Temporal Trends in Fractional Flow Reserve Use in Patients Undergoing Coronary Angiography: A Population-Based Study

Evaluation of stenoses using AI video models applied to coronary angiography

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.

Ultra-high-resolution CT vs. invasive angiography for detecting hemodynamically significant coronary artery disease: Rationale and methods of the CORE-PRECISION multicenter study

BACKGROUND

Direct coronary arterial evaluation via computed tomography (CT) angiography is the most accurate noninvasive test for the diagnosis of coronary artery disease (CAD). However, diagnostic accuracy is limited in the setting of severe coronary calcification or stents. Ultra-high-resolution CT (UHR-CT) may overcome this limitation, but no rigorous study has tested this hypothesis.

METHODS

The CORE-PRECISION is an international, multicenter, prospective diagnostic accuracy study testing the non-inferiority of UHR-CT compared to invasive coronary angiography (ICA) for identifying patients with hemodynamically significant CAD. The study will enroll 150 patients with history of CAD, defined as prior documentation of lumen obstruction, stenting, or a calcium score ≥400, who will undergo UHR-CT before clinically prompted ICA. Assessment of hemodynamically significant CAD by UHR-CT and ICA will follow clinical standards. The reference standard will be the quantitative flow ratio (QFR) with <0.8 defined as abnormal. All data will be analyzed in independent core laboratories.

RESULTS

The primary outcome will be the comparative diagnostic accuracy of UHR-CT vs. ICA for detecting hemodynamically significant CAD on a patient level. Secondary analyses will focus on vessel level diagnostic accuracy, quantitative stenosis analysis, automated contour detection, in-depth plaque analysis, and others.

CONCLUSION

CORE-PRECISION aims to investigate if UHR-CT is non-inferior to ICA for detecting hemodynamically significant CAD in high-risk patients, including those with severe coronary calcification or stents. We anticipate this study to provide valuable insights into the utility of UHR-CT in this challenging population and for its potential to establish a new standard for CAD assessment.

CathAI: fully automated coronary angiography interpretation and stenosis estimation

Coronary angiography is the primary procedure for diagnosis and management decisions in coronary artery disease (CAD), but ad-hoc visual assessment of angiograms has high variability. Here we report a fully automated approach to interpret angiographic coronary artery stenosis from standard coronary angiograms. Using 13,843 angiographic studies from 11,972 adult patients at University of California, San Francisco (UCSF), between April 1, 2008 and December 31, 2019, we train neural networks to accomplish four sequential necessary tasks for automatic coronary artery stenosis localization and estimation. Algorithms are internally validated against criterion-standard labels for each task in hold-out test datasets. Algorithms are then externally validated in real-world angiograms from the University of Ottawa Heart Institute (UOHI) and also retrained using quantitative coronary angiography (QCA) data from the Montreal Heart Institute (MHI) core lab. The CathAI system achieves state-of-the-art performance across all tasks on unselected, real-world angiograms. Positive predictive value, sensitivity and F1 score are all ≥90% to identify projection angle and ≥93% for left/right coronary artery angiogram detection. To predict obstructive CAD stenosis (≥70%), CathAI exhibits an AUC of 0.862 (95% CI: 0.843-0.880). In UOHI external validation, CathAI achieves AUC 0.869 (95% CI: 0.830-0.907) to predict obstructive CAD. In the MHI QCA dataset, CathAI achieves an AUC of 0.775 (95%. CI: 0.594-0.955) after retraining. In conclusion, multiple purpose-built neural networks can function in sequence to accomplish automated analysis of real-world angiograms, which could increase standardization and reproducibility in angiographic coronary stenosis assessment.

Vessel fractional flow reserve-based non-culprit lesion reclassification in patients with ST-segment elevation myocardial infarction: Impact on treatment strategy and clinical outcome (FAST STEMI I study)

BACKGROUND

Complete revascularization in patients with ST-segment elevation myocardial (STEMI) improves clinical outcome. Vessel fractional flow reserve (vFFR) has been validated as a non-invasive physiological technology to evaluate hemodynamic lesion significance without need for a dedicated pressure wire or hyperemic agent. This study aimed to assess discordance between vFFR reclassification and treatment strategy in intermediate non-culprit lesions of STEMI patients and to assess the clinical impact of this discordance.

METHODS

This was a single-center, retrospective cohort study. From January 2018 to December 2019, consecutive eligible STEMI patients were screened based on the presence of a non-culprit vessel with an intermediate lesion (30-80% angiographic stenosis) feasible for offline vFFR analysis. The primary outcome was the percentage of non-culprit vessels with discordance between vFFR and actual treatment strategy. The secondary outcome was two-year vessel-oriented composite endpoint (VOCE), a composite of vessel-related cardiovascular death, vessel-related myocardial infarction, and target vessel revascularization.

