scholarly journals Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium, and epicardial adipose tissue: a prospective study

2019 ◽  
Vol 116 (14) ◽  
pp. 2216-2225 ◽  
Author(s):  
Frederic Commandeur ◽  
Piotr J Slomka ◽  
Markus Goeller ◽  
Xi Chen ◽  
Sebastien Cadet ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Risk Assessment ◽  
Adipose Tissue ◽  
Cardiac Death ◽  
Epicardial Adipose Tissue ◽  
Ascvd Risk ◽  
Asymptomatic Subjects

Abstract Aims Our aim was to evaluate the performance of machine learning (ML), integrating clinical parameters with coronary artery calcium (CAC), and automated epicardial adipose tissue (EAT) quantification, for the prediction of long-term risk of myocardial infarction (MI) and cardiac death in asymptomatic subjects. Methods and results Our study included 1912 asymptomatic subjects [1117 (58.4%) male, age: 55.8 ± 9.1 years] from the prospective EISNER trial with long-term follow-up after CAC scoring. EAT volume and density were quantified using a fully automated deep learning method. ML extreme gradient boosting was trained using clinical co-variates, plasma lipid panel measurements, risk factors, CAC, aortic calcium, and automated EAT measures, and validated using repeated 10-fold cross validation. During mean follow-up of 14.5 ± 2 years, 76 events of MI and/or cardiac death occurred. ML obtained a significantly higher AUC than atherosclerotic cardiovascular disease (ASCVD) risk and CAC score for predicting events (ML: 0.82; ASCVD: 0.77; CAC: 0.77, P < 0.05 for all). Subjects with a higher ML score (by Youden’s index) had high hazard of suffering events (HR: 10.38, P < 0.001); the relationships persisted in multivariable analysis including ASCVD-risk and CAC measures (HR: 2.94, P = 0.005). Age, ASCVD-risk, and CAC were prognostically important for both genders. Systolic blood pressure was more important than cholesterol in women, and the opposite in men. Conclusions In this prospective study, machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death compared with standard clinical risk assessment. Following further validation, such a personalized paradigm could potentially be used to improve cardiovascular risk assessment.

30Machine learning to predict the long-term risk of myocardial infarction and cardiac death based on clinical risk, coronary calcium and epicardial adipose tissue: a prospective study

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
F C Commandeur ◽  
P J Slomka ◽  
M Goeller ◽  
X Chen ◽  
S Cadet ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Adipose Tissue ◽  
Cardiac Death ◽  
Epicardial Adipose Tissue ◽  
Long Term Follow Up ◽  
Ascvd Risk ◽  
Asymptomatic Subjects

Abstract Background/Introduction Machine learning (ML) allows objective integration of clinical and imaging data for the prediction of events. ML prediction of cardiovascular events in asymptomatic subjects over long-term follow-up, utilizing quantitative CT measures of coronary artery calcium (CAC) and epicardial adipose tissue (EAT) have not yet been evaluated. Purpose To analyze the ability of machine learning to integrate clinical parameters with coronary calcium and EAT quantification in order to improve prediction of myocardial infarction (MI) and cardiac death in asymptomatic subjects. Methods We assessed 2071 consecutive subjects [1230 (59%) male, age: 56.049.03] from the EISNER (Early Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) trial with long-term follow-up after non-enhanced cardiac CT. CAC (Agatston) score, age-and-gender-adjusted CAC percentile, and aortic calcium scores were obtained. EAT volume and density were quantified using a fully automated deep learning method. Extreme gradient boosting, a ML algorithm, was trained using demographic variables, plasma lipid panel measurements, risk factors as well as CAC, aortic calcium and EAT measures from CAC CT scans. ML was validated using 10-fold cross validation; event prediction was evaluated using area-under-receiver operating characteristic curve (AUC) analysis and Cox proportional hazards regression. Optimal ML cut-point for risk of MI and cardiac death was determined by highest Youden's index (sensitivity + specificity – 1). Results At 152 years' follow-up, 76 events of MI and/or cardiac death had occurred. ML obtained a significantly higher AUC than the ASCVD risk and CAC score in predicting events (ML: 0.81; ASCVD: 0.76, p<0.05; CAC: 0.75, p<0.01, Figure A). ML performance was mostly driven by age, ASCVD risk and calcium as shown by the variable importance (Figure B); however, all variables with non-zero gain contributed to the ML performance. ML achieved a sensitivity and specificity of 77.6% and 73.5%, respectively. For an equal specificity, ASCVD and CAC scores obtained a sensitivity of 61.8% and 67.1%, respectively. High ML risk was associated with a high risk of suffering an event by Cox regression (HR: 9.25 [95% CI: 5.39–15.87], p<0.001; survival curves in Figure C). The relationships persisted when adjusted for age, gender, CAC, CAC percentile, aortic calcium score, and ASCVD risk score; with a hazard ratio of 3.42 for high ML risk (HR: 3.42 [95% CI: 1.54–7.57], p=0.002). Conclusion(s) Machine learning used to integrate clinical and quantitative imaging-based variables significantly improves prediction of MI and cardiac death in asymptomatic subjects undergoing CAC assessment, compared to standard risk assessment methods. Acknowledgement/Funding NHLBI 1R01HL13361, Bundesministerium für Bildung und Forschung (01EX1012B), Dr. Miriam and Sheldon G. Adelson Medical Research Foundation

