RESUMEN
BACKGROUND: Quantitative coronary angiography (QCA) offers objective and reproducible measures of coronary lesions. However, significant inter- and intra-observer variability and time-consuming processes hinder the practical application of on-site QCA in the current clinical setting. This study proposes a novel method for artificial intelligence-based QCA (AI-QCA) analysis of the major vessels and evaluates its performance. METHODS: AI-QCA was developed using three deep-learning models trained on 7658 angiographic images from 3129 patients for the precise delineation of lumen boundaries. An automated quantification method, employing refined matching for accurate diameter calculation and iterative updates of diameter trend lines, was embedded in the AI-QCA. A separate dataset of 676 coronary angiography images from 370 patients was retrospectively analyzed to compare AI-QCA with manual QCA performed by expert analysts. A match was considered between manual and AI-QCA lesions when the minimum lumen diameter (MLD) location identified manually coincided with the location identified by AI-QCA. Matched lesions were evaluated in terms of diameter stenosis (DS), MLD, reference lumen diameter (RLD), and lesion length (LL). RESULTS: AI-QCA exhibited a sensitivity of 89% in lesion detection and strong correlations with manual QCA for DS, MLD, RLD, and LL. Among 995 matched lesions, most cases (892 cases, 80%) exhibited DS differences ≤10%. Multiple lesions of the major vessels were accurately identified and quantitatively analyzed without manual corrections. CONCLUSION: AI-QCA demonstrates promise as an automated tool for analysis in coronary angiography, offering potential advantages for the quantitative assessment of coronary lesions and clinical decision-making.
Asunto(s)
Inteligencia Artificial , Angiografía Coronaria , Aprendizaje Profundo , Humanos , Angiografía Coronaria/métodos , Masculino , Femenino , Estudios Retrospectivos , Persona de Mediana Edad , Anciano , Vasos Coronarios/diagnóstico por imagen , Enfermedad de la Arteria Coronaria/diagnóstico por imagenRESUMEN
Importance: Although intravascular ultrasonography (IVUS) guidance promotes favorable outcomes after percutaneous coronary intervention (PCI), many catheterization laboratories worldwide lack access. Objective: To investigate whether systematic implementation of quantitative coronary angiography (QCA) to assist angiography-guided PCI could be an alternative strategy to IVUS guidance during stent implantation. Design, Setting, and Participants: This randomized, open-label, noninferiority clinical trial enrolled adults (aged ≥18 years) with chronic or acute coronary syndrome and angiographically confirmed native coronary artery stenosis requiring PCI. Patients were enrolled in 6 cardiac centers in Korea from February 23, 2017, to August 23, 2021, and follow-up occurred through August 25, 2022. All principal analyses were performed according to the intention-to-treat principle. Interventions: After successful guidewire crossing of the first target lesion, patients were randomized in a 1:1 ratio to receive either QCA- or IVUS-guided PCI. Main Outcomes and Measures: The primary outcome was target lesion failure at 12 months, defined as a composite of cardiac death, target vessel myocardial infarction, or ischemia-driven target lesion revascularization. The trial was designed assuming an event rate of 8%, with the upper limit of the 1-sided 97.5% CI of the absolute difference in 12-month target lesion failure (QCA-guided PCI minus IVUS-guided PCI) to be less than 3.5 percentage points for noninferiority. Results: The trial included 1528 patients who underwent PCI with QCA guidance (763; mean [SD] age, 64.1 [9.9] years; 574 males [75.2%]) or IVUS guidance (765; mean [SD] age, 64.6 [9.5] years; 622 males [81.3%]). The post-PCI mean (SD) minimum lumen diameter was similar between the QCA- and IVUS-guided PCI groups (2.57 [0.55] vs 2.60 [0.58] mm, P = .26). Target lesion failure at 12 months occurred in 29 of 763 patients (3.81%) in the QCA-guided PCI group and 29 of 765 patients (3.80%) in the IVUS-guided PCI group (absolute risk difference, 0.01 percentage points [95% CI, -1.91 to 1.93 percentage points]; hazard ratio, 1.00 [95% CI, 0.60-1.68]; P = .99). There was no difference in the rates of stent edge dissection (1.2% vs 0.7%, P = .25), coronary perforation (0.2% vs 0.4%, P = .41), or stent thrombosis (0.53% vs 0.66%, P = .74) between the QCA- and IVUS-guided PCI groups. The risk of the primary end point was consistent regardless of subgroup, with no significant interaction. Conclusions and Relevance: Findings of this randomized clinical trial indicate that QCA and IVUS guidance during PCI showed similar rates of target lesion failure at 12 months. However, due to the lower-than-expected rates of target lesion failure in this trial, the findings should be interpreted with caution. Trial Registration: ClinicalTrials.gov Identifier: NCT02978456.
