| 1. |
|
|
| 2. |
- Escaned, Javier, et al.
(författare)
-
Applied coronary physiology for planning and guidance of percutaneous coronary interventions. A clinical consensus statement from the European Association of Percutaneous Cardiovascular Interventions (EAPCI) of the European Society of Cardiology
- 2023
-
Ingår i: EuroIntervention. - : Europa Digital & Publishing. - 1774-024X .- 1969-6213. ; 19:6, s. 464-
-
Tidskriftsartikel (refereegranskat)abstract
- The clinical value of fractional flow reserve and non-hyperaemic pressure ratios are well established in determining an indication for percutaneous coronary intervention (PCI) in patients with coronary artery disease (CAD). In addition, over the last 5 years we have witnessed a shift towards the use of physio-logy to enhance procedural planning, assess post-PCI functional results, and guide PCI optimisation. In this regard, clinical studies have reported compelling data supporting the use of longitudinal vessel analysis, obtained with pressure guidewire pullbacks, to better understand how obstructive CAD contributes to myocardial ischaemia, to establish the likelihood of functionally successful PCI, to identify the presence and location of residual flow-limiting stenoses and to predict long-term outcomes. The introduction of new functional coronary angiography tools, which merge angiographic information with fluid dynamic equations to deliver information equivalent to intracoronary pressure measurements, are now available and potentially also applicable to these endeavours. Furthermore, the ability of longitudinal vessel analysis to predict the functional results of stenting has played an integral role in the evolving field of simulated PCI. Nevertheless, it is important to have an awareness of the value and challenges of physiology-guided PCI in specific clinical and anatomical contexts. The main aim of this European Association of Percutaneous Cardiovascular Interventions clinical consensus statement is to offer up-to-date evidence and expert opin-ion on the use of applied coronary physiology for procedural PCI planning, disease pattern recognition and post-PCI optimisation.
|
|
| 3. |
- Mamas, Mamas A., et al.
(författare)
-
Predicting target lesion failure following percutaneous coronary intervention through machine learning risk assessment models
- 2023
-
Ingår i: The European Heart Journal - Digital Health. - : Oxford University Press. - 2634-3916. ; 4:6, s. 433-443
-
Tidskriftsartikel (refereegranskat)abstract
- 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.
|
|
