ABSTRACT
Coronary artery disease is defined by the existence of atherosclerotic plaque on the arterial wall, which can cause blood flow impairment, or plaque rupture, and ultimately lead to myocardial ischemia. Intravascular ultrasound (IVUS) imaging can provide a detailed characterization of lumen and vessel features, and so plaque burden, in coronary vessels. Prediction of the regions in a vascular segment where plaque burden can either increase (progression) or decrease (regression) following a certain therapy, has remained an elusive major milestone in cardiology. Studies like IBIS-4 showed an association between plaque burden regression and high-intensity rosuvastatin therapy over 13 months. Nevertheless, it has not been possible to predict if a patient would respond in a favorable/adverse fashion to such a treatment. This work aims to (i) Develop a framework that processes lumen and vessel cross-sectional contours and extracts geometric descriptors from baseline and follow-up IVUS pullbacks; and to (ii) Develop, train, and validate a machine learning model based on baseline/follow-up IVUS datasets that predicts future percent of atheroma volume changes in coronary vascular segments using only baseline information, i.e. geometric features and clinical data. This is a post hoc analysis, revisiting the IBIS-4 study. We employed 140 arteries, from 81 patients, for which expert delineation of lumen and vessel contours were available at baseline and 13-month follow-up. Contour data from baseline and follow-up pullbacks were co-registered and then processed to extract several frame-wise features, e.g. areas, plaque burden, eccentricity, etc. Each pullback was divided into regions of interest (ROIs), following different criteria. Frame-wise features were condensed into region-wise markers using tools from statistics, signal processing, and information theory. Finally, a stratified 5-fold cross-validation strategy (20 repetitions) was used to train/validate an XGBoost regression models. A feature selection method before the model training was also applied. When the models were trained/validated on ROI defined by the difference between follow-up and baseline plaque burden, the average accuracy and Mathews correlation coefficient were 0.70 and 0.41 respectively. Using a ROI partition criterion based only on the baseline's plaque burden resulted in averages of 0.60 accuracy and 0.23 Mathews correlation coefficient. An XGBoost model was capable of predicting plaque progression/regression changes in coronary vascular segments of patients treated with rosuvastatin therapy in 13 months. The proposed method, first of its kind, successfully managed to address the problem of stratification of patients at risk of coronary plaque progression, using IVUS images and standard patient clinical data.
Subject(s)
Coronary Artery Disease , Plaque, Atherosclerotic , Humans , Plaque, Atherosclerotic/diagnostic imaging , Rosuvastatin Calcium/therapeutic use , Cross-Sectional Studies , Ultrasonography, Interventional/methods , Coronary Artery Disease/diagnostic imaging , Coronary Artery Disease/drug therapy , Coronary Vessels/diagnostic imagingABSTRACT
Cardiac allograft vasculopathy (CAV) is a significant determinant of long-term survival in heart transplant recipients. Standard CAV screening typically utilizes invasive coronary angiography (ICA). Quantitative flow ratio (QFR) is a computational method for functional testing of coronary stenosis, and may add diagnostic value to ICA in assessing CAV. Consecutive subjects who received heart transplantation and underwent two separate routine coronary angiograms between January 2013 and April 2016 were enrolled. Coronary angiograms and IVUS were performed per local protocol at 1, 2, 3 and 5 years post-transplant. QFR was calculated offline. CAV was assessed semi-quantitively based on coronary angiogram results. Twenty-two patients were enrolled. Mean time from transplant to first included ICA was 2.1 years. QFR in at least 1 coronary vessel was interpretable in 19/22 (86%) of initial ICA (QFR1). QFR1 correlated well with the CAV score derived from the second ICA (CAV2) with a clustering of CAV at lower QFR values. In a receiver-operating characteristic (ROC) analysis, an optimal QFR threshold of 0.88 yielded 0.94 sensitivity and 0.67 specificity (AUC of 0.79) for at least non-obstructive subsequent CAV. Initial angiographically and intravascular ultrasound derived CAV severity poorly predicted subsequent CAV severity. QFR derived from invasive coronary angiography predicts subsequent development of CAV more accurately than angiography and intravascular ultrasound. This novel method of coronary flow assessment in recipients of heart transplantation may be useful to diagnose and predict subsequent CAV development.