Asunto(s)
Angiografía Coronaria , Stents Liberadores de Fármacos , Intervención Coronaria Percutánea , Ultrasonografía Intervencional , Humanos , Masculino , Ultrasonografía Intervencional/métodos , Femenino , Persona de Mediana Edad , Angiografía Coronaria/métodos , Intervención Coronaria Percutánea/métodos , Anciano , Estenosis Coronaria/cirugía , Estenosis Coronaria/diagnóstico por imagen , Estenosis Coronaria/terapia , Síndrome Coronario Agudo/cirugía , Síndrome Coronario Agudo/terapia , Síndrome Coronario Agudo/diagnóstico por imagenRESUMEN
Background: Management of low-density lipoprotein cholesterol (LDL-C) in Asia remains suboptimal, with â¼50% of patients who are treated with lipid-lowering therapies (LLTs) unable to achieve their guideline-recommended LDL-C goals. Asian-representative studies of the use of inclisiran are needed. Objectives: The authors sought to evaluate the efficacy and safety of inclisiran in Asian patients with atherosclerotic cardiovascular disease (ASCVD) or high risk of ASCVD, as an adjunct to diet and maximally tolerated statin dose, with or without additional LLTs. Methods: The ORION-18 was a phase 3 double-blind trial in which patients were randomized 1:1 to receive either 300 mg inclisiran sodium or matching placebo on days 1, 90, and 270. Percentage change in LDL-C from baseline to day 330 was the primary endpoint. Results: A total of 345 patients (mean age 59.5 years, mean baseline LDL-C 109 mg/dL, 74.7% male) were randomized to inclisiran or placebo. Baseline characteristics were similar in both groups. The percentage decrease in LDL-C from baseline to day 330 was 57.2% (P < 0.001); proprotein convertase subtilisin/kexin type 9 was reduced by 78.3% (P < 0.001). Time-adjusted percentage reduction in LDL-C from baseline after day 90 and up to day 360 was 56.3%. At day 330, 71.7% of participants with inclisiran achieved ≥50% reduction in LDL-C compared with 1.5% with placebo. Over the study period, total cholesterol, apolipoprotein B, and non-high-density lipoprotein cholesterol (HDL-C) levels were decreased significantly, and HDL-C levels increased. The incidence of adverse events with inclisiran was similar to that with placebo. Conclusions: In Asian patients with ASCVD or high risk of ASCVD, inclisiran was effective and safe. (Study of Efficacy and Safety of Inclisiran in Asian Participants With Atherosclerotic Cardiovascular Disease [ASCVD] or ASCVD High Risk and Elevated Low-Density Lipoprotein Cholesterol [LDL-C] [ORION-18]; NCT04765657).
RESUMEN
BACKGROUND: We compared the efficacy and safety of low-intensity atorvastatin and ezetimibe combination therapy with moderate-intensity atorvastatin monotherapy in patients requiring cholesterol-lowering therapy. METHODS: At 19 centers in Korea, 290 patients were randomized to 4 groups: atorvastatin 5 mg and ezetimibe 10 mg (A5E), ezetimibe 10 mg (E), atorvastatin 5 mg (A5), and atorvastatin 10 mg (A10). Clinical and laboratory examinations were performed at baseline, and at 4-week and 8-week follow-ups. The primary endpoint was percentage change from baseline in low-density lipoprotein (LDL) cholesterol levels at the 8-week follow-up. Secondary endpoints included percentage changes from baseline in additional lipid parameters. RESULTS: Baseline characteristics were similar among the study groups. At the 8-week follow-up, percentage changes in LDL cholesterol levels were significantly greater in the A5E group (49.2%) than in the E (18.7%), A5 (27.9%), and A10 (36.4%) groups. Similar findings were observed regarding the percentage changes in total cholesterol, non-high-density lipoprotein cholesterol, and apolipoprotein B levels. Triglyceride levels were also significantly decreased in the A5E group than in the E group, whereas high-density lipoprotein levels substantially increased in the A5E group than in the E group. In patients with low- and intermediate-cardiovascular risk, 93.3% achieved the target LDL cholesterol levels in the A5E group, 40.0% in the E group, 66.7% in the A5 group, and 92.9% in the A10 group. In addition, 31.4% of patients in the A5E group, 8.1% in E, 9.7% in A5, and 7.3% in the A10 group reached the target levels of both LDL cholesterol < 70 mg/dL and reduction of LDL ≥ 50% from baseline. CONCLUSIONS: The addition of ezetimibe to low-intensity atorvastatin had a greater effect on lowering LDL cholesterol than moderate-intensity atorvastatin alone, offering an effective treatment option for cholesterol management, especially in patients with low and intermediate risks.
