare the diagnostic performance of Roadmap alone, CT specialists alone, and CT specialists using Roadmap.
- To determine the ability of these methods to predict obstructive coronary artery disease (CAD) and the need for percutaneous coronary intervention (PCI).
Main Methods:
- Consecutive TAVR candidates undergoing cardiac CT angiography (CTA) and invasive coronary angiography were enrolled.
- Three methods were evaluated: Roadmap AI software, CT specialists with Roadmap, and CT specialists alone.
- Obstructive CAD was defined as ≥50% stenosis on quantitative coronary angiography (QCA).
Main Results:
- AI software Roadmap alone had a low positive predictive value (PPV) for stenosis and PCI prediction.
- CT specialists, with or without Roadmap, demonstrated high diagnostic accuracy (AUC) for stenosis prediction.
- CT specialists using Roadmap showed excellent negative predictive value (NPV) for stenosis (97%) and comparable NPV to QCA for PCI prediction.
Conclusions:
- Roadmap AI software alone is insufficient for clinical decision-making due to low PPV.
- Roadmap can function as a "second observer" for CT specialists, improving workflow efficiency.
- The AI tool aids in flagging lesions, maintaining high diagnostic accuracy and excellent NPV.
Background:
The new artificial intelligence-based software, Roadmap (HeartFlow), may assist in evaluating coronary artery stenosis during cardiac computed tomography (CT) for transcatheter aortic valve replacement (TAVR).
Methods:
Consecutive TAVR candidates who underwent both cardiac CT angiography (CTA) and invasive coronary angiography were enrolled. We evaluated the ability of three methods to predict obstructive coronary artery disease (CAD), defined as ≥50 % stenosis on quantitative coronary angiography (QCA), and the need for percutaneous coronary intervention (PCI) within one year: Roadmap, clinician CT specialists with Roadmap, and CT specialists alone.
Results:
The area under the curve (AUC) for predicting QCA ≥50 % stenosis was similar for CT specialists with or without Roadmap (0.93 [0.85-0.97] vs. 0.94 [0.88-0.98], p = 0.82), both significantly higher than Roadmap alone (all p < 0.05). For PCI prediction, no significant differences were found between QCA and CT specialists, with or without Roadmap, while Roadmap's AUC was lower (all p < 0.05). The negative predictive value (NPV) of CT specialists with Roadmap for ≥50 % stenosis was 97 %, and for PCI prediction, the NPV was comparable to QCA (p = 1.00). In contrast, the positive predictive value (PPV) of Roadmap alone for ≥50 % stenosis was 49 %, the lowest among all approaches, with a similar trend observed for PCI prediction.
Conclusions:
While Roadmap alone is insufficient for clinical decision-making due to low PPV, Roadmap may serve as a "second observer", providing a supportive tool for CT specialists by flagging lesions for careful review, thereby enhancing workflow efficiency and maintaining high diagnostic accuracy with excellent NPV.
More Related Videos
Related Concept Videos
01:28Imaging Studies for Cardiovascular System V: CT
01:25Imaging Studies for Cardiovascular System VI: Calcium -Scoring CT
01:30Acute Coronary Syndrome III: Diagnostic Studies
01:27Coronary Artery Disease V: Interprofessional Care
01:28Cardiac Catheterization I: Pre-Procedure Overview