RESULTS

A total of 441 patients (598 non-culprit vessels) met the inclusion criteria. Median vFFR was 0.85 (0.73-0.91). Revascularization was performed in 34.4% of vessels. Discordance between vFFR and actual treatment strategy occurred in 126 (21.1%) vessels. Freedom from VOCE was higher for concordant vessels (97.5%) as compared to discordant vessels (90.6%)(p = 0.003), particularly due to higher adverse event rates in discordant vessels with a vFFR ≤0.80 but deferred revascularization.

CONCLUSIONS

In STEMI patients with multivessel disease, discordance between vFFR reclassification and treatment strategy was observed in 21.1% of non-culprit vessels with an intermediate lesion and was associated with increased vessel-related adverse events.

The Impact of Virtual Fractional Flow Reserve and Virtual Coronary Intervention on Treatment Decisions in the Cardiac Catheter Laboratory

BACKGROUND

Using fractional flow reserve (FFR) to guide percutaneous coronary intervention for patients with coronary artery disease (CAD) improves clinical decision making but remains underused. Virtual FFR (vFFR), computed from angiographic images, permits physiologic assessment without a pressure wire and can be extended to virtual coronary intervention (VCI) to facilitate treatment planning. This study investigated the effect of adding vFFR and VCI to angiography in patient assessment and management.

METHODS

Two cardiologists independently reviewed clinical data and angiograms of 50 patients undergoing invasive management of coronary syndromes, and their management plans were recorded. The vFFRs were computed and disclosed, and the cardiologists submitted revised plans. Then, using VCI, the physiologic results of various interventional strategies were shown and further revision was invited.

RESULTS

Disclosure of vFFR led to a change in strategy in 27%. VCI led to a change in stent size in 48%. Disclosure of vFFR and VCI resulted in an increase in operator confidence in their decision. Twelve cases were reviewed by 6 additional cardiologists. There was limited agreement in the management plans between cardiologists based on either angiography (kappa = 0.31) or vFFR (kappa = 0.39).

CONCLUSIONS

vFFR has the potential to alter decision making, and VCI can guide stent sizing. However, variability in management strategy remains considerable between operators, even when presented with the same anatomic and physiologic data.

Association Between Adherence to Fractional Flow Reserve Treatment Thresholds and Major Adverse Cardiac Events in Patients With Coronary Artery Disease

IMPORTANCE

Fractional flow reserve (FFR) is an invasive measurement used to assess the potential of a coronary stenosis to induce myocardial ischemia and guide decisions for percutaneous coronary intervention (PCI). It is not known whether established FFR thresholds for PCI are adhered to in routine interventional practice and whether adherence to these thresholds is associated with better clinical outcomes.

OBJECTIVE

To assess the adherence to evidence-based FFR thresholds for PCI and its association with clinical outcomes.

DESIGN, SETTING, AND PARTICIPANTS

A retrospective, multicenter, population-based cohort study of adults with coronary artery disease undergoing single-vessel FFR assessment (excluding ST-segment elevation myocardial infarction) from April 1, 2013, to March 31, 2018, in Ontario, Canada, and followed up until March 31, 2019, was conducted. Two separate cohorts were created based on FFR thresholds (≤0.80 as ischemic and >0.80 as nonischemic). Inverse probability of treatment weighting was used to account for treatment selection bias.

EXPOSURES

PCI vs no PCI.

MAIN OUTCOMES AND MEASURES

The primary outcome was major adverse cardiac events (MACE) defined by death, myocardial infarction, unstable angina, or urgent coronary revascularization.

RESULTS

There were 9106 patients (mean [SD] age, 65 [10.6] years; 35.3% female) who underwent single-vessel FFR measurement. Among 2693 patients with an ischemic FFR, 75.3% received PCI and 24.7% were treated only with medical therapy. In the ischemic FFR cohort, PCI was associated with a significantly lower rate and hazard of MACE at 5 years compared with no PCI (31.5% vs 39.1%; hazard ratio, 0.77 [95% CI, 0.63-0.94]). Among 6413 patients with a nonischemic FFR, 12.6% received PCI and 87.4% were treated with medical therapy only. PCI was associated with a significantly higher rate and hazard of MACE at 5 years compared with no PCI (33.3% vs 24.4%; HR, 1.37 [95% CI, 1.14-1.65]) in this cohort.

CONCLUSIONS AND RELEVANCE

Among patients with coronary artery disease who underwent single-vessel FFR measurement in routine clinical practice, performing PCI, compared with not performing PCI, was significantly associated with a lower rate of MACE for ischemic lesions and a higher rate of MACE for nonischemic lesions. These findings support the performance of PCI procedures according to evidence-based FFR thresholds.