Asunto(s)
Anticolesterolemiantes , Azetidinas , Ácidos Heptanoicos , Inhibidores de Hidroximetilglutaril-CoA Reductasas , Hipercolesterolemia , Humanos , Atorvastatina/uso terapéutico , Anticolesterolemiantes/uso terapéutico , LDL-Colesterol , Hipercolesterolemia/tratamiento farmacológico , Azetidinas/uso terapéutico , Ácidos Heptanoicos/efectos adversos , Pirroles/uso terapéutico , Quimioterapia Combinada , Ezetimiba/uso terapéutico , Colesterol , Resultado del Tratamiento , Método Doble Ciego , Inhibidores de Hidroximetilglutaril-CoA Reductasas/uso terapéuticoRESUMEN
BACKGROUND: Invasive coronary angiography (ICA) is a primary imaging modality that visualizes the lumen area of coronary arteries for diagnosis and interventional guidance. In the current practice of quantitative coronary analysis (QCA), semi-automatic segmentation tools require labor-intensive and time-consuming manual correction, limiting their application in the catheterization room. PURPOSE: This study aims to propose rank-based selective ensemble methods that improve the segmentation performance and reduce morphological errors that limit fully automated quantification of coronary artery using deep-learning segmentation of ICA. METHODS: Two selective ensemble methods proposed in this work integrated the weighted ensemble approach with per-image quality estimation. The segmentation outcomes from five base models with different loss functions were ranked either by mask morphology or estimated dice similarity coefficient (DSC). The final output was determined by imposing different weights according to the ranks. The ranking criteria based on mask morphology were formulated from empirical insight to avoid frequent types of segmentation errors (MSEN), while the estimation of DSCs was performed by comparing the pseudo-ground truth generated from a meta-learner (ESEN). Five-fold cross-validation was performed with the internal dataset of 7426 coronary angiograms from 2924 patients, and prediction model was externally validated with 556 images of 226 patients. RESULTS: The selective ensemble methods improved the segmentation performance with DSCs up to 93.07% and provided a better delineation of coronary lesion with local DSCs of up to 93.93%, outperforming all individual models. Proposed methods also minimized the chances of mask disconnection in the most narrowed regions to 2.10%. The robustness of the proposed methods was also evident in the external validation. Inference time for major vessel segmentation was approximately one-sixth of a second. CONCLUSION: Proposed methods successfully reduced morphological errors in the predicted masks and were able to enhance the robustness of the automatic segmentation. The results suggest better applicability of real-time QCA-based diagnostic methods in routine clinical settings.
Asunto(s)
Aprendizaje Profundo , Humanos , Angiografía Coronaria/métodos , Corazón , Vasos Coronarios/diagnóstico por imagen , Procesamiento de Imagen Asistido por Computador/métodosRESUMEN
We aimed to examine the associations of cardiovascular risk factors with myocardial perfusion reserve (MPR) in patients with type 2 diabetes and stable coronary artery disease. The study patients were retrospectively identified from a database of patients with diabetes and stable coronary artery disease at Asan Medical Center (Seoul, Republic of Korea), covering the period from 2017 to 2019. The primary outcome variable was MPR assessed by dynamic stress 201Tl/rest 99mTc-tetrofosmin SPECT. Univariable and stepwise multivariable analyses were performed to assess the associations of cardiovascular risk factors with MPR. A total of 276 patients (236 men and 40 women) were included. The median global MPR was 2.4 (interquartile range 1.9-3.0). Seventy-five (27.2%) patients had an MPR < 2.0. Multivariable linear regression showed that smoking (ß = - 0.44, 95% confidence interval - 0.68 to - 0.21, P < 0.001), hypertension (ß = - 0.24, 95% confidence interval - 0.47 to - 0.02, P = 0.033), and summed difference score (ß = - 0.05, 95% confidence interval - 0.07 to - 0.03, P < 0.001) were independently associated with MPR. Abnormal MPR (< 2.0) was associated with a higher incidence of cardiac death or myocardial infarction (P = 0.034). MPR assessed by dynamic stress 201Tl/rest 99mTc-tetrofosmin SPECT was impaired in a large cohort of patients with diabetes. After adjusting for risk variables, including standard myocardial perfusion imaging characteristics, smoking, and hypertension were associated with MPR. Our results may aid in identifying patients with impaired MPR and stratifying patients with type 2 diabetes.
Asunto(s)
Enfermedad de la Arteria Coronaria , Diabetes Mellitus Tipo 2 , Hipertensión , Masculino , Humanos , Femenino , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Diabetes Mellitus Tipo 2/complicaciones , Diabetes Mellitus Tipo 2/diagnóstico , Estudios Retrospectivos , Valor Predictivo de las Pruebas , Factores de Riesgo , Tomografía Computarizada de Emisión de Fotón Único/métodos , PerfusiónRESUMEN
Purpose. Pre-treatment prediction of individual blood pressure (BP) response to anti-hypertensive medication is important to determine the specific regimen for promptly and safely achieving a target BP. This study aimed to develop supervised machine learning (ML) models for predicting patient-specific treatment effects using 24-hour ambulatory BP monitoring (ABPM) data.Materials and Methods. A total of 1,129 patients who had both baseline and follow-up ABPM data were randomly assigned into training, validation and test sets in a 3:1:1 ratio. Utilising the features including clinical and laboratory findings, initial ABPM data, and anti-hypertensive medication at baseline and at follow-up, ML models were developed to predict post-treatment individual BP response. Each case was labelled by the mean 24-hour and daytime BPs derived from the follow-up ABPM.Results. At baseline, 616 (55%) patients had been treated using mono or combination therapy with 45 anti-hypertensive drugs and the remaining 513 (45%) patients had been untreated (drug-naïve). By using CatBoost, the difference between predicted vs. measured mean 24-hour systolic BP at follow-up was 8.4 ± 7.0 mm Hg (% difference of 6.6% ± 5.7%). The difference between predicted vs. measured mean 24-hour diastolic BP was 5.3 ± 4.3 mm Hg (% difference of 6.8% ± 5.5%). There were significant correlations between the CatBoost-predicted vs. the ABPM-measured changes in the mean 24-hour Systolic (r = 0.74) and diastolic (r = 0.68) BPs from baseline to follow-up. Even in the patients with renal insufficiency or diabetes, the correlations between CatBoost-predicted vs. ABPM-measured BP changes were significant.Conclusion. ML algorithms accurately predict the post-treatment ambulatory BP levels, which may assist clinicians in personalising anti-hypertensive treatment.