Subject(s)
Coronary Artery Disease , Heart Transplantation , Humans , Coronary Angiography/methods , Predictive Value of Tests , Heart Transplantation/adverse effects , Heart , Allografts/blood supply , Coronary Artery Disease/diagnostic imaging , Coronary Artery Disease/etiology , Coronary Artery Disease/therapyABSTRACT
BACKGROUND: Hemoglobin (Hgb) drop without bleeding is common among patients undergoing transcatheter aortic valve replacement; however, the clinical implications of significant Hgb drop have not been fully evaluated. METHODS AND RESULTS: Consecutive patients undergoing transcatheter aortic valve replacement at our institution from 2011 to 2021 were retrospectively reviewed. Three groups were assessed: no Hgb drop and no bleed (NoD-NoB [reference group]), Hgb drop with bleed, and Hgb drop and no bleed (D-NoB). Hgb drop was defined as ≥3 g/dL decrease from pre- to post-transcatheter aortic valve replacement. Outcomes of interest were in-hospital death and 1-year all-cause mortality. A total of 1851 cases with complete Hgb data were included: NoD-NoB: n=1579 (85.3%); D-NoB: n=49 (2.6%); Hgb drop with bleed: n=223 (12.6%). Compared with NoD-NoB, the D-NoB group was older (81.1 versus 78.9 years of age) with higher preprocedure Hgb (12.9 versus 11.7 g/dL). In-hospital death rate was higher among patients with D-NoB versus NoD-NoB (4.5% versus 0.8%, P<0.001) and similar to Hgb drop with bleed (4.5% versus 4.1%, P=0.999). Predictors of in-hospital death were D-NoB (odds ratio [OR], 3.45 [95% CI, 1.32-8.69]) and transfusion (OR, 10.6 [95% CI, 4.25-28.2]). Landmark survival analysis found that D-NoB experienced 1-year mortality rate comparable to NoD-NoB, whereas Hgb drop with bleed had higher midterm mortality (hazard ratio [HR], 3.2 [95% CI, 1.83-5.73]), and transfusion continued to impact mortality (HR, 2.5 [95% CI, 1.79-3.63]). CONCLUSIONS: Hgb drop without bleeding is common among patients undergoing transcatheter aortic valve replacement and may represent a higher risk of periprocedural death. Blood transfusion increases short- and midterm mortality risk in patients with and without bleeding, supporting a restrictive transfusion strategy.
Subject(s)
Aortic Valve Stenosis , Hemoglobins , Hospital Mortality , Transcatheter Aortic Valve Replacement , Humans , Transcatheter Aortic Valve Replacement/adverse effects , Transcatheter Aortic Valve Replacement/mortality , Male , Female , Aged, 80 and over , Aged , Retrospective Studies , Hemoglobins/metabolism , Hemoglobins/analysis , Aortic Valve Stenosis/surgery , Aortic Valve Stenosis/mortality , Risk Factors , Treatment Outcome , Risk Assessment/methodsABSTRACT
BACKGROUND: Coronary microvascular dysfunction (CMD) is a prevalent condition among patients with cardiovascular risk factors, leading to a reduced quality of life and an increased risk of major adverse cardiovascular events. Novel invasive techniques have emerged to more accurately diagnose CMD. However, CMD's natural history remains poorly understood due to limited data. To address this knowledge gap, the Coronary Microvascular Disease Registry (CMDR) was established with the primary aim of standardizing comprehensive coronary functional testing and understanding of CMD. DESIGN: CMDR is a prospective, multicenter registry enrolling an unlimited number of consecutive subjects who undergo comprehensive invasive hemodynamic assessment of the entire coronary arterial vasculature. Patients undergoing acetylcholine provocation test for coronary vasospasm will also be included. Follow-up assessments will be conducted at 30 days and annually for up to 5 years. The primary endpoint is Canadian Cardiovascular Society angina grade over time. Secondary endpoints, including all-cause mortality, cardiovascular death, acute myocardial infarction, stroke, hospitalizations, medication changes, and subsequent coronary interventions, will be analyzed to establish long-term safety and clinical outcomes in patients undergoing invasive CMD assessment. SUMMARY: CMDR aims to characterize the clinical and physiologic profile of patients undergoing comprehensive invasive coronary functional testing, simultaneously providing crucial longitudinal information on the natural history and outcomes of these patients. This will shed light on CMD's course and clinical implications, which, in turn, holds the potential to significantly improve diagnostic and treatment strategies for CMD patients, ultimately leading to the enhancement of their overall prognosis and quality of life. CLINICAL TRIAL REGISTRATION: clinicaltrials.gov, NCT05960474.
