Identifying people at risk of cardiovascular diseases (CVD) is a cornerstone of preventative cardiology. Risk prediction models currently recommended by clinical guidelines are typically based on a ...limited number of predictors with sub-optimal performance across all patient groups. Data-driven techniques based on machine learning (ML) might improve the performance of risk predictions by agnostically discovering novel risk predictors and learning the complex interactions between them. We tested (1) whether ML techniques based on a state-of-the-art automated ML framework (AutoPrognosis) could improve CVD risk prediction compared to traditional approaches, and (2) whether considering non-traditional variables could increase the accuracy of CVD risk predictions.
Using data on 423,604 participants without CVD at baseline in UK Biobank, we developed a ML-based model for predicting CVD risk based on 473 available variables. Our ML-based model was derived using AutoPrognosis, an algorithmic tool that automatically selects and tunes ensembles of ML modeling pipelines (comprising data imputation, feature processing, classification and calibration algorithms). We compared our model with a well-established risk prediction algorithm based on conventional CVD risk factors (Framingham score), a Cox proportional hazards (PH) model based on familiar risk factors (i.e, age, gender, smoking status, systolic blood pressure, history of diabetes, reception of treatments for hypertension and body mass index), and a Cox PH model based on all of the 473 available variables. Predictive performances were assessed using area under the receiver operating characteristic curve (AUC-ROC). Overall, our AutoPrognosis model improved risk prediction (AUC-ROC: 0.774, 95% CI: 0.768-0.780) compared to Framingham score (AUC-ROC: 0.724, 95% CI: 0.720-0.728, p < 0.001), Cox PH model with conventional risk factors (AUC-ROC: 0.734, 95% CI: 0.729-0.739, p < 0.001), and Cox PH model with all UK Biobank variables (AUC-ROC: 0.758, 95% CI: 0.753-0.763, p < 0.001). Out of 4,801 CVD cases recorded within 5 years of baseline, AutoPrognosis was able to correctly predict 368 more cases compared to the Framingham score. Our AutoPrognosis model included predictors that are not usually considered in existing risk prediction models, such as the individuals' usual walking pace and their self-reported overall health rating. Furthermore, our model improved risk prediction in potentially relevant sub-populations, such as in individuals with history of diabetes. We also highlight the relative benefits accrued from including more information into a predictive model (information gain) as compared to the benefits of using more complex models (modeling gain).
Our AutoPrognosis model improves the accuracy of CVD risk prediction in the UK Biobank population. This approach performs well in traditionally poorly served patient subgroups. Additionally, AutoPrognosis uncovered novel predictors for CVD disease that may now be tested in prospective studies. We found that the "information gain" achieved by considering more risk factors in the predictive model was significantly higher than the "modeling gain" achieved by adopting complex predictive models.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Alcohol use is an important preventable and modifiable cause of non‐communicable disease, and has complex effects on the cardiovascular system that vary with dose. Observational and prospective ...studies have consistently shown a lower risk of cardiovascular and all‐cause mortality in people with low levels of alcohol consumption when compared to abstainers (the ‘J’‐shaped curve). Maximum potential benefit occurs at 0.5 to one standard drinks (7–14 g pure ethanol) per day for women (18% lower all‐cause mortality, 95% confidence interval (CI) = 13–22%) and one to two standard drinks (14–28 g ethanol) per day for men (17% lower all‐cause mortality, 95% CI = 15–19%). However, this evidence is contested, and overall the detrimental effects of alcohol far outweigh the beneficial effects, with the risk of premature mortality increasing steadily after an average consumption of 10 g ethanol/day. Blood pressure (BP) is increased by regular alcohol consumption in a dose‐dependent manner, with a relative risk for hypertension (systolic BP > 140 mm Hg or diastolic > 90 mm Hg) of 1.7 for 50 g ethanol/day and 2.5 at 100 g/day. Important reductions in BP readings can be expected after as little as 1 month of abstinence from alcohol. Heavy alcohol consumption in a binge pattern is associated with the development of acute cardiac arrhythmia, even in people with normal heart function. Atrial fibrillation is the most common arrhythmia associated with chronic high‐volume alcohol intake, and above 14 g alcohol/day the relative risk increases 10% for every extra standard drink (14 g ethanol). Ethanol and its metabolites have toxic effects on cardiac myocytes, and alcoholic cardiomyopathy (ACM) accounts for a third of all cases of non‐ischaemic dilated cardiomyopathy. Screening people drinking alcohol above low‐volume levels and delivering a brief intervention may prevent the development of cardiovascular complications. Although people with established cardiovascular disease show improved outcomes with a reduction to low‐volume alcohol consumption, there is no safe amount of alcohol to drink and patients with ACM should aim for abstinence in order to optimize medical treatment.