The prediction of post-treatment BP response is essential to plan the appropriate optimal treatment strategy for achieving the target BP level.The poor predictability of the post-treatment BP level is due to the complex pathophysiology of individual BP response, which can partly explain the poor rate to achieve the target systolic BP.In this current study including both treated and untreated patients with hypertension, machine leaning models predicted the post-treatment mean BP levels on 24-hr ABPM even in high-risk patients and patients with a high BP variability.Model-derived selection and optimisation of anti-hypertension drugs may facilitate prompt achievement of adequate BP control without drug-related complications and avoiding repeating 24-hour ABPM or multiple visits for drug readjustment.
Asunto(s)
Antihipertensivos , Hipertensión , Humanos , Presión Sanguínea , Monitoreo Ambulatorio de la Presión Arterial , Hipertensión/tratamiento farmacológico , Aprendizaje AutomáticoRESUMEN
BACKGROUND: Current guidelines recommend that patients with established atherosclerotic cardiovascular disease (ASCVD) use high-intensity statin therapy to lower low-density lipoprotein (LDL)-cholesterol levels by at least 50%, irrespective of age. However, in real-world practice, there is reluctance to maintain statin use in response to side-effects, particularly statin-associated muscle symptoms (SAMS). Moreover, no randomized trial has been conducted on the safety of statin therapy in elderly patients. TRIAL DESIGN: This investigator-initiated, multicenter, randomized clinical trial aimed to investigate the incidence of SAMS and its effect on LDL-cholesterol levels in elderly patients with established ASCVD. Eligible patients were aged 70 years or older with established ASCVD. Consecutive patients who met the inclusion criteria were randomized in a 1:1 fashion to receive either intensive statin monotherapy (rosuvastatin 20 mg) or combination therapy (rosuvastatin/ezetimibe, 5/10 mg). The primary endpoint of the study is SAMS at 6 months with regard to treatment strategy. Positive SAMS results are defined as patients with a proposed statin myalgia index score of 7 or higher. The key secondary end-points are target LDL-cholesterol achievement (LDL < 70 mg/dL), incidence of myopathy, rhabdomyolysis, frequency of drug discontinuation, and creatinine kinase, aspartate transaminase, alanine transaminase, total cholesterol, LDL-cholesterol, high-density lipoprotein-cholesterol, triglyceride, and highly sensitive C-reactive protein levels at 6 months. CONCLUSIONS: The SaveSAMS study is a multicenter, randomized trial that will compare the incidence of SAMS in patients with established ASCVD who are 70 years or older on intensive statin monotherapy to that combination therapy.
Asunto(s)
Anticolesterolemiantes , Aterosclerosis , Enfermedades Cardiovasculares , Inhibidores de Hidroximetilglutaril-CoA Reductasas , Anciano , Humanos , Inhibidores de Hidroximetilglutaril-CoA Reductasas/uso terapéutico , Rosuvastatina Cálcica/efectos adversos , Ezetimiba/efectos adversos , Anticolesterolemiantes/uso terapéutico , Enfermedades Cardiovasculares/epidemiología , Enfermedades Cardiovasculares/prevención & control , Enfermedades Cardiovasculares/inducido químicamente , Aterosclerosis/tratamiento farmacológico , LDL-Colesterol , Quimioterapia Combinada , Resultado del TratamientoRESUMEN
Myocardial viability test to guide revascularization remains uncertain in patients with ischemic cardiomyopathy. We evaluated the different impacts of revascularization on cardiac mortality according to the extent of myocardial scar assessed by cardiac magnetic resonance (CMR) with late gadolinium enhancement (LGE) in patients with ischemic cardiomyopathy. A total of 404 consecutive patients with significant coronary artery disease and an ejection fraction ≤35% were assessed by LGE-CMR before revascularization. Of them, 306 patients underwent revascularization and 98 patients received medical treatment alone. The primary outcome was cardiac death. During a median follow-up of 6.3 years, cardiac death occurred in 158 patients (39.1%). Revascularization was associated with a significantly lower risk of cardiac death than medical treatment alone in the overall population (adjusted hazard ratio [aHR] 0.29, 95% confidence interval (CI) 0.19 to 0.45, p <0.001). There was a significant interaction between the number of segments with >75% transmural LGE and revascularization on the risk of cardiac death (p = 0.037 for interaction). In patients with limited myocardial scar (<6 segments with >75% transmural LGE, n = 354), revascularization had a significantly lower risk of cardiac death than medical treatment alone (aHR 0.24, 95% CI 0.15 to 0.37, p <0.001); in patients with extensive myocardial scar (≥6 segments with >75% transmural LGE, n = 50), there was no significant difference between revascularization and medical treatment alone regarding the risk of cardiac death (aHR 1.33, 95% CI 0.46 to 3.80, p = 0.60). In conclusion, the assessment of myocardial scar by LGE-CMR may be helpful in the decision-making process for revascularization in patients with ischemic cardiomyopathy.
Asunto(s)
Cardiomiopatías , Isquemia Miocárdica , Humanos , Medios de Contraste , Gadolinio , Cicatriz/complicaciones , Imagen por Resonancia Cinemagnética , Pronóstico , Isquemia Miocárdica/complicaciones , Espectroscopía de Resonancia Magnética , Muerte , Cardiomiopatías/complicaciones , Valor Predictivo de las PruebasRESUMEN
INTRODUCTION AND OBJECTIVES: There are scarce data on the optimal duration and prognostic impact of dual antiplatelet therapy (DAPT) after percutaneous coronary intervention (PCI) with second-generation drug-eluting stents for left main coronary artery (LMCA) disease. The aim of this study was to investigate the practice pattern and long-term prognostic effect of DAPT duration in patients undergoing PCI with second-generation drug-eluting stents for LMCA disease. METHODS: Using individual patient-level data from the IRIS-MAIN and KOMATE registries, 1827 patients undergoing PCI with second-generation drug-eluting stents for LMCA disease with valid information on DAPT duration were included. The efficacy outcome was major adverse cardiovascular events (MACE, a composite of cardiac death, myocardial infarction, and stent thrombosis) and the safety outcome was TIMI major bleeding. RESULTS: DAPT duration was <6 months (n=273), 6 to 12 months (n=477), 12 to 24 months (n=637), and ≥ 24 months (n=440). The median follow-up duration was 3.9 [interquartile range, 3.01-5.00] years. Prolonged DAPT duration was associated with lower incidences of MACE. In multigroup propensity score analysis, adjusted HR for MACE were significantly higher for DAPT <6 months and DAPT 6 to 12 months than for DAPT 12 to 24 months (HR, 4.51; 95%CI, 2.96-6.88 and HR 1.92; 95%CI, 1.23-3.00). There was no difference in HR for major bleeding among the assessed groups. CONCLUSIONS: DAPT duration following PCI for LMCA disease is highly variable. Although the duration of DAPT should be considered in the context of the clinical situation of each patient, <12 months of DAPT was associated with higher incidence of MACE. Registration identifiers: NCT01341327; NCT03908463.
Asunto(s)
Enfermedad de la Arteria Coronaria , Infarto del Miocardio , Intervención Coronaria Percutánea , Humanos , Enfermedad de la Arteria Coronaria/cirugía , Enfermedad de la Arteria Coronaria/complicaciones , Quimioterapia Combinada , Hemorragia/inducido químicamente , Hemorragia/epidemiología , Hemorragia/complicaciones , Infarto del Miocardio/etiología , Intervención Coronaria Percutánea/efectos adversos , Inhibidores de Agregación Plaquetaria/uso terapéutico , Resultado del TratamientoRESUMEN
Background: There is a paucity of direct data on the incidence and predictors of intracranial bleeding (ICB) after coronary artery bypass graft surgery (CABG). Methods: The Korean National Health Insurance database was used to identify patients without prior ICB who underwent CABG. The outcomes of interest were the time-dependent incidence rates of ICB and the associated mortality. Results: Among 35,021 patients who underwent CABG between 2007 and 2018, 895 (2.6%) experienced an ICB during a median follow-up of 6.0 years. The 1-year cumulative incidence of ICB was 0.76%, with a relatively high incidence rate (9.93 cases per 1,000 person-years) within the first 1-30 days. Subsequent incidence rates showed a sharp decline until 3 years, followed by a steady decrease up to 10 years. The 1-year mortality rate after ICB was 38.1%, with most deaths occurring within 30 days (23.6%). The predictors of ICB after CABG were age ≥ 75 years, hypertension, pre-existing dementia, history of ischemic stroke or transient ischemic attack, and end-stage renal disease. Conclusions: In an unselected nationwide population undergoing CABG, the incidence of ICB was non-negligible and showed a relatively high incidence rate during the early postoperative period. Post-CABG ICB was associated with a high risk of premature death. Further research is needed to stratify high-risk patients and personalize therapeutic decisions for preventing ICB after CABG.
RESUMEN
BACKGROUND: Although there is a growing interest in prediction models based on electronic medical records (EMRs) to identify patients at risk of adverse cardiac events following invasive coronary treatment, robust models fully utilizing EMR data are limited. OBJECTIVE: We aimed to develop and validate machine learning (ML) models by using diverse fields of EMR to predict the risk of 30-day adverse cardiac events after percutaneous intervention or bypass surgery. METHODS: EMR data of 5,184,565 records of 16,793 patients at a quaternary hospital between 2006 and 2016 were categorized into static basic (eg, demographics), dynamic time-series (eg, laboratory values), and cardiac-specific data (eg, coronary angiography). The data were randomly split into training, tuning, and testing sets in a ratio of 3:1:1. Each model was evaluated with 5-fold cross-validation and with an external EMR-based cohort at a tertiary hospital. Logistic regression (LR), random forest (RF), gradient boosting machine (GBM), and feedforward neural network (FNN) algorithms were applied. The primary outcome was 30-day mortality following invasive treatment. RESULTS: GBM showed the best performance with area under the receiver operating characteristic curve (AUROC) of 0.99; RF had a similar AUROC of 0.98. AUROCs of FNN and LR were 0.96 and 0.93, respectively. GBM had the highest area under the precision-recall curve (AUPRC) of 0.80, and the AUPRCs of RF, LR, and FNN were 0.73, 0.68, and 0.63, respectively. All models showed low Brier scores of <0.1 as well as highly fitted calibration plots, indicating a good fit of the ML-based models. On external validation, the GBM model demonstrated maximal performance with an AUROC of 0.90, while FNN had an AUROC of 0.85. The AUROCs of LR and RF were slightly lower at 0.80 and 0.79, respectively. The AUPRCs of GBM, LR, and FNN were similar at 0.47, 0.43, and 0.41, respectively, while that of RF was lower at 0.33. Among the categories in the GBM model, time-series dynamic data demonstrated a high AUROC of >0.95, contributing majorly to the excellent results. CONCLUSIONS: Exploiting the diverse fields of the EMR data set, the ML-based 30-day adverse cardiac event prediction models demonstrated outstanding results, and the applied framework could be generalized for various health care prediction models.