scholarly journals METABOLIC SYNDROME AND AUTOMATED EPICARDIAL ADIPOSE TISSUE MEASURES PREDICT LONG-TERM RISK OF CARDIAC EVENTS IN ASYMPTOMATIC SUBJECTS

2020 ◽  
Vol 75 (11) ◽  
pp. 1717
Author(s):  
Andrew Lin ◽  
Nathan D. Wong ◽  
Frederic Commandeur ◽  
Sebastien Cadet ◽  
Heidi Gransar ◽  
...  
Keyword(s):  
Metabolic Syndrome ◽  
Adipose Tissue ◽  
Epicardial Adipose Tissue ◽  
Cardiac Events ◽  
Asymptomatic Subjects

scholarly journals Long-term impact of chronic total occlusion recanalisation in patients with ST-elevation myocardial infarction

Heart ◽  
2018 ◽  
Vol 104 (17) ◽  
pp. 1432-1438 ◽  
Author(s):  
Joëlle Elias ◽  
Ivo M van Dongen ◽  
Truls Råmunddal ◽  
Peep Laanmets ◽  
Erlend Eriksen ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Cardiac Death ◽  
Chronic Total Occlusion ◽  
Randomised Trial ◽  
Left Ventricular ◽  
Total Occlusion ◽  
St Elevation ◽  
One Year

BackgroundDuring primary percutaneous coronary intervention (PCI), a concurrent chronic total occlusion (CTO) is found in 10% of patients with ST-elevation myocardial infarction (STEMI). Long-term benefits of CTO-PCI have been suggested; however, randomised data are lacking. Our aim was to determine mid-term and long-term clinical outcome of CTO-PCI versus CTO-No PCI in patients with STEMI with a concurrent CTO.MethodsThe Evaluating Xience and left ventricular function in PCI on occlusiOns afteR STEMI (EXPLORE) was a multicentre randomised trial that included 302 patients with STEMI after successful primary PCI with a concurrent CTO. Patients were randomised to either CTO-PCI or CTO-No PCI. The primary end point of the current study was occurrence of major adverse cardiac events (MACE): cardiac death, coronary artery bypass grafting and MI. Other end points were 1-year left ventricular function (LVF); LV-ejection fraction and LV end-diastolic volume and angina status.ResultsThe median long-term follow-up was 3.9 (2.1–5.0) years. MACE was not significantly different between both arms (13.5% vs 12.3%, HR 1.03, 95% CI 0.54 to 1.98; P=0.93). Cardiac death was more frequent in the CTO-PCI arm (6.0% vs 1.0%, P=0.02) with no difference in all-cause mortality (12.9% vs 6.2%, HR 2.07, 95% CI 0.84 to 5.14; P=0.11). One-year LVF did not differ between both arms. However, there were more patients with freedom of angina in the CTO-PCI arm at 1 year (94% vs 87%, P=0.03).ConclusionsIn this randomised trial involving patients with STEMI with a concurrent CTO, CTO-PCI was not associated with a reduction in long-term MACE compared to CTO-No PCI. One-year LVF was comparable between both treatment arms. The finding that there were more patients with freedom of angina after CTO-PCI at 1-year follow-up needs further investigation.Clinical trial registrationEXPLORE trial number NTR1108 www.trialregister.nl.

