RESUMO
INTRODUCTION: Point-of-care ultrasound has become a universal practice, employed by physicians across various disciplines, contributing to diagnostic processes and decision-making. AIM: To assess the association of reduced (<50%) left-ventricular ejection fraction (LVEF) based on prospective point-of-care ultrasound operated by medical students using an artificial intelligence (AI) tool and 1-year primary composite outcome, including mortality and readmission for cardiovascular-related causes. METHODS: Eight trained medical students used a hand-held ultrasound device (HUD) equipped with an AI-based tool for automatic evaluation of the LVEF of non-selected patients hospitalized in a cardiology department from March 2019 through March 2020. RESULTS: The study included 82 patients (72 males aged 58.5 ± 16.8 years), of whom 34 (41.5%) were diagnosed with AI-based reduced LVEF. The rates of the composite outcome were higher among patients with reduced systolic function compared to those with preserved LVEF (41.2% vs. 16.7%, p = 0.014). Adjusting for pertinent variables, reduced LVEF independently predicted the composite outcome (HR 2.717, 95% CI 1.083-6.817, p = 0.033). As compared to those with LVEF ≥ 50%, patients with reduced LVEF had a longer length of stay and higher rates of the secondary composite outcome, including in-hospital death, advanced ventilatory support, shock, and acute decompensated heart failure. CONCLUSION: AI-based assessment of reduced systolic function in the hands of medical students, independently predicted 1-year mortality and cardiovascular-related readmission and was associated with unfavorable in-hospital outcomes. AI utilization by novice users may be an important tool for risk stratification for hospitalized patients.
RESUMO
Introduction: Point-of-care ultrasound (POCUS) use is now universal among nonexperts. Artificial intelligence (AI) is currently employed by nonexperts in various imaging modalities to assist in diagnosis and decision making. Aim: To evaluate the diagnostic accuracy of POCUS, operated by medical students with the assistance of an AI-based tool for assessing the left ventricular ejection fraction (LVEF) of patients admitted to a cardiology department. Methods: Eight students underwent a 6-hour didactic and hands-on training session. Participants used a hand-held ultrasound device (HUD) equipped with an AI-based tool for the automatic evaluation of LVEF. The clips were assessed for LVEF by three methods: visually by the students, by students + the AI-based tool, and by the cardiologists. All LVEF measurements were compared to formal echocardiography completed within 24 hours and were evaluated for LVEF using the Simpson method and eyeballing assessment by expert echocardiographers. Results: The study included 88 patients (aged 58.3 ± 16.3 years). The AI-based tool measurement was unsuccessful in 6 cases. Comparing LVEF reported by students' visual evaluation and students + AI vs. cardiologists revealed a correlation of 0.51 and 0.83, respectively. Comparing these three evaluation methods with the echocardiographers revealed a moderate/substantial agreement for the students + AI and cardiologists but only a fair agreement for the students' visual evaluation. Conclusion: Medical students' utilization of an AI-based tool with a HUD for LVEF assessment achieved a level of accuracy similar to that of cardiologists. Furthermore, the use of AI by the students achieved moderate to substantial inter-rater reliability with expert echocardiographers' evaluation.
Assuntos
Estudantes de Medicina , Função Ventricular Esquerda , Humanos , Volume Sistólico , Inteligência Artificial , Sistemas Automatizados de Assistência Junto ao Leito , Reprodutibilidade dos Testes , Ecocardiografia/métodos , Poder PsicológicoRESUMO
We sought to prospectively investigate the accuracy of an artificial intelligence (AI)-based tool for left ventricular ejection fraction (LVEF) assessment using a hand-held ultrasound device (HUD) in COVID-19 patients and to examine whether reduced LVEF predicts the composite endpoint of in-hospital death, advanced ventilatory support, shock, myocardial injury, and acute decompensated heart failure. COVID-19 patients were evaluated with a real-time LVEF assessment using an HUD equipped with an AI-based tool vs. assessment by a blinded fellowship-trained echocardiographer. Among 42 patients, those with LVEF < 50% were older with more comorbidities and unfavorable exam characteristics. An excellent correlation was demonstrated between the AI and the echocardiographer LVEF assessment (0.774, p < 0.001). Substantial agreement was demonstrated between the two assessments (kappa = 0.797, p < 0.001). The sensitivity, specificity, PPV, and NPV of the HUD for this threshold were 72.7% 100%, 100%, and 91.2%, respectively. AI-based LVEF < 50% was associated with worse composite endpoints; unadjusted OR = 11.11 (95% CI 2.25-54.94), p = 0.003; adjusted OR = 6.40 (95% CI 1.07-38.09, p = 0.041). An AI-based algorithm incorporated into an HUD can be utilized reliably as a decision support tool for automatic real-time LVEF assessment among COVID-19 patients and may identify patients at risk for unfavorable outcomes. Future larger cohorts should verify the association with outcomes.