ABSTRACT
BACKGROUND: patients with atrial fibrillation (AF) under treatment with chronic oral anticoagulation (OAC) often require coronary angiography with or without percutaneous coronary intervention (PCI). Deciding the management of OAC during this periprocedural period requires balancing the risks of hemorrhage and thrombotic complications. Guidelines recommend an uninterrupted strategy in patients receiving Vitamin-K Antagonists (VKA). However, for patients undergoing coronary angiography or PCI while on direct oral anticoagulants (DOACs), withdrawal 12-24 h prior to the procedure is still recommended. This is based on expert opinions given the lack of evidence. Therefore, whether DOAC discontinuation prior to trans-radial coronary procedures should be the strategy of choice is a matter of debate and solid evidence is needed to guide clinical decision making. METHODS: The DOAC-NOSTOP study is a prospective, single-arm, open-label study evaluating the safety of DOACs continuation in 200 patients undergoing transradial percutaneous coronary procedures. DOAC treatment will not be interrupted throughout the periprocedural period. Primary outcome will be Bleeding Academic Research Consortium (BARC) type 2, 3, or 5 events, assessed at a 30-day follow-up. CONCLUSIONS: The DOAC-NOSTOP is the first study prospectively assessing the risk of bleeding with uninterrupted DOAC in patients undergoing trans-radial percutaneous coronary procedures.
Subject(s)
Atrial Fibrillation , Drug Administration Schedule , Hemorrhage , Percutaneous Coronary Intervention , Radial Artery , Humans , Percutaneous Coronary Intervention/adverse effects , Prospective Studies , Radial Artery/diagnostic imaging , Hemorrhage/chemically induced , Administration, Oral , Time Factors , Treatment Outcome , Risk Factors , Risk Assessment , Atrial Fibrillation/therapy , Atrial Fibrillation/diagnosis , Atrial Fibrillation/complications , Factor Xa Inhibitors/administration & dosage , Factor Xa Inhibitors/adverse effects , Coronary Angiography/adverse effects , Anticoagulants/administration & dosage , Anticoagulants/adverse effects , Catheterization, Peripheral/adverse effects , PuncturesABSTRACT
Spontaneous coronary artery dissection (SCAD) is a rare cause of ST-segment elevation myocardial infarction (STEMI), predominantly affecting women. Because primary percutaneous coronary intervention (PPCI) is reserved for a select group of patients, vulnerable and minority patients may experience delays in appropriate management and adverse outcomes. We examined the racial differences in the outcomes for patients with SCAD who underwent PPCI for STEMI. Records of patients aged ≥18 years who underwent PPCI for SCAD-related STEMI between 2016 and 2020 were identified from the National Inpatient Sample database. Clinical, socioeconomic, and hospital characteristics were compared between non-White and White patients. Weighted multivariate analysis assessed the association of race with inpatient mortality, length of stay (LOS), and hospitalization costs. The total weighted estimate of patients with SCAD-STEMI who underwent PPCI was 4,945, constituting 25% non-White patients. Non-White patients were younger (56 vs 60.7 years, p <0.001); had a higher prevalence of diabetes, acute renal failure, and obesity; and were more likely to be uninsured and be in the lowest income group. Inpatient mortality (7.7% vs 8.4%, p = 0.74) and hospitalization costs ($34,213 vs $31,858, p = 0.27) were similar for non-White and White patients, and the adjusted analysis did not show any association between the patients' race and inpatient mortality (odds ratio 0.60, 95% confidence interval [CI] 0.32 to 1.13, p = 0.11) or hospitalization costs (ß [ß coefficient]: 215, 95% CI -4,193 to 4,623, p >0.90). Similarly, there was no association between the patients' race and LOS (incident rate ratio 1.20, 95% CI 1.00 to 1.45, p = 0.054). The weighted multivariate analysis showed that age; clinical co-morbidities such as diabetes, acute renal failure, valvular dysfunction, and obesity; low-income status; and hospitalization in the western region were associated with adverse outcomes. In conclusion, our study does not show any differences in inpatient mortality, LOS, and hospitalization costs between non-White and White patients who underwent PPCI for SCAD-related STEMI.
