Coronary Physiology Instantaneous Wave-Free Ratio (iFR) Derived From X-Ray Angiography Using Artificial Intelligence Deep Learning Models: A Pilot Study
See where this sits in the topic map →Summary AI-generated
- TL;DR
- This study explores using artificial intelligence instead of traditional dynamic fluid computational algorithms to simplify and increase the usage of coronary physiology methods derived from coronary angiography.
- Problem
- Current coronary angiography-derived physiology methods rely mostly on dynamic fluid computational algorithms, leaving alternative approaches based on artificial intelligence largely unexplored.
- Method
- Using data from consecutive patients undergoing invasive instantaneous wave-free ratio (iFR) measurements, the researchers developed three AI models to classify target lesions as positive (iFR ≤ 0.89) or negative (iFR > 0.89) and compared the predictions to true measurements.
- Results
- Across 250 measurements, performance varied by model and target vessel. Model 3 showed the best overall performance with 69% accuracy, 88% negative predictive value (NPV), 44% positive predictive value (PPV), 74% sensitivity, and 67% specificity, while vessel-specific evaluations showed that models achieved consistently high NPVs (such as 97% for the right coronary artery) alongside modest or low PPVs.
- Contributions
- Not specified in the abstract.
- Limitations
- Not specified in the abstract.
- Takeaways
- This pilot study demonstrates a successful proof of concept for estimating binary iFR from coronary angiography images using AI. Despite modest overall accuracy, the consistently high negative predictive value could help patients avoid further invasive procedures.
- Applications
- Clinical decision support systems in cardiology to help avoid further invasive maneuvers after coronary angiography.
- Topics
- Coronary Physiology, Instantaneous Wave-Free Ratio, Artificial Intelligence, Deep Learning, X-Ray Angiography
- For industry
- Healthcare and Clinical Diagnostics
- Why it matters
- Provides a proof of concept for AI-driven coronary physiology estimation that could simplify procedures and reduce the need for further invasive measurements.
Abstract
OBJECTIVES: Coronary angiography (CAG)-derived physiology methods have been developed in an attempt to simplify and increase the usage of coronary physiology, based mostly on dynamic fluid computational algorithms. We aimed to develop a different approach based on artificial intelligence methods, which has seldom been explored. METHODS: Consecutive patients undergoing invasive instantaneous free-wave ratio (iFR) measurements were included. We developed artificial intelligence (AI) models capable of classifying target lesions as positive (iFR ≤ 0.89) or negative (iFR > 0.89). The predictions were then compared to the true measurements. RESULTS: Two hundred-fifty measurements were included, and 3 models were developed. Model 3 had the best overall performance: accuracy, negative predictive value (NPV), positive predictive value (PPV), sensitivity, and specificity were 69%, 88%, 44%, 74%, and 67%, respectively. Performance differed per target vessel. For the left anterior descending artery (LAD), model 3 had the highest accuracy (66%), while model 2 the highest NPV (86%) and sensitivity (91%). PPV was always low/modest. Model 1 had the highest specificity (68%). For the right coronary artery, model 1's accuracy was 86%, NPV was 97%, and specificity was 87%, but all models had low PPV (maximum 25%) and low/modest sensitivity (maximum 60%). For the circumflex, model 1 performed best: accuracy, NPV, PPV, sensitivity, and specificity were 69%, 96%, 24%, 80%, and 68%, respectively. CONCLUSIONS: We developed 3 AI models capable of binary iFR estimation from CAG images. Despite modest accuracy, the consistently high NPV is of potential clinical significance, as it would enable avoiding further invasive maneuvers after CAG. This pivotal study offers proof of concept for further development.