RESUMO
The role of point-of-care ultrasound (POCUS) in patient management has been established in recent years as an important tool. It is increasingly used by multiple medical disciplines in numerous clinical settings, for different applications and diagnostic purposes and in the guidance of procedures. The introduction of small-sized and inexpensive hand-held ultrasound devices (HUDs) has addressed some of the POCUS-related challenges and has thus extended POCUS' applicability. HUD utilization is even more relevant in the COVID-19 setting given the operators' infection risk, excessive workload concerns and general equipment contamination. This review focuses on the available technology, usefulness, feasibility and clinical applications of HUD for echocardiogram assessment in patients with COVID-19.
RESUMO
BACKGROUND: The association between COVID-19 infection and the cardiovascular system necessitates the use of an echocardiogram in this setting. Information on the utilization, safety, and quality of point-of-care cardiac and lung ultrasound using a hand-held device in these patients is scarce. AIMS: To investigate the safety, technical aspects, quality indices, and interpretive accuracy of a hand-held echocardiogram in patients with COVID-19. METHODS: From April-28 through July-27, 2020, consecutive patients with COVID-19 underwent hand-held echocardiogram and lung ultrasound evaluation (Vscan Extend™; GE Healthcare) within 48-h of admission. The operators recorded a series of technical parameters and graded individual experiences. The examinations were further analyzed by a blinded fellowship-trained echocardiographer for general quality, proper acquisition, and right ventricular (RV) demonstration. RESULTS: Among 103 patients, 66 (64.1%) were male. Twenty-nine (28.2%) patients could not turn on their left side and 23 (22.3%) could not maintain effective communication. The mean length of each echocardiogram study was 8.5 ± 2.9 min, battery usage was 14 ± 5%, and mean operator-to-patient proximity was 59 ± 11 cm. Ninety-five (92.2%) examinations were graded as fair/good quality. A fair agreement was demonstrated between the operator and the echocardiographer for general ultrasound quality (Kappa = 0.329, p < 0.001). A fair-good correlation (r = 0.679, p < 0.001) and substantial agreement (Kappa = 0.612, p < 0.001) were demonstrated between the operator and echocardiographer for left ventricular ejection fraction (LVEF), whereas a fair agreement was demonstrated for RV systolic function (Kappa = 0.308, p = 0.002). LVEF agreement was also assessed using the Bland-Altman analysis revealing a mean bias of -0.96 (95% limits of agreement 9.43 to -11.35; p = 0.075). CONCLUSIONS: Among patients with COVID-19, echocardiography with a hand-held ultrasound is a safe and reasonable alternative for a complete formal study (<10% poor-quality indices). Echocardiogram assessment by the operators during the exam acquisition is reliable for LVEF, while RV systolic function should be subsequently offline reassessed.
Assuntos
COVID-19 , Ecocardiografia , Estudos de Viabilidade , Feminino , Humanos , Pulmão/diagnóstico por imagem , Masculino , Volume Sistólico , Função Ventricular EsquerdaRESUMO
Patients with ST-elevation myocardial infarction (STEMI) can present with angiographically significant coronary artery disease (CAD) of non-infarct-related artery (IRA) or with IRA-only CAD. This study aimed to evaluate the prevalence, predictors, and outcome of patients with STEMI and angiographically significant CAD of non-IRA. All consecutive patients with STEMI who underwent primary percutaneous coronary intervention between 2000 and 2020 were included. Angiographically significant CAD was defined as >50% stenosis of the left main coronary artery and/or >90% stenosis for all other coronary arteries. A total of 2,663 patients had IRA-only CAD (80.2%) and 657 had angiographically significant non-IRA CAD (19.8%). Independent predictors for non-IRA CAD were male gender (odds ratio [OR] 1.34, 95% confidence interval [CI] 1.05 to 1.70, p = 0.021), age >50 years (OR 1.45, 95% CI 1.11 to 1.91, p = 0.007), and diabetes mellitus (OR 1.56, 95% CI 1.29 to 1.9, p <0.001), whereas smoking (OR 0.83, 95% CI 0.68 to 0.99, p = 0.004) and family history of CAD (OR 0.78, 95% CI 0.62 to 0.98, p = 0.032) were found to be negatively associated with non-IRA CAD. In-hospital 30-day and 1- and 5-year all-cause mortality were higher in patients with non-IRA CAD compared with IRA-only CAD (5.8% vs 2.5%, 8.5% vs 3.3%, 18.4% vs 7.6% and 36.3% vs 20.3%, respectively; p for all <0.001). In conclusion, 20% of patients with STEMI had angiographically significant non-IRA CAD. Older age, male gender, and diabetes mellitus were independent predictors for non-IRA CAD, whereas smoking and family history of CAD predicted IRA-only CAD. The presence of non-IRA CAD was associated with higher short- and long-term all-cause mortality rates.