Full text
Available for:
BFBNIB, DOBA, FSPLJ, FZAB, GIS, IJS, IZUM, KILJ, NLZOH, NUK, OILJ, PILJ, PNG, SAZU, SBCE, SBMB, SIK, UILJ, UKNU, UL, UM, UPUK, VSZLJ
PET imaging of atherosclerosis can quantify several in vivo pathological processes occurring within the arterial system. (18)F-fluorodeoxyglucose (FDG) is the most-commonly used PET tracer, with ...well-established roles in atherosclerosis imaging. In this context, the (18)F-FDG signal largely reflects tracer uptake by plaque macrophages and, therefore, inflammation with smaller contributions from other resident cell types. As a marker of plaque vulnerability, the (18)F-FDG PET signal can be used to help to identify patients at the highest risk of clinical events. (18)F-FDG PET has also been used successfully as a surrogate end point in clinical trials of antiatherosclerotic therapies. Nonetheless, imaging atherosclerosis with (18)F-FDG has several limitations. Most importantly, coronary artery imaging is problematic because (18)F-FDG accumulates in all cells that metabolize glucose, and background myocardial uptake is generally greater than any signal originating from a plaque. To help to overcome these limitations, several novel PET tracers, which might be more-specifically targeted than (18)F-FDG, have been tested in atherosclerosis imaging. These tracers are designed to track inflammation, hypoxia, neoangiogenesis, or active calcification, which are all precursors to plaque rupture and its clinical sequelae.
With combined positron emission tomography and computed tomography (CT), we investigated coronary arterial uptake of 18F-sodium fluoride (18F-NaF) and 18F-fluorodeoxyglucose (18F-FDG) as markers of ...active plaque calcification and inflammation, respectively.
The noninvasive assessment of coronary artery plaque biology would be a major advance particularly in the identification of vulnerable plaques, which are associated with specific pathological characteristics, including micro-calcification and inflammation.
We prospectively recruited 119 volunteers (72 ± 8 years of age, 68% men) with and without aortic valve disease and measured their coronary calcium score and 18F-NaF and 18F-FDG uptake. Patients with a calcium score of 0 were used as control subjects and compared with those with calcific atherosclerosis (calcium score >0).
Inter-observer repeatability of coronary 18F-NaF uptake measurements (maximum tissue/background ratio) was excellent (intra-class coefficient 0.99). Activity was higher in patients with coronary atherosclerosis (n = 106) versus control subjects (1.64 ± 0.49 vs. 1.23 ± 0.24; p = 0.003) and correlated with the calcium score (r = 0.652, p < 0.001), although 40% of those with scores >1,000 displayed normal uptake. Patients with increased coronary 18F-NaF activity (n = 40) had higher rates of prior cardiovascular events (p = 0.016) and angina (p = 0.023) and higher Framingham risk scores (p = 0.011). Quantification of coronary 18F-FDG uptake was hampered by myocardial activity and was not increased in patients with atherosclerosis versus control subjects (p = 0.498).
18F-NaF is a promising new approach for the assessment of coronary artery plaque biology. Prospective studies with clinical outcomes are now needed to assess whether coronary 18F-NaF uptake represents a novel marker of plaque vulnerability, recent plaque rupture, and future cardiovascular risk. (An Observational PET/CT Study Examining the Role of Active Valvular Calcification and Inflammation in Patients With Aortic Stenosis; NCT01358513).
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Summary Background Dalcetrapib modulates cholesteryl ester transfer protein (CETP) activity to raise high-density lipoprotein cholesterol (HDL-C). After the failure of torcetrapib it was unknown if ...HDL produced by interaction with CETP had pro-atherogenic or pro-inflammatory properties. dal-PLAQUE is the first multicentre study using novel non-invasive multimodality imaging to assess structural and inflammatory indices of atherosclerosis as primary endpoints. Methods In this phase 2b, double-blind, multicentre trial, patients (aged 18–75 years) with, or with high risk of, coronary heart disease were randomly assigned (1:1) to dalcetrapib 600 mg/day or placebo for 24 months. Randomisation was done with a computer-generated randomisation code and was stratified by centre. Patients and investigators were masked to treatment. Coprimary endpoints were MRI-assessed indices (total vessel area, wall area, wall thickness, and normalised wall index average carotid) after 24 months and18 F-fluorodeoxyglucose (18 F-FDG) PET/CT assessment of arterial inflammation within an index vessel (right carotid, left carotid, or ascending thoracic aorta) after 6 months, with no-harm boundaries established before unblinding of the trial. Analysis was by intention to treat. This trial is registered at ClinicalTrials.gov , NCT00655473. Findings 189 patients were screened and 130 randomly assigned to placebo (66 patients) or dalcetrapib (64 patients). For the coprimary MRI and PET/CT endpoints, CIs were below the no-harm boundary or the adverse change was numerically lower in the dalcetrapib group than in the placebo group. MRI-derived change in total vessel area was reduced in patients given dalcetrapib compared with those given placebo after 24 months; absolute change from baseline relative to placebo was −4·01 mm2 (90% CI −7·23 to −0·80; nominal p=0·04). The PET/CT measure of index vessel most-diseased-segment target-to-background ratio (TBR) was not different between groups, but carotid artery analysis showed a 7% reduction in most-diseased-segment TBR in the dalcetrapib group compared with the placebo group (–7·3 90% CI −13·5 to −0·8; nominal p=0·07). Dalcetrapib did not increase office blood pressure and the frequency of adverse events was similar between groups. Interpretation Dalcetrapib showed no evidence of a pathological effect related to the arterial wall over 24 months. Moreover, this trial suggests possible beneficial vascular effects of dalcetrapib, including the reduction in total vessel enlargement over 24 months, but long-term safety and clinical outcomes efficacy of dalcetrapib need to be analysed. Funding F Hoffmann-La Roche Ltd.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
The use of non-invasive imaging to identify ruptured or high-risk coronary atherosclerotic plaques would represent a major clinical advance for prevention and treatment of coronary artery disease. We ...used combined PET and CT to identify ruptured and high-risk atherosclerotic plaques using the radioactive tracers 18F-sodium fluoride (18F-NaF) and 18F-fluorodeoxyglucose (18F-FDG).
In this prospective clinical trial, patients with myocardial infarction (n=40) and stable angina (n=40) underwent 18F-NaF and 18F-FDG PET-CT, and invasive coronary angiography. 18F-NaF uptake was compared with histology in carotid endarterectomy specimens from patients with symptomatic carotid disease, and with intravascular ultrasound in patients with stable angina. The primary endpoint was the comparison of 18F-fluoride tissue-to-background ratios of culprit and non-culprit coronary plaques of patients with acute myocardial infarction.
In 37 (93%) patients with myocardial infarction, the highest coronary 18F-NaF uptake was seen in the culprit plaque (median maximum tissue-to-background ratio: culprit 1·66 IQR 1·40–2·25 vs highest non-culprit 1·24 1·06–1·38, p<0·0001). By contrast, coronary 18F-FDG uptake was commonly obscured by myocardial uptake and where discernible, there were no differences between culprit and non-culprit plaques (1·71 1·40–2·13 vs 1·58 1·28–2·01, p=0·34). Marked 18F-NaF uptake occurred at the site of all carotid plaque ruptures and was associated with histological evidence of active calcification, macrophage infiltration, apoptosis, and necrosis. 18 (45%) patients with stable angina had plaques with focal 18F-NaF uptake (maximum tissue-to-background ratio 1·90 IQR 1·61–2·17) that were associated with more high-risk features on intravascular ultrasound than those without uptake: positive remodelling (remodelling index 1·12 1·09–1·19 vs 1·01 0·94–1·06; p=0·0004), microcalcification (73% vs 21%, p=0·002), and necrotic core (25% 21–29 vs 18% 14–22, p=0·001).
18F-NaF PET-CT is the first non-invasive imaging method to identify and localise ruptured and high-risk coronary plaque. Future studies are needed to establish whether this method can improve the management and treatment of patients with coronary artery disease.
Chief Scientist Office Scotland and British Heart Foundation.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Imaging Atherosclerosis Tarkin, Jason M; Dweck, Marc R; Evans, Nicholas R ...
Circulation research,
2016-February-19, 2016-Feb-19, 2016-02-19, 20160219, Volume:
118, Issue:
4
Journal Article
Peer reviewed
Open access
Advances in atherosclerosis imaging technology and research have provided a range of diagnostic tools to characterize high-risk plaque in vivo; however, these important vascular imaging methods ...additionally promise great scientific and translational applications beyond this quest. When combined with conventional anatomic- and hemodynamic-based assessments of disease severity, cross-sectional multimodal imaging incorporating molecular probes and other novel noninvasive techniques can add detailed interrogation of plaque composition, activity, and overall disease burden. In the catheterization laboratory, intravascular imaging provides unparalleled access to the world beneath the plaque surface, allowing tissue characterization and measurement of cap thickness with micrometer spatial resolution. Atherosclerosis imaging captures key data that reveal snapshots into underlying biology, which can test our understanding of fundamental research questions and shape our approach toward patient management. Imaging can also be used to quantify response to therapeutic interventions and ultimately help predict cardiovascular risk. Although there are undeniable barriers to clinical translation, many of these hold-ups might soon be surpassed by rapidly evolving innovations to improve image acquisition, coregistration, motion correction, and reduce radiation exposure. This article provides a comprehensive review of current and experimental atherosclerosis imaging methods and their uses in research and potential for translation to the clinic.