RESUMEN
BACKGROUND AND OBJECTIVES: Studies evaluating the nature of ischemic burden of chronic total occlusion (CTO) vessels are still lacking. METHODS: A total of 165 patients with single vessel CTO >2.5 mm in an epicardial coronary artery who underwent single photon emission computed tomography (SPECT) were enrolled in the study. Ischemic burden was calculated with the use of semi-quantitative SPECT analysis, and was defined as the summed difference score (SDS) divided by the maximal limit of the score (=SDS/68). RESULTS: The mean age of the participants was 59.5 years and the CTO of the left anterior descending coronary artery (LAD), left circumplex coronary artery (LCX), and right coronary artery (RCA) accounted for 93 (56.4%), 18 (10.9%), and 54 (32.7%) patients, respectively. The median ischemic burden of the total population was 8.8%, and it was highest in the LAD CTO (10.3%) compared with the LCX (5.9%) and RCA CTO (5.9%, p<0.001). High-ischemic burden (ischemic burden >10%) was observed in 66 patients (40.0%), and in 47 patients (50.5%) of the LAD CTO. Ischemic burden was different according to the CTO location only in LAD CTO. The statistically significant predictors for high-ischemic burden were hypertension, baseline ejection fraction >45%, LAD CTO, proximal CTO location, and de novo CTO. Japanese-CTO score and Rentrop scale collateral grade were not associated with high-ischemic burden. CONCLUSIONS: Only 40% of patients with single vessel CTO had ischemic burden >10%. For CTO vessels, measurement of ischemic burden using SPECT prior to revascularization may be helpful in identifying beneficial subjects.
RESUMEN
INTRODUCTION: Angiography remains the gold standard for guiding percutaneous coronary intervention (PCI). However, it is prone to suboptimal stent results due to the visual estimation of coronary measurements. Although the benefit of intravascular ultrasound (IVUS)-guided PCI is becoming increasingly recognised, IVUS is not affordable for many catheterisation laboratories. Thus, a more practical and standardised angiography-based approach is necessary to support stent implantation. METHODS AND ANALYSIS: The Quantitative Coronary Angiography versus Intravascular Ultrasound Guidance for Drug-Eluting Stent Implantation trial is a randomised, investigator-initiated, multicentre, open-label, non-inferiority trial comparing the quantitative coronary angiography (QCA)-guided PCI strategy with IVUS-guided PCI in all-comer patients with significant coronary artery disease. A novel, standardised, QCA-based PCI protocol for the QCA-guided group will be provided to all participating operators, while the PCI optimisation criteria will be predefined for both strategies. A total of 1528 patients will be randomised to either group at a 1:1 ratio. The primary endpoint is the 12-month cumulative incidence of target-lesion failure defined as a composite of cardiac death, target-vessel myocardial infarction or ischaemia-driven target-lesion revascularisation. Clinical follow-up assessments are scheduled at 1, 6 and 12 months for all patients enrolled in the study. ETHICS AND DISSEMINATION: Ethics approval for this study was granted by the Institutional Review Board of Asan Medical Center (no. 2017-0060). Informed consent will be obtained from every participant. The study findings will be published in peer-reviewed journal articles and disseminated through public forums and academic conference presentations. Cost-effectiveness and secondary imaging analyses will be shared in secondary papers. TRIAL REGISTRATION NUMBER: NCT02978456.
Asunto(s)
Enfermedad de la Arteria Coronaria , Stents Liberadores de Fármacos , Intervención Coronaria Percutánea , Angiografía Coronaria/métodos , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Enfermedad de la Arteria Coronaria/cirugía , Humanos , Estudios Multicéntricos como Asunto , Intervención Coronaria Percutánea/métodos , Ensayos Clínicos Controlados Aleatorios como Asunto , Resultado del Tratamiento , Ultrasonografía Intervencional/métodosRESUMEN
Percutaneous coronary intervention (PCI) is used to treat obstructive coronary artery disease (CAD). The role of PCI is well defined in acute coronary syndrome, but that for stable CAD remains debatable. Although PCI generally relieves angina in patients with stable CAD, it may not change its prognosis. The extent and severity of CAD are major determinants of prognosis, and complete revascularization (CR) of all ischemia-causing lesions might improve outcomes. Several studies have shown better outcomes with CR than with incomplete revascularization, emphasizing the importance of functional angioplasty. However, different definitions of inducible myocardial ischemia have been used across studies, making their comparison difficult. Various diagnostic tools have been used to estimate the presence, extent, and severity of inducible myocardial ischemia. However, to date, there are no agreed reference standards of inducible myocardial ischemia. The hallmarks of inducible myocardial ischemia such as electrocardiographic changes and regional wall motion abnormalities may be more clinically relevant as the reference standard to define ischemia-causing lesions. In this review, we summarize studies regarding myocardial ischemia, PCI guidance, and possible explanations for similar findings across studies. Also, we provide some insights into the ideal definition of inducible myocardial ischemia and highlight the appropriate PCI strategy.