Assuntos
Doença da Artéria Coronariana , Diabetes Mellitus , Intervenção Coronária Percutânea , Infarto do Miocárdio com Supradesnível do Segmento ST , Constrição Patológica , Angiografia Coronária , Doença da Artéria Coronariana/complicações , Doença da Artéria Coronariana/epidemiologia , Diabetes Mellitus/epidemiologia , Diabetes Mellitus/etiologia , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Intervenção Coronária Percutânea/efeitos adversos , Prevalência , Resultado do TratamentoRESUMO
BACKGROUND: Strict isolation precautions limit formal echocardiography use in the setting of COVID-19 infection. Information on the importance of handheld focused ultrasound for cardiac evaluation in these patients is scarce. This study investigated the utility of a handheld echocardiography device in hospitalised patients with COVID-19 in diagnosing cardiac pathologies and predicting the composite end point of in-hospital death, mechanical ventilation, shock, and acute decompensated heart failure. METHODS: From April 28 through July 27, 2020, consecutive patients diagnosed with COVID-19 underwent evaluation with the use of handheld ultrasound (Vscan Extend with Dual Probe; GE Healthcare) within 48 hours of admission. The patients were divided into 2 groups: "normal" and "abnormal" echocardiogram, as defined by biventricular systolic dysfunction/enlargement or moderate/severe valvular regurgitation/stenosis. RESULTS: Among 102 patients, 26 (25.5%) had abnormal echocardiograms. They were older with more comorbidities and more severe presenting symptoms compared with the group with normal echocardiograms. The prevalences of the composite outcome among low- and high-risk patients (oxygen saturation < 94%) were 3.1% and 27.1%, respectively. Multivariate logistic regression analysis revealed that an abnormal echocardiogram at presentation was independently associated with the composite end point (odds ratio 6.19, 95% confidence interval 1.50-25.57; P = 0.012). CONCLUSIONS: An abnormal echocardiogram in COVID-19 infection settings is associated with a higher burden of medical comorbidities and independently predicts major adverse end points. Handheld focused echocardiography can be used as an important "rule-out" tool among high-risk patients with COVID-19 and should be integrated into their routine admission evaluation. However, its routine use among low-risk patients is not recommended.
Assuntos
COVID-19/complicações , Ecocardiografia/instrumentação , Cardiopatias/diagnóstico por imagem , Pneumopatias/diagnóstico por imagem , Ultrassonografia/instrumentação , Idoso , Ecocardiografia/normas , Feminino , Cardiopatias/etiologia , Hospitalização , Humanos , Pneumopatias/etiologia , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , SARS-CoV-2 , Ultrassonografia/normasRESUMO
BACKGROUND: Clinical risk assessment with quantitative formal risk scores may add to intuitive physician risk assessment and are advised by the international guidelines for the management of acute coronary syndrome (ACS) patients. Most previous studies have used the binary regression/classification approach (dead/alive) for long-term mortality post-ACS, without considering the time-to-event as in survival analysis. The use of machine learning (ML)-based survival models has yet to be validated. The primary objective was to compare survival prediction performance of 1-year mortality following ACS of two newly developed ML-based models [random survival forest (RSF) and deep learning (DeepSurv)] with the traditional Cox-proportional hazard (CPH) model. The secondary objective was external validation of the findings. METHODS: This was a retrospective, supervised learning data mining study based on the Acute Coronary Syndrome Israeli Survey (ACSIS) and the Myocardial Ischemia National Audit Project (MINAP). The ACSIS data were divided to train/test in a 70/30 fashion. Next, the models were externally validated on the MINAP data. Harrell's C-index, inverse probability of censoring weighting (IPCW), and the Brier-score were used for models' performance comparison. RESULTS: RSF performed best among the three models, with Harrell's C-index on training and testing sets reaching 0.953 and 0.924 respectively, followed by CPH multivariate selected model (0.805/0.849), CPH Univariate selected model (0.828/0.806), DeepSurv model (0.801/0.804), and the traditional CPH model (0.826/0.738). The RSF model also had the highest performance on the validation data set with 0.811 for Harrell's C-index, 0.844 for IPCW, and 0.093 for Brier score. The CPH model performance on the validation set had C-index range between 0.689 to 0.790, 0.713 to 0.826 for IPCW, and 0.094 to 0.103 Brier score. CONCLUSIONS: RSF survival predictions for long-term mortality post-ACS show improved model performance compared with the classic statistical method. This may benefit patients by allowing better risk stratification and tailored therapy, however further prospective evaluations are required.
Assuntos
Síndrome Coronariana Aguda , Humanos , Aprendizado de Máquina , Modelos de Riscos Proporcionais , Estudos Retrospectivos , Fatores de RiscoRESUMO
Constituting hypolipidemic and pleiotropic effects, statins stabilize coronary artery plaque and may prevent STEMI events. This study investigated the association between contemporary statin pretreatment intensity, low-density lipoprotein cholesterol (LDL-C) levels, and the type of acute coronary syndrome (ACS) presentation: STEMI vs. NSTE-ACS. Data were drawn from the ACS Israeli Survey (ACSIS), a biennial prospective national survey that took place in 2008-2018. The rate of STEMI vs. NSTE-ACS was calculated by statin use, including statin intensity (high-intensity statin therapy (HIST) and low-intensity statin therapy (LIST) prior to the index ACS event. Among 5103 patients, 2839 (56%) were statin-naive, 1389 (27%) used LIST and 875 (17%) used HIST. Statin pretreated patients were older and had a higher rates of co-morbidities, cardiovascular disease history and pretreatment with evidence-based medications. STEMI vs. NSTE-ACS was lower among HIST vs. LIST vs. statin-naive patients (31.0%, 37.8%, and 54.0%, respectively, p for trend < 0.001). Multivariate analysis revealed that HIST was independently associated with lower STEMI presentation (ORadj 0.70; 95% CI 0.57-0.86), while LIST (ORadj 0.92; 95% CI 0.77-1.10) and LDL-C < 70 mg/dL (ORadj 0.96; 95% CI 0.82-1.14) were not. In conclusion, among patients admitted with ACS, pretreatment with HIST was independently associated with a lower probability of STEMI presentation, while LIST and LDL-C < 70 mg/dL were not.
RESUMO
BACKGROUND: Limited data are available regarding the optimal management of patients with cancer in the acute myocardial infarction (AMI) setting. PATIENTS AND METHODS: We studied consecutive patients with AMI included in a national registry (years 2010, 2016) with the diagnosis of past or active malignancy and followed them for 1 year. RESULTS: Our cohort consisted of 2937 cancer-naive patients and 152 patients with cancer, of whom 35% presented with active malignancies. Compared with cancer-naive patients, patients with cancer were older, with female predominance, and presented more often with a history of hypertension and chronic kidney disease (P<0.001 for all comparisons). The rate of ST-elevation AMI was comparable (P=0.067). GRACE score more than 140 was more common in the cancer group (P<0.001). Most patients with cancer were referred to coronary angiography, though less than cancer-naive patients (87 vs. 93%; P=0.004). The rate of percutaneous coronary intervention was similar (P=0.265). Propensity score matching demonstrated similar rates of in-hospital complications between groups, and no mortality or major cardiac adverse event differences were noted at 30 days. Moreover, short-term mortality was similar between patients with active versus past malignancies, and between patients with solid and nonsolid tumors. However, cancer in patients with AMI was found to predict an increased mortality risk at 1 year by multivariable analysis (hazard ratio=2.52; P<0.001). CONCLUSION: Patients with cancer and AMI have a more complicated clinical presentation, yet their short-term prognosis is similar to cancer-naive patients. Nevertheless, 1-year outcome is worse.
Assuntos
Infarto do Miocárdio/terapia , Neoplasias/terapia , Fatores Etários , Idoso , Idoso de 80 Anos ou mais , Comorbidade , Feminino , Nível de Saúde , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Infarto do Miocárdio/diagnóstico , Infarto do Miocárdio/mortalidade , Neoplasias/diagnóstico , Neoplasias/mortalidade , Prognóstico , Sistema de Registros , Estudos Retrospectivos , Medição de Risco , Fatores de Risco , Fatores Sexuais , Fatores de TempoRESUMO
Family history of premature cardiovascular disease (FHpCVD) is a well-established risk factor for development of coronary artery disease. However, little is known about the impact of FHpCVD on the outcome of patients presenting with acute coronary syndrome (ACS). We therefore aimed to evaluate the outcomes of ACS patients grouped by the presence and/or absence of FHpCVD. All patients ≤65 at admission who had an ACS event and were enrolled in the national ACS Israel Survey registry from 2000 to 2013 were included. Patients were grouped by the presence or absence of self-reported FHpCVD. Nearest neighbor propensity score matching was applied to create an evenly matched cohort of patients. Outcomes included 30-day MACE (defined as the composite of death, unstable angina pectoris, myocardial infarction, stroke, stent thrombosis, and urgent revascularization) and its individual components. Of 7,173 ACS patients, 33.9% reported FHpCVD. These patients were younger, with lower prevalence of diabetes, previous cerebrovascular and kidney diseases, but had higher prevalence of smoking and hyperlipidemia (p <0.001 for each). The propensity score-matching cohort included 1,793 pairs of evenly matched patients. The rate of 30-day MACE did not differ in the groups, as well as 1-year mortality (2.4% vs 2.2%, with vs without FHpCVD, respectively). During long-term follow-up (median 7.6 years), mortality rate was lower in the FHpCVD group (hazard ratio 0.82, 95% confidence intervals 0.69 to 0.99). In conclusion, we observed no differences in short- and intermediate-term outcomes based on the presence and/or absence of FHpCVD. However, patients with FHpCVD had better long-term survival.
Assuntos
Síndrome Coronariana Aguda/genética , Doenças Cardiovasculares/genética , Síndrome Coronariana Aguda/mortalidade , Síndrome Coronariana Aguda/terapia , Adolescente , Adulto , Fatores Etários , Idoso , Feminino , Predisposição Genética para Doença , Inquéritos Epidemiológicos , Hospitalização , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Pontuação de Propensão , Sistema de Registros , Fatores de Risco , Autorrelato , Taxa de SobrevidaRESUMO
High-grade atrioventricular block (HAVB) is a frequent complication of acute myocardial infarction (AMI) and is associated with increased morbidity and mortality. We aimed to evaluate the incidence, predictors, and prognostic significance of HAVB in a contemporary cohort of patients with AMI, in the recent era of early reperfusion. Patients with acute coronary syndromes (n=11,487) during the years 2000-2010 were included. Patients were divided into two groups: with HAVB (n=308, 2.7%) and without HAVB (n=11,179, 97.3%). The incidence of HAVB decreased from 4.2% in 2000 to 2.1% in 2010 (p for trend<0.01). Patients with HAVB were more likely to develop in-hospital complications. Independent predictors of developing HAVB were older age, ST-elevation myocardial infarction (STEMI), smoking and Killip class≥2 on admission. 30-day and 1-year mortality rates were significantly higher in the HAVB as compared to the non-HAVB group (24% vs. 4.9%, p<0.01, 33.5% vs. 10%, p<0.01, respectively). Multivariable logistic regression analysis revealed that, HAVB was associated with increased 30-day (OR - 3.97; 95% CI - 1.96-8.04) and 1-year mortality risk (HR - 2.02; 95% CI - 1.3-3.1). Similar estimates were obtained for STEMI and non-STEMI (NSTEMI). In conclusion, although the incidence of HAVB decreased over the last decade, the associated morbidity and mortality are still high in these patients despite early reperfusion therapy.
Assuntos
Bloqueio Atrioventricular/etiologia , Infarto do Miocárdio/complicações , Idoso , Bloqueio Atrioventricular/mortalidade , Bloqueio Atrioventricular/fisiopatologia , Bloqueio Atrioventricular/terapia , Feminino , Mortalidade Hospitalar , Humanos , Incidência , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Prognóstico , Estudos Prospectivos , Fatores de RiscoRESUMO
BACKGROUND: Ischemic time has prognostic importance in ST-elevation myocardial infarction patients. Mobile intensive care unit use can reduce components of total ischemic time by appropriate triage of ST-elevation myocardial infarction patients. METHODS: Data from the Acute Coronary Survey in Israel registry 2000-2010 were analyzed to evaluate factors associated with mobile intensive care unit use and its impact on total ischemic time and patient outcomes. RESULTS: The study comprised 5474 ST-elevation myocardial infarction patients enrolled in the Acute Coronary Survey in Israel registry, of whom 46% ( n=2538) arrived via mobile intensive care units. There was a significant increase in rates of mobile intensive care unit utilization from 36% in 2000 to over 50% in 2010 ( p<0.001). Independent predictors of mobile intensive care unit use were Killip>1 (odds ratio=1.32, p<0.001), the presence of cardiac arrest (odds ratio=1.44, p=0.02), and a systolic blood pressure <100 mm Hg (odds ratio=2.01, p<0.001) at presentation. Patients arriving via mobile intensive care units benefitted from increased rates of primary reperfusion therapy (odds ratio=1.58, p<0.001). Among ST-elevation myocardial infarction patients undergoing primary reperfusion, those arriving by mobile intensive care unit benefitted from shorter median total ischemic time compared with non-mobile intensive care unit patients (175 (interquartile range 120-262) vs 195 (interquartile range 130-333) min, respectively ( p<0.001)). Upon a multivariate analysis, mobile intensive care unit use was the most important predictor in achieving door-to-balloon time <90 min (odds ratio=2.56, p<0.001) and door-to-needle time <30 min (odds ratio=2.96, p<0.001). One-year mortality rates were 10.7% in both groups (log-rank p-value=0.98), however inverse propensity weight model, adjusted for significant differences between both groups, revealed a significant reduction in one-year mortality in favor of the mobile intensive care unit group (odds ratio=0.79, 95% confidence interval (0.66-0.94), p=0.01). CONCLUSIONS: Among patients with ST-elevation myocardial infarction, the utilization of mobile intensive care units is associated with increased rates of primary reperfusion, a reduction in the time interval to reperfusion, and a reduction in one-year adjusted mortality.
Assuntos
Síndrome Coronariana Aguda/complicações , Ambulâncias/estatística & dados numéricos , Sistema de Registros , Infarto do Miocárdio com Supradesnível do Segmento ST/diagnóstico , Inquéritos e Questionários , Tempo para o Tratamento/tendências , Síndrome Coronariana Aguda/diagnóstico , Síndrome Coronariana Aguda/epidemiologia , Angiografia Coronária , Eletrocardiografia , Feminino , Seguimentos , Mortalidade Hospitalar/tendências , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Razão de Chances , Estudos Retrospectivos , Infarto do Miocárdio com Supradesnível do Segmento ST/epidemiologia , Infarto do Miocárdio com Supradesnível do Segmento ST/etiologia , Taxa de Sobrevida/tendênciasRESUMO
BACKGROUND: Risk scores for prediction of mortality 30-days following a ST-segment elevation myocardial infarction (STEMI) have been developed using a conventional statistical approach. OBJECTIVE: To evaluate an array of machine learning (ML) algorithms for prediction of mortality at 30-days in STEMI patients and to compare these to the conventional validated risk scores. METHODS: This was a retrospective, supervised learning, data mining study. Out of a cohort of 13,422 patients from the Acute Coronary Syndrome Israeli Survey (ACSIS) registry, 2782 patients fulfilled inclusion criteria and 54 variables were considered. Prediction models for overall mortality 30days after STEMI were developed using 6 ML algorithms. Models were compared to each other and to the Global Registry of Acute Coronary Events (GRACE) and Thrombolysis In Myocardial Infarction (TIMI) scores. RESULTS: Depending on the algorithm, using all available variables, prediction models' performance measured in an area under the receiver operating characteristic curve (AUC) ranged from 0.64 to 0.91. The best models performed similarly to the Global Registry of Acute Coronary Events (GRACE) score (0.87 SD 0.06) and outperformed the Thrombolysis In Myocardial Infarction (TIMI) score (0.82 SD 0.06, p<0.05). Performance of most algorithms plateaued when introduced with 15 variables. Among the top predictors were creatinine, Killip class on admission, blood pressure, glucose level, and age. CONCLUSIONS: We present a data mining approach for prediction of mortality post-ST-segment elevation myocardial infarction. The algorithms selected showed competence in prediction across an increasing number of variables. ML may be used for outcome prediction in complex cardiology settings.