Subject(s)
Coronary Vessel Anomalies , Hospital Mortality , Percutaneous Coronary Intervention , ST Elevation Myocardial Infarction , Humans , Female , Male , Middle Aged , Percutaneous Coronary Intervention/statistics & numerical data , ST Elevation Myocardial Infarction/surgery , ST Elevation Myocardial Infarction/epidemiology , Coronary Vessel Anomalies/complications , Coronary Vessel Anomalies/epidemiology , Coronary Vessel Anomalies/surgery , United States/epidemiology , Vascular Diseases/epidemiology , Vascular Diseases/congenital , Vascular Diseases/surgery , Length of Stay/statistics & numerical data , Aged , Healthcare Disparities/statistics & numerical data , Hospital Costs/statistics & numerical data , Retrospective Studies , Acute Kidney Injury/epidemiology , Acute Kidney Injury/etiologyABSTRACT
In the original publication [...].
ABSTRACT
In current clinical practice, qualitative or semi-quantitative measures are primarily used to report coronary artery disease on cardiac CT. With advancements in cardiac CT technology and automated post-processing tools, quantitative measures of coronary disease severity have become more broadly available. Quantitative coronary CT angiography has great potential value for clinical management of patients, but also for research. This document aims to provide definitions and standards for the performance and reporting of quantitative measures of coronary artery disease by cardiac CT.
ABSTRACT
Many lesions in patients undergoing percutaneous coronary intervention (PCI) exhibit significant calcification. Several techniques have been developed to improve outcomes in this setting. However, their impact on coronary microcirculation remains unknown. The aim of this study is to evaluate the influence of plaque modification techniques on coronary microcirculation across patients with severely calcified coronary artery disease. In this multicenter retrospective study, consecutive patients undergoing PCI with either Rotablation (RA) or Shockwave-intravascular-lithotripsy (IVL) were included. Primary endpoint was the impairment of coronary microvascular resistances assessed by Δ angiography-derived index of microvascular resistance (ΔIMRangio) which was defined as the difference in IMRangio value post- and pre-PCI. Secondary endpoints included the development of peri procedural PCI complications (flow-limiting coronary dissection, slow-flow/no reflow during PCI, coronary perforation, branch occlusion, failed PCI, stroke and shock developed during PCI) and 12-month follow-up adverse events. 162 patients were included in the analysis. Almost 80% of patients were male and the left descending anterior artery was the most common treated vessel. Both RA and IVL led to an increase in ΔIMRangio (22.3 and 10.3; p = 0.038, respectively). A significantly higher rate of PCI complications was observed in patients with ΔIMRangio above the median of the cohort (21.0% vs. 6.2%; p = 0.006). PCI with RA was independently associated with higher ΔIMRangio values (OR 2.01, 95% CI: 1.01-4.03; p = 0.048). Plaque modification with IVL and RA during PCI increases microvascular resistance. Evaluating the microcirculatory status in this setting might help to predict clinical and procedural outcomes and to optimize clinical results.
ABSTRACT
Coronary atherosclerosis remains a leading cause of morbidity and mortality worldwide. The underlying pathophysiology includes a complex interplay of endothelial dysfunction, lipid accumulation and inflammatory pathways. Multiple structural and inflammatory features of the atherosclerotic lesions have become targets to identify high-risk lesions. Various intracoronary imaging devices have been developed to assess the morphological, biocompositional and molecular profile of the intracoronary atheromata. These techniques guide interventional and therapeutical management and allow the identification and stratification of atherosclerotic lesions. We sought to provide an overview of the inflammatory pathobiology of atherosclerosis, distinct high-risk plaque features and the ability to visualize this process with contemporary intracoronary imaging techniques.