scholarly journals 56. Long-Term Cardiovascular Outcomes After Drug-Related vs Non-Drug-Related Infective Endocarditis

2021 ◽  
Vol 8 (Supplement_1) ◽  
pp. S39-S40
Author(s):  
Brandon Muncan ◽  
Aikaterini Papamanoli ◽  
Hal A Skopicki ◽  
Andreas Kalogeropoulos
Keyword(s):  
Myocardial Infarction ◽  
Heart Failure ◽  
Ischemic Stroke ◽  
Drug Use ◽  
Cardiac Death ◽  
First Episode ◽  
Kaplan Meier ◽  
Icd 10

Abstract Background Drug use-related infective endocarditis (IE) has nearly doubled in the past two decades in the United States, largely due to the current opioid crisis. Although there are robust data on surgical outcomes for people who use drugs (PWUD) vs. non-PWUD patients after an initial encounter for IE, long-term comparative data on post-IE outcomes are relatively sparse. Methods Using data from the TriNetX electronic health records network, we identified (1) a cohort of patients 16 to 64 years old who had a first encounter for IE (captured with ICD-10 codes I33, I38, or I39) and history of drug use (captured with ICD-10 codes F11, F13-F16, F18, F19, O99.32, or T40) preceding the IE episode and (2) a propensity score-matched cohort of patients age 16-64 who had a first episode of IE and no documented drug use. We compared the post-IE incidence of (1) mortality; (2) ischemic stroke; (3) intracranial hemorrhage; (4) myocardial infarction; (5) heart failure; and (6) sudden cardiac death (cardiac arrest or ventricular fibrillation or tachycardia) between the 2 cohorts over a 5-year follow up period. We matched the cohorts for demographic data and clinically relevant medical history. We used Kaplan-Meier estimates and Cox models to compare incidence. Results We identified 6,578 PWUD patients and 6,578 matched non-PWUD patients 16-64 years old with a first episode of IE. The baseline characteristics are summarized in Table 1. Standardized mean differences of characteristics were generally &lt; 0.1, indicating adequate matching. The 5-year Kaplan-Meier rates of outcomes of interest are summarized in Table 2. Mortality did not differ between cohorts. However, the incidence of ischemic stroke and intracranial hemorrhage was consistently higher among PWUD throughout the 5-year follow-up. Rates of myocardial infarction were also higher among PWUD; however, the difference was more pronounced later during follow-up. Rates of heart failure and sudden cardiac death did not differ. Conclusion Cardiovascular events after IE were common among both PWUD and non-PWUD patients over a 5-year follow-up period. However, rates of ischemic and hemorrhagic stroke were consistently higher among PWUD. Further investigation is needed to elucidate the sources of elevated stroke risk among PWUD and identify targets for intervention. Disclosures All Authors: No reported disclosures

scholarly journals The Natural history of Epicardial Adipose Tissue Volume and Attenuation: A long-term prospective cohort follow-up study

2020 ◽  
Vol 10 (1) ◽  
Author(s):  
Nitesh Nerlekar ◽  
Udit Thakur ◽  
Andrew Lin ◽  
Ji Quan Samuel Koh ◽  
Elizabeth Potter ◽  
...  
Keyword(s):  
Adipose Tissue ◽  
Natural History ◽  
Prospective Cohort ◽  
Epicardial Adipose Tissue ◽  
Tissue Volume ◽  
Follow Up Study ◽  
History Of ◽  
Adipose Tissue Volume

5193Percutaneous coronary intervention provided better result than optimal medical therapy in patients with chronic total occlusion: a metanalysis