Assuntos
Síndrome Coronariana Aguda/epidemiologia , Algoritmos , Mineração de Dados/métodos , Aprendizado de Máquina , Sistema de Registros , Infarto do Miocárdio com Supradesnível do Segmento ST/mortalidade , Inquéritos e Questionários , Idoso , Feminino , Mortalidade Hospitalar/tendências , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Prognóstico , Curva ROC , Estudos Retrospectivos , Medição de Risco , Fatores de Risco , Taxa de Sobrevida/tendênciasRESUMO
BACKGROUND: Young women are usually protected against coronary artery disease due to hormonal and risk-factor profile. Previous studies have suggested poorer outcome in women hospitalized with acute coronary syndrome as compared with men. However, when adjusted for age and other risk factors, this difference does not remain significant. We compared the risk profile and outcome between young (≤55 years) women and men admitted with acute coronary syndrome. METHODS: We analyzed clinical characteristics, management strategies, and outcomes of men and women ≤55 years of age enrolled in the biennial Acute Coronary Syndrome Israeli Surveys between 2000 and 2013. RESULTS: Among 11,536 patients enrolled, 3949 (34%) were ≤55 years old (407 women, 3542 men). Women were slightly older (48.9 ± 5.7 vs 48.3 ± 5.5, P = .007) and suffered more from diabetes (34% vs 24%) and hypertension (47% vs 37%, P <.001 for both). Rates of prior myocardial infarction were high in both sexes (18% vs 21%). Women presented less often with ST-elevation myocardial infarction (50% vs 57%, P = .007) and with typical chest pain (73% vs 80%, P = .004), and had higher rates of Global Registry of Acute Coronary Events (GRACE) score ≥140 (19% vs 12%, P = .007). After adjustment for GRACE score, diabetes, and enrollment year, women had a lower likelihood to undergo coronary angiography during hospitalization (odds ratio 0.6, P = .007). Female sex was independently associated with higher risk of in-hospital mortality (hazard ratio [HR] 4.1; 95% confidence interval [CI], 1.15-14.0), 30-day major adverse cardiac and cerebral events (HR 2.1; 95% CI, 1.31-3.36), and 5-year mortality (HR 1.96; 95% CI, 1.3-2.8). CONCLUSIONS: Young women admitted with acute coronary syndrome are a unique high-risk group that presents a diagnostic challenge for clinicians. Women receive less invasive therapy during hospitalization and have worse in-hospital and long-term outcomes.
Assuntos
Síndrome Coronariana Aguda , Angiografia Coronária/estatística & dados numéricos , Gerenciamento Clínico , Hospitalização/estatística & dados numéricos , Síndrome Coronariana Aguda/diagnóstico , Síndrome Coronariana Aguda/epidemiologia , Síndrome Coronariana Aguda/terapia , Adulto , Comorbidade , Feminino , Inquéritos Epidemiológicos/estatística & dados numéricos , Mortalidade Hospitalar , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Avaliação de Processos e Resultados em Cuidados de Saúde , Modelos de Riscos Proporcionais , Fatores de Risco , Fatores SexuaisRESUMO
OBJECTIVE: Patients with diabetes mellitus (DM) presenting with acute coronary syndrome (ACS) and undergoing percutaneous coronary intervention (PCI) derived enhanced benefit with dual antiplatelet therapy (DAPT) with prasugrel vs. clopidogrel. The risk profile and treatment response to DAPT for medically managed ACS patients with DM remains uncertain. METHODS: The TRILOGY ACS trial compared aspirin + prasugrel vs. aspirin + clopidogrel for up to 30months in non-ST-segment elevation (NSTE) ACS patients managed medically without revascularization. We compared treatment-related outcomes among 3539 patients with DM vs. 5767 patients without DM. The primary endpoint was a composite of cardiovascular death, myocardial infarction, or stroke. RESULTS: Patients with vs. without DM were younger, more commonly female, heavier, and more often had revascularization prior to the index ACS event. The frequency of the primary endpoint through 30months was higher among patients with vs. without DM (24.8% vs. 16.3%), with a higher risk for those patients with DM treated with insulin vs. those treated without insulin (35.3% vs. 19.9%). There was no significant difference in the frequency of the primary endpoint by treatment with prasugrel vs. clopiodgrel in those with or without DM (Pint=0.82) and with or without insulin treatment among those with DM (Pint=0.304). CONCLUSIONS: Among NSTE ACS patients managed medically without revascularization, patients with DM had a higher risk of ischemic events that was amplified among those treated with insulin. There was no differential treatment effect with a more potent DAPT regimen of aspirin + prasugrel vs. aspirin + clopidogrel.