ABSTRACT
BACKGROUND: Recent randomized studies have broadened the indication of transcatheter aortic valve replacement (TAVR) to also include low-surgical-risk patients. However, the data on self-expanding (SE) and balloon-expandable (BE) valves in low-risk patients remain sparse. METHODS: The current study is a post hoc analysis of combined data from both LRT 1.0 and 2.0 trials comparing BE and SE transcatheter heart valves. RESULTS: A total of 294 patients received a BE valve, and 102 patients received an SE valve. The 30-day clinical outcomes were similar across both groups except for stroke (4.9% vs. 0.7%, p = 0.014) and permanent pacemaker implantation (17.8% vs. 5.8%, p < 0.001), which were higher in the SE cohort than the BE cohort. No difference was observed in terms of paravalvular leak (≥moderate) between the groups (0% vs. 1.5%, p = 0.577). SE patients had higher aortic valve area (1.92 ± 0.43 mm2 vs. 1.69 ± 0.45 mm2, p < 0.001) and lower mean gradient (8.93 ± 3.53 mmHg vs. 13.41 ± 4.73 mmHg, p < 0.001) than BE patients. In addition, the rate of subclinical leaflet thrombosis was significantly lower in SE patients (5.6% vs. 13.8%, p = 0.038). CONCLUSION: In this non-randomized study assessing SE and BE valves in low-risk TAVR patients, SE valves are associated with better hemodynamics and lesser leaflet thrombosis, with increased rates of stroke and permanent pacemaker implantation at 30 days; however, this could be due to certain patient-dependent factors not fully evaluated in this study. The long-term implications of these outcomes on structural valve durability remain to be further investigated. CLINICAL TRIAL REGISTRY: LRT 1.0: NCT02628899 LRT 2.0: NCT03557242.
Subject(s)
Aortic Valve Stenosis , Heart Valve Prosthesis , Stroke , Thrombosis , Transcatheter Aortic Valve Replacement , Humans , Transcatheter Aortic Valve Replacement/adverse effects , Aortic Valve/diagnostic imaging , Aortic Valve/surgery , Aortic Valve Stenosis/diagnosis , Aortic Valve Stenosis/surgery , Aortic Valve Stenosis/etiology , Stroke/etiology , Thrombosis/etiology , Treatment Outcome , Prosthesis Design , Risk FactorsABSTRACT
BACKGROUND: Patients with ST-segment-elevation myocardial infarction but no coronary microvascular injury are at low risk of early cardiovascular complications (ECC). We aim to assess whether nonhyperemic angiography-derived index of microcirculatory resistance (NH-IMRangio) could be a user-friendly tool to identify patients at low risk of ECC, potentially candidates for expedited care pathway and early hospital discharge. METHODS: Retrospective analysis of 2 independent, international, prospective, observational cohorts included 568 patients with ST-segment-elevation myocardial infarction. NH-IMRangio was calculated based on standard coronary angiographic views with 3-dimensional-modeling and computational analysis of the coronary flow. RESULTS: Overall, ECC (a composite of cardiovascular death, cardiogenic shock, acute heart failure, life-threatening arrhythmias, resuscitated cardiac arrest, left ventricular thrombus, post-ST-segment-elevation myocardial infarction mechanical complications, and rehospitalization for acute heart failure or acute myocardial infarction at 30 days follow-up), occurred in 54 (9.3%) patients. NH-IMRangio was significantly correlated with pressure/thermodilution-based index of microcirculatory resistance (r=0.607; P<0.0001) and demonstrated good accuracy in predicting ECC (area under the curve, 0.766 [95% CI, 0.706-0.827]; P<0.0001). Importantly, ECC occurred more frequently in patients with NH-IMRangio ≥40 units (18.1% versus 1.4%; P<0.0001). At multivariable analysis, NH-IMRangio provided incremental prognostic value to conventional clinical, angiographic, and echocardiographic features (adjusted-odds ratio, 14.861 [95% CI, 5.177-42.661]; P<0.0001). NH-IMRangio<40 units showed an excellent negative predictive value (98.6%) in ruling out ECC. Discharging patients with NH-IMRangio<40 units at 48 hours after admission would reduce the total in-hospital stay by 943 days (median 2 [1-4] days per patient). CONCLUSIONS: NH-IMRangio is a valuable risk-stratification tool in patients with ST-segment-elevation myocardial infarction. NH-IMRangio guided strategies to early discharge may contribute to safely shorten hospital stay, optimizing resources utilization.
Subject(s)
Heart Failure , Myocardial Infarction , Percutaneous Coronary Intervention , ST Elevation Myocardial Infarction , Humans , Coronary Angiography , Coronary Vessels/diagnostic imaging , Heart Failure/etiology , Microcirculation , Myocardial Infarction/diagnostic imaging , Myocardial Infarction/therapy , Myocardial Infarction/etiology , Patient Discharge , Percutaneous Coronary Intervention/adverse effects , Prospective Studies , Retrospective Studies , ST Elevation Myocardial Infarction/diagnostic imaging , ST Elevation Myocardial Infarction/therapy , ST Elevation Myocardial Infarction/etiology , Treatment Outcome , Observational Studies as TopicABSTRACT
Background: Critical limb-threatening ischemia (CLTI) is a severe condition characterized by rest pain and ischemic tissue loss that affects 5% to 10% of people with peripheral artery disease. In the United States, there are few Food and Drug Administration-approved devices for the primary treatment of arteries below-the-knee (BTK). Unfortunately, all suffer from high restenosis rates due to intimal hyperplasia, elastic recoil, and untreated dissection because of a lack of scaffolding. The Esprit BTK system is a resorbable, drug-eluting scaffold device with the potential to address an unmet need in people suffering from CLTI because of infrapopliteal atherosclerosis. The LIFE-BTK (pivotaL Investigation of saFety and Efficacy of drug-eluting resorbable scaffold treatment-Below The Knee) randomized controlled trial (RCT) is a prospectively designed premarket evaluation of the Esprit BTK drug-eluting resorbable scaffold used in the treatment of those patients. Methods: The LIFE-BTK trial enrolled 261 subjects with CLTI for the RCT and a further 7 subjects for a pharmacokinetic substudy. The objective of the RCT was to evaluate the safety and efficacy of the Esprit BTK scaffold compared to percutaneous transluminal angioplasty. The primary efficacy end point was a composite of limb salvage and primary patency at 12 months. The primary safety end point is freedom from major adverse limb events and peri-operative death at 6 months and 30 days, respectively. Clinical follow-up care is planned for 5 years. Conclusions: Novel devices must be tested in RCTs to evaluate their safety and efficacy compared to the standard of care if we are to improve outcomes for this challenging group of patients.
ABSTRACT
Intravascular ultrasound (IVUS) provides grayscale images of the entire vessel wall, and its technology has recently been improved, resulting in more accurate tissue characterization. Compared with conventional IVUS, high-definition (HD) IVUS provides better resolution, better image quality, faster acquisition and integration of processing tools for more efficient cath lab workflow. HD-IVUS includes transducers with higher frequencies (≥ 45 MHz), allowing a higher near field resolution combined with enough tissue penetration for a more precise assessment of the entire vessel wall. HD-IVUS preserves the potential advantages of conventional (40 MHz) IVUS over optical coherence tomography by adding a substantially higher spatial resolution. For this reason, this technology has generated increasing interest among interventional cardiologists and researchers to provide better detailed morphological evaluation on complicated plaques in acute coronary syndrome patients and better stent optimization. In this review, we provide the state-of-the-art on this technology and its current clinical applications.