The study sought to test whether high-dose statin treatment would result in greater reductions in plaque inflammation than low-dose statins, using fluorodeoxyglucose-positron emission ...tomography/computed tomographic imaging (FDG-PET/CT).
Intensification of statin therapy reduces major cardiovascular events.
Adults with risk factors or with established atherosclerosis, who were not taking high-dose statins (n = 83), were randomized to atorvastatin 10 versus 80 mg in a double-blind, multicenter trial. FDG-PET/CT imaging of the ascending thoracic aorta and carotid arteries was performed at baseline, 4, and 12 weeks after randomization and target-to-background ratio (TBR) of FDG uptake within the artery wall was assessed while blinded to time points and treatment.
Sixty-seven subjects completed the study, providing imaging data for analysis. At 12 weeks, inflammation (TBR) in the index vessel was significantly reduced from baseline with atorvastatin 80 mg (% reduction 95% confidence interval: 14.42% 8.7% to 19.8%; p < 0.001), but not atorvastatin 10 mg (% reduction: 4.2% -2.3% to 10.4%; p > 0.1). Atorvastatin 80 mg resulted in significant additional relative reductions in TBR versus atorvastatin 10 mg (10.6% 2.2% to 18.3%; p = 0.01) at week 12. Reductions from baseline in TBR were seen as early as 4 weeks after randomization with atorvastatin 10 mg (6.4% reduction, p < 0.05) and 80 mg (12.5% reduction, p < 0.001). Changes in TBR did not correlate with lipid profile changes.
Statin therapy produced significant rapid dose-dependent reductions in FDG uptake that may represent changes in atherosclerotic plaque inflammation. FDG-PET imaging may be useful in detecting early treatment effects in patients at risk or with established atherosclerosis.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Bioprosthetic aortic valve degeneration is increasingly common, often unheralded, and can have catastrophic consequences.
The authors sought to assess whether 18F-fluoride positron emission ...tomography (PET)-computed tomography (CT) can detect bioprosthetic aortic valve degeneration and predict valve dysfunction.
Explanted degenerate bioprosthetic valves were examined ex vivo. Patients with bioprosthetic aortic valves were recruited into 2 cohorts with and without prosthetic valve dysfunction and underwent in vivo contrast-enhanced CT angiography, 18F-fluoride PET, and serial echocardiography during 2 years of follow-up.
All ex vivo, degenerate bioprosthetic valves displayed 18F-fluoride PET uptake that colocalized with tissue degeneration on histology. In 71 patients without known bioprosthesis dysfunction, 14 had abnormal leaflet pathology on CT, and 24 demonstrated 18F-fluoride PET uptake (target-to-background ratio 1.55 interquartile range (IQR): 1.44 to 1.88). Patients with increased 18F-fluoride uptake exhibited more rapid deterioration in valve function compared with those without (annualized change in peak transvalvular velocity 0.30 IQR: 0.13 to 0.61 vs. 0.01 IQR: −0.05 to 0.16 ms−1/year; p < 0.001). Indeed 18F-fluoride uptake correlated with deterioration in all the conventional echocardiographic measures of valve function assessed (e.g., change in peak velocity, r = 0.72; p < 0.001). Each of the 10 patients who developed new overt bioprosthesis dysfunction during follow-up had evidence of 18F-fluoride uptake at baseline (target-to-background ratio 1.89 IQR: 1.46 to 2.59). On multivariable analysis, 18F-fluoride uptake was the only independent predictor of future bioprosthetic dysfunction.
18F-fluoride PET-CT identifies subclinical bioprosthetic valve degeneration, providing powerful prediction of subsequent valvular dysfunction and highlighting patients at risk of valve failure. This technique holds major promise in the diagnosis of valvular degeneration and the surveillance of patients with bioprosthetic valves. (18F-Fluoride Assessment of Aortic Bioprosthesis Durability and Outcome 18F-FAABULOUS; NCT02304276)
Display omitted
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Major focus has been placed on the identification of vulnerable plaques as a means of improving the prediction of myocardial infarction. However, this strategy has recently been questioned on the ...basis that the majority of these individual coronary lesions do not in fact go on to cause clinical events. Attention is, therefore, shifting to alternative imaging modalities that might provide a more complete pan-coronary assessment of the atherosclerotic disease process. These include markers of disease activity with the potential to discriminate between patients with stable burnt-out disease that is no longer metabolically active and those with active atheroma, faster disease progression, and increased risk of infarction. This review will examine how novel molecular imaging approaches can provide such assessments, focusing on inflammation and microcalcification activity, the importance of these processes to coronary atherosclerosis, and the advantages and challenges posed by these techniques.
PDF