RESUMEN
OBJECTIVES: We aimed to assess the advantages of using the retrograde approach as an initial strategy rather than as a rescue strategy for complex chronic total occlusions (CTOs). BACKGROUND: Even for complex CTOs where a retrograde approach is deemed necessary, an antegrade approach is frequently used as an initial strategy in real-world practice. METHODS: We evaluated 352 retrograde procedures for CTO conducted at our high-volume center between January 2007 and January 2019. Procedural efficiency and safety was assessed based on the guidewire manipulation time (GWMT) and the occurrence of procedure-related adverse events for the primary retrograde approach (PRA) and the rescue retrograde approach (RRA). RESULTS: PRA and RRA were used in 191 (54.3%) and 161 (45.7%) of the CTO procedures, respectively. The complexity of the CTO lesion was significantly higher in the PRA group than in the RRA group (Japanese-CTO score, 2.62 ± 1.07 vs. 2.38 ± 1.06, p = 0.037). The technical success rate of two groups was similar (p = 0.47). The median GWMT required for PRA was significantly shorter than that for RRA (85 [interquartile range, 55-126] vs. 120 [85-157] min, p < 0.001). The total duration of the procedure and fluoroscopic time were shorter, and the number of guidewires and amount of contrast used during the index procedure were smaller in the PRA group. The incidence of procedure-related adverse events was not significantly different between the two groups. CONCLUSIONS: PRA showed higher procedural efficiency than RRA with comparable safety. Opting for PRA for complex CTOs might be a rational decision to enhance the procedural efficiency.
Asunto(s)
Oclusión Coronaria , Intervención Coronaria Percutánea , Enfermedad Crónica , Angiografía Coronaria/métodos , Oclusión Coronaria/diagnóstico por imagen , Oclusión Coronaria/etiología , Oclusión Coronaria/terapia , Humanos , Intervención Coronaria Percutánea/efectos adversos , Intervención Coronaria Percutánea/métodos , Sistema de Registros , Factores de Riesgo , Resultado del TratamientoRESUMEN
Background The long-term impact of newly discovered, asymptomatic abnormal ankle-brachial index (ABI) in patients with significant coronary artery disease is limited. Methods and Results Between January 2006 and December 2009, ABI was evaluated in 2424 consecutive patients with no history of claudication or peripheral artery disease who had significant coronary artery disease. We previously reported a 3-year result; therefore, the follow-up period was extended. The primary end point was a composite of all-cause death, myocardial infarction (MI), and stroke over 7 years. Of the 2424 patients with significant coronary artery disease, 385 had an abnormal ABI (ABI ≤0.9 or ≥1.4). During the follow-up period, the rate of the primary outcome was significantly higher in the abnormal ABI group than in the normal ABI group (P<0.001). The abnormal ABI group had a significantly higher risk of composite of all-cause death/MI/stroke than the normal ABI group, after adjustment with multivariable Cox proportional hazards regression analysis (hazard ratio [HR], 2.07; 95% CI, 1.67-2.57; P<0.001) and propensity score-matched analysis (HR, 1.97; 95% CI, 1.49-2.60; P<0.001). In addition, an abnormal ABI was associated with a higher risk of all-cause death, MI, and stroke, but not repeat revascularization. Conclusions Among patients with significant coronary artery disease, asymptomatic abnormal ABI was associated with sustained and increased incidence of composite of all-cause death/MI/stroke, all-cause death, MI, and stroke during extended follow-up over 7 years.
Asunto(s)
Índice Tobillo Braquial , Enfermedad de la Arteria Coronaria , Causas de Muerte , Enfermedad de la Arteria Coronaria/epidemiología , Enfermedad de la Arteria Coronaria/fisiopatología , Estudios de Seguimiento , Humanos , Infarto del Miocardio/epidemiología , Valor Predictivo de las Pruebas , Factores de Riesgo , Accidente Cerebrovascular/epidemiologíaRESUMEN
OBJECTIVES: This study evaluated the association between elevated levels of lipoprotein(a) [Lp(a)] and risk of recurrent ischemic events in patients who underwent percutaneous coronary intervention (PCI). BACKGROUND: Elevated levels of Lp(a) have been identified as an independent, possibly causal, risk factor for atherosclerotic cardiovascular disease in a general population study. METHODS: A prospective single-center registry was used to identify 12,064 patients with baseline Lp(a) measurements who underwent PCI between 2003 and 2013. The primary outcomes were a composite of cardiovascular death, spontaneous myocardial infarction, and ischemic stroke. RESULTS: From the registry, 3,747 (31.1%) patients had high Lp(a) (>30 mg/dL) and 8,317 (68.9%) patients had low Lp(a) (≤30 mg/dL). During a median follow-up of 7.4 years, primary outcomes occurred in 1,490 patients, and the incidence rates of primary outcomes were 2.0 per 100 person-years in the high-Lp(a) group and 1.6 per 100 person-years in the low-Lp(a) group (adjusted hazard ratio [aHR]: 1.17; 95% confidence interval [CI]: 1.05-1.30; P = 0.004). Increased risk of recurrent ischemic cardiovascular events in the high-Lp(a) group was consistent in various subgroups including patients receiving statin treatment at discharge (aHR: 1.18; 95% CI: 1.03-1.34; P = 0.011). In addition, the risk of repeated revascularization was significantly higher in the high-Lp(a) group (aHR: 1.13; 95% CI: 1.02-1.25; P = 0.022). CONCLUSIONS: Elevated levels of Lp(a) were significantly associated with the recurrent ischemic events in patients who underwent PCI. This study provides a rationale for outcome trials to test Lp(a)-lowering therapy for secondary prevention in patients undergoing PCI.
