Background

Instantaneous wave free ratio (iFR) does not require adenosine, but has a relatively wide intermediate range where functional assessment remains inconclusive. In this pilot study, we sought to enhance iFR through with the use of intracoronary (IC) saline (iFRs) and contrast media (iFRc) and determine whether these techniques correlated well with fractional flow reserve (FFR).

Methods

Patients with coronary artery stenosis (CAS) associated with an iFR in the intermediate zone (≥0.86 and ≤0.93) were prospectively assessed with resting distal coronary pressure/aorta pressure (Pd/Pa), iFR, iFRs, iFRc and FFR.

Results

A total of 40 coronary lesions were studied (40 patients). Pearson correlation coefficients for FFR and iFR, FFR and iFRs, FFR and iFRc were respectively: 0.57 (P=0.0002), 0.80 (P<0.0001) and 0.77 (P<0.0001). Receiver-operating characteristic (ROC) curve analysis showed similar area under the curve (AUC) of iFRs and iFR [0.90 (95% CI: 0.76-1) vs. 0.89 (95% CI: 0.79-0.99), P=0.89]. Youden's index established cut-off values of ≤0.90 for iFR (sensitivity =91%, specificity =74%) and ≤0.78 for iFRs (sensitivity =73%, specificity =100%). In contrast, the AUC of iFRc was superior to the AUC of iFR [0.99 (95% CI: 0.98-1), P=0.049]. iFRc showed excellent accuracy and established cut-off values of ≤0.81 in predicting an FFR value of ≤0.80 (sensitivity =100%, specificity =93%).

Conclusions

When iFR is in the intermediate zone, functional assessment of CAS by iFR is enhanced with the use of contrast media but not saline. This pilot study could be hypothesis generating for further study to enhance iFR specificity and sensibility.

The coronary angiogram is the gold standard for evaluating the severity of coronary artery disease stenoses. Presently, the assessment is conducted visually by cardiologists, a method that lacks standardization. This study introduces DeepCoro, a ground-breaking AI-driven pipeline that integrates advanced vessel tracking and a video-based Swin3D model that was trained and validated on a dataset comprised of 182,418 coronary angiography videos spanning 5 years. DeepCoro achieved a notable precision of 71.89% in identifying coronary artery segments and demonstrated a mean absolute error of 20.15% (95% CI: 19.88-20.40) and a classification AUROC of 0.8294 (95% CI: 0.8215-0.8373) in stenosis percentage prediction compared to traditional cardiologist assessments. When compared to two expert interventional cardiologists, DeepCoro achieved lower variability than the clinical reports (19.09%; 95% CI: 18.55-19.58 vs 21.00%; 95% CI: 20.20-21.76, respectively). In addition, DeepCoro can be fine-tuned to a different modality type. When fine-tuned on quantitative coronary angiography assessments, DeepCoro attained an even lower mean absolute error of 7.75% (95% CI: 7.37-8.07), underscoring the reduced variability inherent to this method. This study establishes DeepCoro as an innovative video-based, adaptable tool in coronary artery disease analysis, significantly enhancing the precision and reliability of stenosis assessment.