scholarly journals Cardiac computed tomography improves prediction of long-term cardiovascular events: a retrospective cohort study of type 2 diabetic with higher cardiovascular risk

2020 ◽  
Author(s):  
Zhijie Jian ◽  
Zhe Liu ◽  
Li Zhou ◽  
Ningning Ding ◽  
Hui Zhang ◽  
...  
Keyword(s):  
Computed Tomography ◽  
Cardiovascular Risk ◽  
Risk Stratification ◽  
Cardiovascular Events ◽  
Cardiac Ct ◽  
Cardiac Computed Tomography ◽  
Ct Data ◽  
Type 2 Diabetic

Abstract Background: The value of cardiac computed tomography (CT) for screening and risk stratification in patients with type 2 diabetes mellitus (DM) who are at a higher cardiovascular risk is unclear. Thus, this study aim s to investigate the efficacy of cardiac CT in predicting long-term cardiovascular events (CVEVs) in this subset of patients. Methods: Type 2 diabetic with a higher cardiovascular risk who underwent cardiac CT between 2012 and 2014 were included in this study. Cardiac CT was performed, and coronary artery calcium score, location and extent of lesion, stenosis severity, plaque composition, and epicardial adipose tissue (EAT) volume were assessed. The endpoints were a composite of CVEVs (cardiac death, non-fatal myocardial infarction, or coronary revascularization,non-fatal stroke, hospitalization for unstable angina, and hospitalization for congestive heart failure). Potential predictors of CVEVs were identified. Predictive models were created and compared. Results: CVEVs occurred in 26.8% of the patients. Independent predictors of CVEVs included diabetes duration (odds ratio [OR]=10.003), mean creatinine level (OR=3.845), hypertension (OR=3.844), atheroma burden obstructive score (OR=14.060), segment stenosis score (OR=7.912), and EAT volume (OR=7.947). The model including cardiac CT data and clinical parameters improved the prediction of CVEVs, with an area under the receiver operating characteristic curve of 0.912 (95% confidence interval 0.829–0.963; p<0.05) for the prediction of the study endpoints. Conclusion: Cardiac CT showed a great value in risk stratification for patients with diabetes with higher cardiovascular risk. Cardiac CT data may help predict CVEVs and potentially improve outcomes.

scholarly journals Artificial intelligence applied to non-contrast-enhanced cardiac computed tomography for the prediction of cardiovascular events

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
S Chiappino ◽  
D Della Latta ◽  
N Martini ◽  
A Ripoli ◽  
A Aimo ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Computed Tomography ◽  
Cardiovascular Risk ◽  
General Population ◽  
Cardiovascular Events ◽  
Cardiac Computed Tomography ◽  
Ct Scans ◽  
Event Prediction ◽  
Contrast Enhanced ◽  
Asymptomatic Individuals

Abstract Background Non-contrast-enhanced cardiac computed tomography (CT) may provide two measures that are emerging as independent predictors of cardiovascular events: coronary calcium score (CCS) and the volume of epicardial fat, a metabolically and immunologically active tissue surrounding the coronary arteries. The quantification of epicardial fat volume (EFV) is not routinely performed in clinical practice for the long time required for image reconstruction and the intra- and inter-observer variability. Purpose We evaluated if artificial intelligence (AI) might prove a valuable tool to interpret the CT data-set, and to better understand the relative prognostic value of CCS and EFV compared to “traditional” cardiovascular risk factors. Methods The Montignoso HEart and Lung Project is a community-based study carried out in a small town of Northern Tuscany (Italy). Starting from 2009, asymptomatic individuals from the general population underwent a baseline screening including a non-contrast cardiac CT, and were followed-up. For the present study, CCS and EFV were automatically measured from CT scans through a deep learning (DL) strategy based on convolutional neural networks. Because of the low incidence of the primary endpoint (myocardial infarction [MI]), the observed cardiac events were predicted with a random forest model built using a subsampling approach. Results Study participants (n=1528; 48% males, age 40 to 77 years) experienced 47 MI events (3%) over 5.5±1.5 years. CCS and EFV independently predicted this endpoint (p values &lt;0.001 and 0.005, respectively) in a model including other predictors, namely weight, age, male gender, and hypertension. The model displayed a good prognostic performance, with an out-of-bag accuracy of 80.43% (accuracy on non-event prediction: 81.17%; performance on event prediction: 57,45%). The CCS emerged as the most important predictor, followed by EFV, weight and age. Interestingly, the incidence of cardiovascular events linked with CCS levels was associated with elevated EFV and the subjects with elevated CCS values but low EFV had no events (figure 1). Conclusions The tools of AI allow to perform an automated analysis of non-contrast-enhanced CT scans, with rapid and accurate measurement of CCS and EFV through a DL approach. In asymptomatic individuals from the general population, these features are more predictive of non-fatal MI than other variables related to the cardiovascular risk, as we can be demonstrated through an application of AI. Figure 1 Funding Acknowledgement Type of funding source: None

