Key result
Vessel-based AI mildly outperforms humans in iFR classification, achieving 72% accuracy with higher LAD NPV.
Why the study?
Invasive coronary physiology is underused and carries risks and costs, and non-invasive derivation via AI—particularly for iFR—has seldom been explored or compared with human performance.
Does a deep learning artificial intelligence model improve the accuracy of binary iFR lesion classification from invasive coronary angiography compared to human operators in patients undergoing CAG and iFR?
Observational (n=250)
No
Does a deep learning artificial intelligence model improve the accuracy of binary iFR lesion classification from invasive coronary angiography compared to human operators in patients undergoing CAG and iFR?
A novel deep learning AI model can non-invasively derive binary iFR from coronary angiography with high negative predictive value, mildly outperforming experienced interventional cardiologists.
May support AI-assisted iFR estimation from angiography; leaves open prospective validation before clinical adoption.
Invasive coronary physiology is underused and carries risks/costs. Artificial Intelligence (AI) might enable non-invasive physiology from invasive coronary angiography (CAG), possibly outperforming humans, but has seldom been explored, especially for instantaneous wave-free Ratio (iFR). We aimed to develop binary iFR lesion classification AI models and compare them with human performance. single-center retrospective study of patients undergoing CAG and iFR. A validated encoder-decoder convolutional neural network (CNN) performed segmentation. Manual annotation of target vessel and pressure sensor location on a segmented telediastolic frame followed. Three AI models classified lesions as positive (≤ 0.89) or negative (> 0.89). Model 1 uses preprocessed vessel diameters with a transformer. Models 2/3 are EfficientNet-B5 CNNs using concatenated angiography and segmentation - Model 3 employs class-frequency-weighted Cross-Entropy Loss. Previous findings demonstrated Model 3's superiority for left anterior descending (LAD) and Model 1's for circumflex (Cx)/right coronary artery (RCA) - they were therefore unified into a vessel-based model. Ten-fold patient-level cross-validation enabled full sample training/testing. Three experienced operators performed binary iFR classification using single frames of raw/segmented images. Comparison metrics were accuracy, sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV). Across 250 measurements, AI accuracy was 72%, PPV 48%, NPV 90%, sensitivity 77%, and specificity 71%. Human accuracy ranged from 54 to 74%. NPV was high for the Cx/RCA (AI: 96/98%; operators: 94/97%), but AI significantly outperformed humans in the LAD (78% vs. 60-64%). An AI model capable of binary iFR lesions classification mildly outperformed interventional cardiologists, supporting further validation studies.
No takes yet. Share an insight, caveat, or question.
Oliveira et al. (2025) conducted an observational in Coronary artery disease requiring invasive coronary angiography and iFR (n=250). Vessel-based AI model for binary iFR lesion classification vs. Human operators (experienced interventional cardiologists) was evaluated on Accuracy of binary iFR lesion classification. A vessel-based AI model for binary iFR lesion classification achieved 72% accuracy, mildly outperforming human operators (54-74% accuracy), with significantly higher NPV in the LAD (78% vs 60-64%).
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: