Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models.

Aims: Central to the practice of precision medicine in percutaneous coronary intervention (PCI) is a risk-stratification tool to predict outcomes following the procedure. This study is intended to assess machine learning (ML)-based risk models to predict clinically relevant outcomes in PCI and to support individualized clinical decision-making in this setting. Methods and results: Five different ML models [gradient boosting classifier (GBC), linear discrimination analysis, Naïve Bayes, logistic regression, and K-nearest neighbours algorithm) for the prediction of 1-year target lesion failure (TLF) were trained on an extensive data set of 35 389 patients undergoing PCI and enrolled in the global, all-comers e-ULTIMASTER registry. The data set was split into a training (80%) and a test set (20%). Twenty-three patient and procedural characteristics were used as predictive variables. The models were compared for discrimination according to the area under the receiver operating characteristic curve (AUC) and for calibration. The GBC model showed the best discriminative ability with an AUC of 0.72 (95% confidence interval 0.69-0.75) for 1-year TLF on the test set. The discriminative ability of the GBC model for the components of TLF was highest for cardiac death with an AUC of 0.82, followed by target vessel myocardial infarction with an AUC of 0.75 and clinically driven target lesion revascularization with an AUC of 0.68. The calibration was fair until the highest risk deciles showed an underestimation of the risk. Conclusion: Machine learning-derived predictive models provide a reasonably accurate prediction of 1-year TLF in patients undergoing PCI. A prospective evaluation of the predictive score is warranted. Registration: Clinicaltrial.gov identifier is NCT02188355.

Complexity assessment and technical aspect of coronary angiogram and percutaneous coronary intervention following transcatheter aortic valve implantation.

BACKGROUND: Performing selective coronary angiogram (CA) and percutaneous coronary intervention (PCI) post transcatheter aortic valve implantation (TAVI) may be challenging with various success rates of coronary ostia engagement. METHODS: Among all patients who underwent CA and/or PCI after TAVI from our single center TAVI registry, ostia cannulation success was reported according to the quality of ostia engagement and artery opacification, and was classified as either selective, partially selective or non-selective but sufficient for diagnosis. RESULTS: Among the 424 consecutive TAVI procedures performed at the aforementioned institution, 20 (4.7%) CA were performed in 19 (4.5%) patients at a median time of 464 days post TAVI (25-75% IQ: 213-634 days). CA were performed in 7 CoreValve, 9 Evolut R, 1 Evolut PRO and 2 Edwards Sapien 3 devices. Transradial vascular approach was attempted in 9 procedures (45%, right n = 6 and left n = 3) and was successful in 8 (40%) patients. A total of 20 left main artery ostium cannulation were attempted leading to a diagnostic CA in all of them with selective engagement in 65%. Engagement of the right coronary artery in 2 out of 15 attempted cases failed due to a low ostium in conjunction with a high implantation of a CoreValve prosthesis. 11 PCI (55% of CA) including 2 left main lesions were performed. In 4 patients (36.4% of the PCI), an extension catheter was required to engage the left main. All planned PCI were successful. CONCLUSIONS: Post TAVI CA and PCI are challenging but feasible even after supra-annular self-expandable valve implantation.

Discordance in the diagnostic assessment of vulnerable plaques between radiofrequency intravascular ultrasound versus optical coherence tomography among patients with acute myocardial infarction: insights from the IBIS-4 study.

We aimed to evaluate the diagnostic agreement between radiofrequency (RF) intravascular ultrasound (IVUS) and optical coherence tomography (OCT) for thin-cap fibroatheroma (TCFA) in non-infarct-related coronary arteries (non-IRA) in patients with ST-segment elevation myocardial infarction (STEMI). In the Integrated Biomarker Imaging Study (IBIS-4), 103 STEMI patients underwent OCT and RF-IVUS imaging of non-IRA after successful primary percutaneous coronary intervention and at 13-month follow-up. A coronary lesion was defined as a segment with ≥ 3 consecutive frames (≈1.2 mm) with plaque burden ≥ 40% as assessed by grayscale IVUS. RF-IVUS-derived TCFA was defined as a lesion with > 10% confluent necrotic core abutting to the lumen in > 10% of the circumference. OCT-TCFA was defined by a minimum cap thickness < 65 µm. The two modalities were matched based on anatomical landmarks using a dedicated matching software. Using grayscale IVUS, we identified 276 lesions at baseline (N = 146) and follow-up (N = 130). Using RF-IVUS, 208 lesions (75.4%) were classified as TCFA. Among them, OCT identified 14 (6.7%) TCFA, 60 (28.8%) thick-cap fibroatheroma (ThCFA), and 134 (64.4%) non-fibroatheroma. All OCT-TCFA (n = 14) were confirmed as RF-TCFA. The concordance rate between RF-IVUS and OCT for TCFA diagnosis was 29.7%. The reasons for discordance were: OCT-ThCFA (25.8%); OCT-fibrous plaque (34.0%); attenuation due to calcium (23.2%); attenuation due to macrophage (10.3%); no significant attenuation (6.7%). There was a notable discordance in the diagnostic assessment of TCFA between RF-IVUS and OCT. The majority of RF-derived TCFA were not categorized as fibroatheroma using OCT, while all OCT-TCFA were classified as TCFA by RF-IVUS.ClinicalTrials.gov Identifier NCT00962416.