Assuntos
Síndrome Coronariana Aguda/tratamento farmacológico , Aspirina/administração & dosagem , Diabetes Mellitus/tratamento farmacológico , Cloridrato de Prasugrel/administração & dosagem , Ticlopidina/análogos & derivados , Idoso , Clopidogrel , Relação Dose-Resposta a Droga , Método Duplo-Cego , Quimioterapia Combinada , Eletrocardiografia , Feminino , Seguimentos , Humanos , Masculino , Revascularização Miocárdica , Inibidores da Agregação Plaquetária/administração & dosagem , Ticlopidina/administração & dosagem , Fatores de Tempo , Resultado do TratamentoRESUMO
OBJECTIVE: To assess the real-world use, clinical outcomes, and adherence to novel P2Y12 inhibitors. METHODS: We evaluated 1,093 consecutive acute myocardial infarction patients undergoing a percutaneous intervention. Patients were derived from a prospective, multicenter, nationwide registry and were followed for 30 days; 381 patients (35%) received clopidogrel, 468 (43%) received prasugrel, and 244 (22%) received ticagrelor. Patients treated with clopidogrel were older and more likely to suffer from chronic renal failure and stroke and/or present with non-ST-elevation myocardial infarction (NSTEMI) (p < 0.01 for all). Independent predictors of undertreatment with novel P2Y12 inhibitors included: older age (OR 0.17; 95% CI 0.1-0.27, p < 0.0001), a prior stroke (OR 0.41; 95% CI 0.2-0.68, p = 0.008), and NSTEMI (OR 0.37; 95% CI 0.26-0.54, p < 0.0001). RESULTS: Novel P2Y12 inhibitors were associated with a lower incidence of cardiovascular events, major bleeding, and/or death (7.6 vs.11%, HR 0.67; 95% CI 0.43-1, p = 0.05). However, after a multivariate analysis this trend was not statistically significant. Patients discharged with ticagrelor versus thienopyridines demonstrated a higher rate of crossover to other P2Y12 inhibitors (11 vs. 5%, p = 0.03). CONCLUSIONS: In a real-world cohort, there was an underutilization of novel P2Y12 inhibitors which was more pronounced in higher-risk subsets that might benefit from novel P2Y12 inhibitors at least as much as other patients.
Assuntos
Adenosina/análogos & derivados , Infarto do Miocárdio/tratamento farmacológico , Inibidores da Agregação Plaquetária/uso terapêutico , Cloridrato de Prasugrel/uso terapêutico , Antagonistas do Receptor Purinérgico P2Y/uso terapêutico , Adenosina/uso terapêutico , Idoso , Clopidogrel , Terapia Combinada , Uso de Medicamentos/estatística & dados numéricos , Feminino , Humanos , Masculino , Pessoa de Meia-Idade , Infarto do Miocárdio/terapia , Intervenção Coronária Percutânea , Estudos Prospectivos , Ticagrelor , Ticlopidina/análogos & derivados , Ticlopidina/uso terapêuticoRESUMO
OBJECTIVE: We investigated whether prior clopidogrel influenced long-term ischaemic and bleeding risks and modified the randomised treatment effect of clopidogrel versus prasugrel among medically managed patients with acute coronary syndromes (ACS) treated with dual antiplatelet therapy. METHODS: Medically managed patients with ACS in the Targeted Platelet Inhibition to Clarify the Optimal Strategy to Medically Manage Acute Coronary Syndromes (TRILOGY ACS) trial were randomised to clopidogrel versus prasugrel (plus aspirin), stratified by prior clopidogrel use. From the analysis population (n=8927), we compared two groups: 'clopidogrel in-hospital (n=6513)' (clopidogrel started ≤72â h of presentation for index ACS event) and 'prior-clopidogrel (n=2414)' (on clopidogrel ≥5â days before index hospitalisation). Treatment-related differences in ischaemic (all-cause death, cardiovascular (CV) death, myocardial infarction (MI), stroke and the composite of CV death/MI/stroke) and bleeding outcomes (severe/life-threatening or moderate bleeding events based on Global Use of Strategies to Open Occluded Coronary Arteries (GUSTO) criteria) through 30â months were analysed between patients in the two groups. RESULTS: Compared with 'clopidogrel in-hospital,' 'prior clopidogrel' patients were younger (median 64â years vs 66â years, p<0.001), more likely to have prior CV events/revascularisation, and had a higher frequency of CV death, MI or stroke through 30â months (20.8% vs 18.2%, p=0.002), with no difference in bleeding events (2.3% vs 3.4%, p=0.50). Randomised treatment effect (prasugrel vs clopidogrel) was similar for ischaemic and bleeding outcomes in both groups (all pinteraction>0.05). CONCLUSIONS: Patients receiving clopidogrel before admission for ACS and subsequently treated only medically are at higher risk for CV events versus those not previously receiving clopidogrel. More potent antiplatelet inhibition with prasugrel versus clopidogrel did not significantly reduce this risk. TRIAL REGISTRATION NUMBER: NCT00699998.