Asunto(s)
Enfermedad de la Arteria Coronaria , Intervención Coronaria Percutánea , Biomarcadores , Enfermedad de la Arteria Coronaria/diagnóstico por imagen , Enfermedad de la Arteria Coronaria/terapia , Humanos , Lipoproteína(a) , Intervención Coronaria Percutánea/efectos adversos , Estudios Prospectivos , Factores de Riesgo , Resultado del TratamientoRESUMEN
PURPOSE: We investigated whether the combination therapy of low-intensity rosuvastatin and ezetimibe is an useful alternative to moderate-intensity rosuvastatin monotherapy in patients requiring cholesterol-lowering therapy. METHODS: This was a multicenter randomized, double-blind study to investigate the safety and efficacy of a fixed-dose combination of rosuvastatin 2.5 mg and ezetimibe 10 mg (R2.5+E10) compared to those of ezetimibe 10 mg monotherapy (E10), rosuvastatin 2.5 mg (R2.5), and rosuvastatin 5 mg monotherapy (R5) in patients with hypercholesterolemia. A total of 348 patients at 15 centers in Korea were screened, and 279 patients were randomized to different groups in the study. Clinical and laboratory examinations were performed at baseline and 4 and 8 weeks after intervention. The primary endpoint was the percentage change of low-density lipoprotein (LDL) cholesterol levels at the 8-week follow-up. FINDINGS: Baseline characteristics were similar among the four groups. There were significant changes in lipid profiles at the 8-week follow-up. A greater decrease in the LDL cholesterol levels (primary endpoint) were found in the R2.5+E10 group (-45.7±18.6%) than in the E10 group (-16.7±14.7%, p<0.0001), R2.5 group (-32.6±15.1%, p<0.0001), and R5 group (-38.9±13.9%, p=0.0003). Similar outcomes were observed regarding the decrease in total cholesterol, non-high-density lipoprotein (HDL) cholesterol, and apolipoprotein B protein. In addition, changes in the triglyceride and HDL levels in the R2.5+E10 group were significantly different compared with those in the E10 group; however, the changes were similar to those in the other treatment groups. In patients with low and moderate risk, all patients achieved the target LDL cholesterol levels in the R2.5+E10 group (100%) compared to 13.0% in the E10 group, 47.6% in the R2.5 group, and 65.2% in the R5 group. Adverse effects were rare and similar in the four groups. IMPLICATIONS: Fixed-dose combination of low-intensity rosuvastatin and ezetimibe was more effective in lowering LDL cholesterol and achieving LDL cholesterol goals than moderate-intensity rosuvastatin monotherapy. These findings suggest that the combination therapy of low-intensity rosuvastatin and ezetimibe is an useful alternative to moderate-intensity rosuvastatin monotherapy for cholesterol management, particularly in patients with low and moderate risk. ClinicalTrials.gov identifier: NCT04652349.
Asunto(s)
Anticolesterolemiantes , Inhibidores de Hidroximetilglutaril-CoA Reductasas , Hipercolesterolemia , Anticolesterolemiantes/uso terapéutico , Método Doble Ciego , Quimioterapia Combinada , Ezetimiba/uso terapéutico , Humanos , Inhibidores de Hidroximetilglutaril-CoA Reductasas/uso terapéutico , Hipercolesterolemia/tratamiento farmacológico , Lípidos , Rosuvastatina Cálcica/uso terapéutico , Resultado del TratamientoRESUMEN
BACKGROUND: Sodium-glucose co-transporter 2 inhibitors reduce the risk of cardiovascular events in type 2 diabetic patients with coronary artery disease (CAD); however, the underlying mechanisms remain unclear. OBJECTIVES: We compared the effects of empagliflozin vs. sitagliptin therapy on myocardial perfusion reserve (MPR) using dynamic single-photon emission computed tomography (SPECT) imaging. METHODS: In total, 100 patients with type 2 diabetes, CAD and an MPR <2.5 were randomized to receive either empagliflozin (10 mg once daily) or sitagliptin (100 mg once daily). Dynamic SPECT examinations were performed at baseline and at 6 months. The primary endpoint was the percent change of global MPR. Evaluable SPECT data were available for 98 patients. RESULTS: Baseline clinical characteristics and SPECT data were well balanced between the two groups. At a 6-month follow-up, the fasting glucose and glycated hemoglobin levels significantly decreased in both groups. Hematocrit and hemoglobin levels significantly increased in the empagliflozin group but not in the sitagliptin group. The global MPR significantly improved after treatment in both groups (34.5 ± 70.6%; P = 0.005 for empagliflozin vs. 22.4 ± 45.7%; P = 0.024 for sitagliptin). However, there was no significant difference in the global MPR between the two groups (P = 0.934). Similar findings were detected with regard to the regional MPR. CONCLUSION: Among patients with type 2 diabetes and CAD, both empagliflozin and sitagliptin significantly improved the global MPR with no significant difference between the groups.