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
D Khanra ◽  
B Duggal ◽  
I Basu Ray ◽  
B Kumar ◽  
R Walia
Keyword(s):  
Myocardial Infarction ◽  
Cardiac Death ◽  
Chronic Total Occlusion ◽  
Meta Analysis ◽  
Statistical Significance ◽  
Coronary Intervention ◽  
Total Occlusion ◽  
All Cause Mortality

Abstract Background Studies comparing the outcome of percutaneous coronary intervention (PCI) along with optimal medical therapy (OMT) versus OMT alone in treatment of chronic total occlusion (CTO) are limited by observational design, variable follow up period, diverse clinical outcome, high drop-out and cross-over rate. Prematurely terminated DECISION CTO trail and the promising result of the most recent EUROCTO trial still left the quest unanswered. Previous metanalysis on the present context were restricted to studies with propensity-matched analysis only and did not incorporate the recent randomized trials. Purpose This study aims to conduct a meta-analysis of published data of observational as well as randomized studies comparing long term outcomes of PCI+OMT versus OMT alone. Methods The present protocol is registered in PROSPERO. PubMed, Embase and Cochrane databases were systematically reviewed. Fourteen studies meeting criteria were included in the meta-analysis. The Cochrane Risk of Bias scale was used to appraise the overall quality of the studies. Revman 5.3 software was used to analyse the data and random-effects model with inverse variance method was undertaken. R packages were used for assessment of bias and metaregression. Results Baseline parameters of both the groups were comparable. Major adverse cardiovascular events (MACE) which comprises of cardiac death, myocardial infarction, stroke, and unplanned revascularization [Figure 1] were significantly lower in the PCI+OMT group. (RR: 0.77; 95% CI: 0.61 to 0.97; P≤0.ehz746.00521; I2=85%). High heterogeneity was partially (14%) explained by age factor. However study design, follow up duration, LVEF, presence of TVD did not attribute significantly to heterogeneity, in isolation or any combination in metregression model. All cause mortality and cardiac death [Figure 2, 3 respectively] were significantly lower in the PCI+OMT group (P=0.29, p=0.63, respectively). Myocardial infarction (P=0.25) and stroke rates (P=0.15) were lower in the PCI+OMT group, however they did not reach statistical significance. Unplanned revascularization (of any vessel) showed a higher trend in the PCI+OMT group, without reaching statistical significance (P=0.46, I2=88%). Conclusion PCI of CTO is rewarded with better long term outcome, in terms of MACE and all-cause mortality but limited to greater unplanned revascularization. Acknowledgement/Funding None

scholarly journals Metabolic syndrome, fatty liver, and artificial intelligence-based epicardial adipose tissue measures predict long-term risk of cardiac events: a prospective study

2021 ◽  
Vol 20 (1) ◽  
Author(s):  
Andrew Lin ◽  
Nathan D. Wong ◽  
Aryabod Razipour ◽  
Priscilla A. McElhinney ◽  
Frederic Commandeur ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Metabolic Syndrome ◽  
Adipose Tissue ◽  
Fatty Liver ◽  
Risk Score ◽  
Epicardial Adipose Tissue ◽  
Imaging Biomarkers ◽  
Ascvd Risk ◽  
Asymptomatic Individuals

Abstract Background We sought to evaluate the association of metabolic syndrome (MetS) and computed tomography (CT)-derived cardiometabolic biomarkers (non-alcoholic fatty liver disease [NAFLD] and epicardial adipose tissue [EAT] measures) with long-term risk of major adverse cardiovascular events (MACE) in asymptomatic individuals. Methods This was a post-hoc analysis of the prospective EISNER (Early-Identification of Subclinical Atherosclerosis by Noninvasive Imaging Research) study of participants who underwent baseline coronary artery calcium (CAC) scoring CT and 14-year follow-up for MACE (myocardial infarction, late revascularization, or cardiac death). EAT volume (cm3) and attenuation (Hounsfield units [HU]) were quantified from CT using fully automated deep learning software (< 30 s per case). NAFLD was defined as liver-to-spleen attenuation ratio < 1.0 and/or average liver attenuation < 40 HU. Results In the final population of 2068 participants (59% males, 56 ± 9 years), those with MetS (n = 280;13.5%) had a greater prevalence of NAFLD (26.0% vs. 9.9%), higher EAT volume (114.1 cm3 vs. 73.7 cm3), and lower EAT attenuation (−76.9 HU vs. −73.4 HU; all p < 0.001) compared to those without MetS. At 14 ± 3 years, MACE occurred in 223 (10.8%) participants. In multivariable Cox regression, MetS was associated with increased risk of MACE (HR 1.58 [95% CI 1.10–2.27], p = 0.01) independently of CAC score; however, not after adjustment for EAT measures (p = 0.27). In a separate Cox analysis, NAFLD predicted MACE (HR 1.78 [95% CI 1.21–2.61], p = 0.003) independently of MetS, CAC score, and EAT measures. Addition of EAT volume to current risk assessment tools resulted in significant net reclassification improvement for MACE (22% over ASCVD risk score; 17% over ASCVD risk score plus CAC score). Conclusions MetS, NAFLD, and artificial intelligence-based EAT measures predict long-term MACE risk in asymptomatic individuals. Imaging biomarkers of cardiometabolic disease have the potential for integration into routine reporting of CAC scoring CT to enhance cardiovascular risk stratification. Trial registration NCT00927693.