ABSTRACT
Small vessel coronary artery disease (CAD) is present in 30% to 67% of patients undergoing percutaneous coronary intervention according to different series, representing an unmet clinical need in light of an increased risk of technical failure, restenosis, and need for repeated revascularization. The definition of small vessel is inconsistent across trials, and no definite cutoff value has yet been determined. The lack of consensus on the definition of small vessel CAD has contributed to the high degree of heterogeneity in the safety and efficacy of the various revascularization options. Therefore, the aim of this article is to provide a critical appraisal of existing reports and to propose a reference vessel diameter of <2.5 âmm definition of small vessel CAD to guide future clinical trials and clinical decision-making.
ABSTRACT
A machine learning (ML) algorithm for automatic segmentation of intravascular ultrasound was previously validated. It has the potential to improve efficiency, accuracy and precision of coronary vessel segmentation compared to manual segmentation by interventional cardiology experts. The aim of this study is to compare the performance of human readers to the machine and against the readings from a Core Laboratory. This is a post-hoc, cross-sectional analysis of the IBIS-4 study. Forty frames were randomly selected and analyzed by 10 readers of varying expertise two separate times, 1 week apart. Their measurements of lumen, vessel, plaque areas, and plaque burden were performed in an offline software. Among humans, the intra-observer variability was not statistically significant. For the total 80 frames, inter-observer variability between human readers, the ML algorithm and Core Laboratory for lumen area, vessel area, plaque area and plaque burden were not statistically different. For lumen area, however, relative differences between the human readers and the Core Lab ranged from 0.26 to 12.61%. For vessel area, they ranged from 1.25 to 9.54%. Efficiency between the ML algorithm and the readers differed notably. Humans spent 47 min on average to complete the analyses, while the ML algorithm took on average less than 1 min. The overall lumen, vessel and plaque means analyzed by humans and the proposed ML algorithm are similar to those of the Core Lab. Machines, however, are more time efficient. It is warranted to consider use of the ML algorithm in clinical practice.
ABSTRACT
RESUMEN La angioplastia transluminal coronaria (ATC) es una de las principales estrategias de revascularización en pacientes con enfermedad coronaria aterosclerótica (ECA). Numerosos estudios respaldan la optimización de la ATC mediante métodos de imagen endovascular; sin embargo, estos métodos son subutilizados en la práctica clínica contemporánea y enfrentan desafíos en la interpretación de los datos obtenidos, por lo que la integración de la inteligencia artificial (IA) se vislumbra como una solución atractiva para promover y simplificar su uso. La IA se define como un programa computarizado que imita la capacidad del cerebro humano para recopilar y procesar datos. El aprendizaje de máquinas es una subdisciplina de la IA que implica la creación de algoritmos capaces de analizar grandes conjuntos de datos sin suposiciones previas, mientras que el aprendizaje profundo se centra en la construcción y entrenamiento de redes neuronales artificiales profundas y complejas. Así, se ha demostrado que la incorporación de sistemas de IA a los métodos de imagen endovascular incrementa la precisión de la ATC, disminuye el tiempo del procedimiento y la variabilidad interobservador en la interpretación de los datos obtenidos, promueve así una mayor adopción y facilita su utilización. El propósito de la presente revisión es destacar cómo los sistemas actuales basados en IA pueden desempeñar un papel fundamental en la interpretación de los datos generados por los métodos de imagen endovascular, lo que conduce a una mejora en la optimización de la ATC en pacientes con ECA.
ABSTRACT Percutaneous coronary intervention (PCI) is one of the primary revascularization strategies in patients with coronary artery disease (CAD). Several studies support the use of intravascular imaging methods to optimize PCI. However, these methods are underutilized in contemporary clinical practice and face challenges in data interpretation. Therefore, the incorporation of artificial intelligence (AI) is seen as an attractive solution to promote and simplify their use. AI can be defined as a computer program that mimics the human brain in its ability to collect and process data. Machine learning is a sub-discipline of AI that involves the creation of algorithms capable of analyzing large datasets without making prior assumptions, while deep learning focuses on the construction and training of deep and complex artificial neural networks. The incorporation of AI systems to intravascular imaging methods improves the accuracy of PCI, reduces procedure duration, and minimizes interobserver variability in data interpretation. This promotes their wider adoption and facilitates their use. The aim of this review is to highlight how current AI-based systems can play a key role in the interpretation of data generated by intravascular imaging methods and optimize PCI in patients with CAD.