Starting a carotid artery stenting program is safe.

BACKGROUND: Little is known on the performance of newly initiated carotid artery stenting (CAS) programs. The safety of the procedure is being questioned following the publication of the EVA-3S trial, a study criticized for the limited interventional experience required to enroll patients. METHODS: Within a newly started academic CAS program, patient data and outcomes were collected prospectively. The outcomes of the first 100 consecutive patients treated are reported. A CAS-fellowship-trained interventionalist was involved in all procedures. All patients underwent clinical assessment by a neurologist before and after the procedure, and serial ECG and cardiac enzymes were routinely obtained. Primary outcome measures included 30-day major adverse events (MAE), defined as death, stroke, or myocardial infarction, while on follow-up deaths and ipsilateral strokes were added. RESULTS: Between July 2003 and November 2006, 92 patients had a single internal carotid artery treated, while 7 underwent staged bilateral CAS. In one patient, the procedure was aborted prior to lesion treatment. The 30-day MAE rate per procedure was 1.9% (one major and one minor stroke). By a mean follow-up of 16 months (range 2-42 months), one patient had died of refractory heart failure, while one patient had a minor ipsilateral stroke and three had minor contralateral strokes, corresponding to total MAE per patient of 4%. The rate of any stroke or death was 7%. The rate of restenosis >or=50% per lesion by ultrasound was 3.8%. CONCLUSION: This single center experience suggests that it is safe to start a CAS program following dedicated fellowship.

Current strategies with high-dose tirofiban.

The glycoprotein (GP) IIb/IIIa receptor is a platelet-specific adhesion receptor that mediates the formation of platelet aggregates. Pharmacologic blockade of the receptor is associated with a reduction in major cardiovascular adverse events after percutaneous coronary interventions and in the setting of acute coronary syndromes. Three intravenous GP IIb/IIIa receptor inhibitors are available: abciximab, tirofiban and eptifibatide. Tirofiban is a small, synthetic non-peptide, competitive GP IIb/IIIa antagonist with high specificity and high affinity for the GP IIb/IIIa receptor. In a head-to-head comparison, tirofiban 10-microg/kg bolus followed by a 0.15-microg/kg/min infusion was found to be inferior to standard dose of abciximab in patients undergoing percutaneous coronary intervention. Insufficient platelet inhibition with low-dose tirofiban may likely explain these results. Subsequently, a high-bolus dose of tirofiban (25 microg/kg bolus) followed by standard infusion was tested and evidence suggest that in this dosing tirofiban may be as effective as abciximab and have a comparable safety profile. Therefore, high-bolus dose tirofiban may be an appealing and cost-effective alternative to abciximab. However, further testing is warranted given the short follow up and limited statistical power of the available data.

Novel doppler assessment of intracoronary volumetric flow reserve: validation against PET in patients with or without flow-dependent vasodilation.

UNLABELLED: Volumetric blood flow (Q) determination requires simultaneous assessment of mean blood flow velocity and vessel cross-sectional area. At present, no method provides both values. Intracoronary Doppler-based assessment of coronary flow velocity reserve (CFVR) relies on average peak velocity (APV). Because this does not account for changes in velocity profile or vessel area usually occurring with flow-dependent vasodilation, results can be misleading. The aim of this clinical study was to validate against the current gold standard (measurement of myocardial perfusion reserve [MPR] by PET) a new, Doppler-based method for calculating coronary Q and coronary flow reserve (CFR). METHODS: Doppler-based intracoronary Q was measured with a proprietary guidewire device in a nonstenotic coronary artery at baseline and during adenosine-induced hyperemic flow (140 mug/kg/min intravenously during 7 min). Three gate positions were assessed, of which 2 were lying within the vessel and 1 was intersecting the vessel. The zeroth (M(0)) and the first (M(1)) Doppler moments of the intersecting gate were used to calculate mean blood flow velocity (M(1)/M(0)) and vessel area (M(0)), and M(0) of the 2 proximal gates was used to correct for scattering and attenuation. CFR was calculated as hyperemic/resting flow with Q and compared with APV-derived CFVR and with the corresponding segmental MPR obtained with (15)O-labeled water and PET. RESULTS: Q (CFR, 2.60 +/- 1.07) correlated well with PET (MPR, 2.58 +/- 1.11) (r = 0.832, P < 0.005; Bland-Altman limits, -1.42 to 1.09), whereas CFVR did not (r = 0.09, P = not statistically significant; Bland-Altman limits, -3.36 to 2.24). However, in vessels without dilation, there was no difference between CFR, CFVR, and MPR. CONCLUSION: This procedure for intracoronary Q measurement using the proprietary Doppler guidewire system, which accounts for both changes in flow profile and changes in vessel area, allows invasive, accurate assessment of CFR even in the presence of flow-dependent vasodilation.