Assuntos
Síndrome Coronariana Aguda/tratamento farmacológico , Inibidores da Agregação Plaquetária/administração & dosagem , Ticlopidina/análogos & derivados , Síndrome Coronariana Aguda/complicações , Síndrome Coronariana Aguda/diagnóstico , Síndrome Coronariana Aguda/mortalidade , Idoso , Aspirina/administração & dosagem , Clopidogrel , Método Duplo-Cego , Esquema de Medicação , Quimioterapia Combinada , Feminino , Hemorragia/induzido quimicamente , Hospitalização , Humanos , Estimativa de Kaplan-Meier , Masculino , Pessoa de Meia-Idade , Infarto do Miocárdio/etiologia , Inibidores da Agregação Plaquetária/efeitos adversos , Cloridrato de Prasugrel/administração & dosagem , Modelos de Riscos Proporcionais , Medição de Risco , Fatores de Risco , Acidente Vascular Cerebral/etiologia , Ticlopidina/administração & dosagem , Ticlopidina/efeitos adversos , Fatores de Tempo , Resultado do TratamentoRESUMO
BACKGROUND: STEMI is thought to occur as a result of a vulnerable coronary plaque rupture. Statins possess hypolipidemic and pleotropic effects that stabilize coronary plaque. We sought to determine the association between LDL-C levels, statin use prior to the index event on the type of acute coronary syndrome (ACS) presentation: STEMI vs. non-STEMI/unstable angina. METHODS: Data was drawn from the ACS Israeli Survey (ACSIS), a biennial prospective survey of ACS patients hospitalized in all CCU/Cardiology departments during 2002-2010. RESULTS: Among 6790 patients, 2760 (41%) reported statin use prior to the index ACS event. The proportion of STEMI was significantly lower among statin treated vs. statin naive patients (36% vs. 57%, p<0.0001). At each LDL-C level, the proportion of STEMI was significantly lower only among statin treated patients (p<0.0001). LDL-C<70 mg/dL was associated with a lower proportion of STEMI only among statin treated but not among statin naive patients (33% vs. 57%, p<0.0001). Multivariate analysis revealed that statin use was independently associated with a lower probability of presenting with STEMI (ORadj=0.73, p=0.007), but not LDL-C<70 mg/dL (ORadj=1.13, p=0.32). Patients on high-intensity statin therapy (HIST) were less likely to present with STEMI as compared with low-intensity statin therapy (LIST) or statin naive patients (27%, 38%, 56%, respectively, p for trend <0.0001; HIST ORadj=0.28, p=0.01; LIST ORadj=0.48, p=0.026). CONCLUSIONS: Among patients admitted with ACS, statin use but not LDL-C level, was associated with a lower probability of presenting with STEMI. Patients on HIST had the lowest likelihood of presenting with STEMI.
Assuntos
Síndrome Coronariana Aguda/sangue , Síndrome Coronariana Aguda/tratamento farmacológico , LDL-Colesterol/sangue , Inibidores de Hidroximetilglutaril-CoA Redutases/uso terapêutico , Infarto do Miocárdio com Supradesnível do Segmento ST/sangue , Infarto do Miocárdio com Supradesnível do Segmento ST/tratamento farmacológico , Síndrome Coronariana Aguda/epidemiologia , Idoso , Feminino , Seguimentos , Humanos , Israel/epidemiologia , Masculino , Pessoa de Meia-Idade , Estudos Prospectivos , Infarto do Miocárdio com Supradesnível do Segmento ST/epidemiologia , Inquéritos e QuestionáriosRESUMO
AIM: To evaluate the incidence and prognostic implications of ventricular tachyarrhythmias (VTAs) complicating acute myocardial infarction (MI). METHODS AND RESULTS: We evaluated 7669 MI patients [ST elevation (n = 3573) and non-ST-elevation acute coronary syndrome (ACS) (n = 4096)] from the Acute Coronary Syndrome Israeli Survey for the incidence of VTA. Ventricular tachyarrhythmia occurred in 3.8% of patients [2.1% early (≤ 48 h) and 1.7% late (>48 h) VTA]. In-hospital mortality rates were higher for patients with VTA when compared with patients with no VTA (P < 0.001). Consistent with these findings, multivariable analysis demonstrated that early and late VTAs were associated with increased risk of in-hospital death [hazard ratio (HR) = 3.84; 95% confidence interval (CI) 1.77-6.78, P < 0.001, and HR = 8.23; 95% CI 4.84-13.98, P < 0.001, respectively]. In contrast, post-discharge outcomes demonstrated that only late VTA was independently associated with a significant increased risk of 30-day mortality (HR = 5.17; 95% CI 1.54-17.27, P = 0.007) with a trend towards an increased 1-year mortality risk (HR = 1.69; 95% CI 0.79-3.62, P = 0.17). The long-term risk associated with in-hospital VTA was driven by sustained ventricular tachycardia (VT) (HR = 3.28; 95% CI 1.92-5.60, P < 0.001) but not ventricular fibrillation (HR = 1.27; 95% CI 0.65-2.49, P = 0.47). CONCLUSIONS: Our findings suggest that in patients with ACS, both early and late VTAs are associated with an increased risk of in-hospital mortality. However, only late VTA, mostly sustained VT, is associated with long-term adverse outcome.