scholarly journals Disease overarching mechanisms that explain and predict outcome of patients with high cardiovascular risk: rationale and design of the Berlin Long-term Observation of Vascular Events (BeLOVE) study

2019 ◽  
Author(s):  
Bob Siegerink ◽  
Joachim Weber ◽  
Michael Ahmadi ◽  
Kai-Uwe Eckardt ◽  
Frank Edelmann ◽  
...  
Keyword(s):  
Risk Factors ◽  
Type 2 Diabetes ◽  
Cardiovascular Risk ◽  
High Risk ◽  
Cardiovascular Events ◽  
Target Organ Damage ◽  
Organ Damage ◽  
High Cardiovascular Risk

AbstractBackgroundCardiovascular disease (CVD) is the leading cause of premature death worldwide. Effective and individualized treatment requires exact knowledge about both risk factors and risk estimation. Most evidence for risk prediction currently comes from population-based studies on first incident cardiovascular events. In contrast, little is known about the relevance of risk factors for the outcome of patients with established CVD or those who are at high risk of CVD, including patients with type 2 diabetes. In addition, most studies focus on individual diseases, whereas less is known about disease overarching risk factors and cross-over risk.AimThe aim of BeLOVE is to improve short- and long-term prediction and mechanistic understanding of cardiovascular disease progression and outcomes in very high-risk patients, both in the acute as well as in the chronic phase, in order to provide the basis for improved, individualized management.Study designBeLOVE is an observational prospective cohort study of patients of both sexes aged >18 in selected Berlin hospitals, who have a high risk of future cardiovascular events, including patients with a history of acute coronary syndrome (ACS), acute stroke (AS), acute heart failure (AHF), acute kidney injury (AKI) or type 2 diabetes with manifest target-organ damage. BeLOVE includes 2 subcohorts: The acute subcohort includes 6500 patients with ACS, AS, AHF, or AKI within 2-8 days after their qualifying event, who undergo a structured interview about medical history as well as blood sample collection. The chronic subcohort includes 6000 patients with ACS, AS, AHF, or AKI 90 days after event, and patients with type 2 diabetes (T2DM) and target-organ damage. These patients undergo a 6-8 hour deep phenotyping program, including detailed clinical phenotyping from a cardiological, neurological and metabolic perspective, questionnaires including patient-reported outcome measures (PROMs)as well as magnetic resonance imaging. Several biological samples are collected (i.e. blood, urine, saliva, stool) with blood samples collected in a fasting state, as well as after a metabolic challenge (either nutritional or cardiopulmonary exercise stress test). Ascertainment of major adverse cardiovascular events (MACE) will be performed in all patients using a combination of active and passive follow-up procedures, such as on-site visits (if applicable), telephone interviews, review of medical charts, and links to local health authorities. Additional phenotyping visits are planned at 2, 5 and 10 years after inclusion into the chronic subcohort.Future perspectiveBeLOVE provides a unique opportunity to study both the short- and long-term disease course of patients at high cardiovascular risk through innovative and extensive deep phenotyping. Moreover, the unique study design provides opportunities for acute and post-acute inclusion and allows us to derive two non-nested yet overlapping sub-cohorts, tailored for upcoming research questions. Thereby, we aim to study disease-overarching research questions, to understand crossover risk, and to find similarities and differences between clinical phenotypes of patients at high cardiovascular risk.

Sign in / Sign up

Export Citation Format

Share Document