scholarly journals Long-term prognostic value of whole-heart coronary magnetic resonance angiography

2021 ◽  
Vol 23 (1) ◽  
Author(s):  
Satoshi Nakamura ◽  
Masaki Ishida ◽  
Kei Nakata ◽  
Yasutaka Ichikawa ◽  
Shinichi Takase ◽  
...  
Keyword(s):  
Risk Factors ◽  
Myocardial Infarction ◽  
Coronary Artery ◽  
Cardiac Death ◽  
Prognostic Value ◽  
Vessel Disease ◽  
History Of ◽  
Whole Heart

Abstract Background Coronary magnetic resonance angiography (CMRA) allows non-ionizing visualization of luminal narrowing in coronary artery disease (CAD). Although a prior study showed the usefulness of CMRA for risk stratification in short-term follow-up, the long-term prognostic value of CMRA remains unclear. The purpose of this study was to evaluate the long-term prognostic value of CMRA. Methods A total of 506 patients without history of myocardial infarction or prior coronary artery revascularization underwent free-breathing whole-heart CMRA between 2009 and 2015. Images were acquired using a 1.5 T or 3 T scanner and visually evaluated as the consensus decisions of two observers. Obstructive CAD on CMRA was defined as luminal narrowing of ≥ 50% in at least one coronary artery. Major adverse cardiac events (MACE) comprised cardiac death, nonfatal myocardial infarction, and unstable angina. Results Obstructive CAD on CMRA was observed in 214 patients (42%). During follow-up (median, 5.6 years), 31 MACE occurred. Kaplan–Meier curve analysis revealed a significant difference in event-free survival between patients with and without obstructive CAD for MACE (log-rank, p = 0.003) and cardiac death (p = 0.012). Annualized event rates for MACE in patients with no obstructive CAD, 1-vessel disease, 2-vessel disease, and left-main or 3-vessel disease were 0.6%, 1.5%, 2.3%, and 3.6%, respectively (log-rank, p = 0.003). Cox proportional hazard regression analysis showed that, among obstructive CAD on CMRA and clinical risk factors (age, sex, hypertension, diabetes, dyslipidemia, smoking, and family history of CAD), obstructive CAD and diabetes were significant predictors of MACE (hazard ratios, 2.9 [p = 0.005] and 2.2 [p = 0.034], respectively). In multivariate analysis, obstructive CAD remained an independent predictor (adjusted hazard ratio, 2.6 [p = 0.010]) after adjusting for diabetes. Addition of obstructive CAD to clinical risk factors significantly increased the global chi-square result from 8.3 to 13.8 (p = 0.022). Conclusions In long-term follow-up, free breathing whole heart CMRA allows non-invasive risk stratification for MACE and cardiac death and provides incremental prognostic value over conventional risk factors in patients without a history of myocardial infarction or prior coronary artery revascularization. The presence and severity of obstructive CAD detected by CMRA were associated with worse prognosis. Importantly, patients without obstructive CAD on CMRA displayed favorable prognosis.

Sign in / Sign up

Export Citation Format

Share Document