External validation of integrated genetic-epigenetic biomarkers for predicting incident coronary heart disease.
Ontology highlight
ABSTRACT:
SUBMITTER: Dogan MV
PROVIDER: S-EPMC8356680 | biostudies-literature | 2021 Jul
REPOSITORIES: biostudies-literature
Publications
External validation of integrated genetic-epigenetic biomarkers for predicting incident coronary heart disease.
Dogan Meeshanthini V MV Knight Stacey S Dogan Timur K TK Knowlton Kirk U KU Philibert Robert R
Epigenomics 20210621 14
<b>Aim:</b> The Framingham Risk Score (FRS) and atherosclerotic cardiovascular disease (ASCVD) Pooled Cohort Equation (PCE) for predicting risk for incident coronary heart disease (CHD) work poorly. To improve risk stratification for CHD, we developed a novel integrated genetic-epigenetic tool. <b>Materials & methods:</b> Using machine learning techniques and datasets from the Framingham Heart Study (FHS) and Intermountain Healthcare (IM), we developed and validated an integrated genetic-epigene ...[more]
Similar Datasets
Project description:BackgroundCoronary heart disease (CHD) is the leading cause of death in the world. Unfortunately, many of the key diagnostic tools for CHD are insensitive, invasive, and costly; require significant specialized infrastructure investments; and do not provide information to guide postdiagnosis therapy. In prior work using data from the Framingham Heart Study, we provided in silico evidence that integrated genetic-epigenetic tools may provide a new avenue for assessing CHD.Methods and resultsIn this communication, we use an improved machine learning approach and data from 2 additional cohorts, totaling 449 cases and 2067 controls, to develop a better model for ascertaining symptomatic CHD. Using the DNA from the 2 new cohorts, we translate and validate the in silico findings into an artificial intelligence-guided, clinically implementable method that uses input from 6 methylation-sensitive digital polymerase chain reaction and 10 genotyping assays. Using this method, the overall average area under the curve, sensitivity, and specificity in the 3 test cohorts is 82%, 79%, and 76%, respectively. Analysis of targeted cytosine-phospho-guanine loci shows that they map to key risk pathways involved in atherosclerosis that suggest specific therapeutic approaches.ConclusionsWe conclude that this scalable integrated genetic-epigenetic approach is useful for the diagnosis of symptomatic CHD, performs favorably as compared with many existing methods, and may provide personalized insight to CHD therapy. Furthermore, given the dynamic nature of DNA methylation and the ease of methylation-sensitive digital polymerase chain reaction methodologies, these findings may pave a pathway for precision epigenetic approaches for monitoring CHD treatment response.
| S-EPMC10727271 | biostudies-literature
Project description:An improved method for detecting coronary heart disease (CHD) could have substantial clinical impact. Building on the idea that systemic effects of CHD risk factors are a conglomeration of genetic and environmental factors, we use machine learning techniques and integrate genetic, epigenetic and phenotype data from the Framingham Heart Study to build and test a Random Forest classification model for symptomatic CHD. Our classifier was trained on n = 1,545 individuals and consisted of four DNA methylation sites, two SNPs, age and gender. The methylation sites and SNPs were selected during the training phase. The final trained model was then tested on n = 142 individuals. The test data comprised of individuals removed based on relatedness to those in the training dataset. This integrated classifier was capable of classifying symptomatic CHD status of those in the test set with an accuracy, sensitivity and specificity of 78%, 0.75 and 0.80, respectively. In contrast, a model using only conventional CHD risk factors as predictors had an accuracy and sensitivity of only 65% and 0.42, respectively, but with a specificity of 0.89 in the test set. Regression analyses of the methylation signatures illustrate our ability to map these signatures to known risk factors in CHD pathogenesis. These results demonstrate the capability of an integrated approach to effectively model symptomatic CHD status. These results also suggest that future studies of biomaterial collected from longitudinally informative cohorts that are specifically characterized for cardiac disease at follow-up could lead to the introduction of sensitive, readily employable integrated genetic-epigenetic algorithms for predicting onset of future symptomatic CHD.
| S-EPMC5749823 | biostudies-literature
Project description:An improved approach for predicting the risk for incident coronary heart disease (CHD) could lead to substantial improvements in cardiovascular health. Previously, we have shown that genetic and epigenetic loci could predict CHD status more sensitively than conventional risk factors. Herein, we examine whether similar machine learning approaches could be used to develop a similar panel for predicting incident CHD. Training and test sets consisted of 1180 and 524 individuals, respectively. Data mining techniques were employed to mine for predictive biosignatures in the training set. An ensemble of Random Forest models consisting of four genetic and four epigenetic loci was trained on the training set and subsequently evaluated on the test set. The test sensitivity and specificity were 0.70 and 0.74, respectively. In contrast, the Framingham risk score and atherosclerotic cardiovascular disease (ASCVD) risk estimator performed with test sensitivities of 0.20 and 0.38, respectively. Notably, the integrated genetic-epigenetic model predicted risk better for both genders and very well in the three-year risk prediction window. We describe a novel DNA-based precision medicine tool capable of capturing the complex genetic and environmental relationships that contribute to the risk of CHD, and being mapped to actionable risk factors that may be leveraged to guide risk modification efforts.
| S-EPMC6315411 | biostudies-literature
Project description:Analyses of circulating metabolites in large prospective epidemiological studies could lead to improved prediction and better biological understanding of coronary heart disease (CHD). We performed a mass spectrometry-based non-targeted metabolomics study for association with incident CHD events in 1,028 individuals (131 events; 10 y. median follow-up) with validation in 1,670 individuals (282 events; 3.9 y. median follow-up). Four metabolites were replicated and independent of main cardiovascular risk factors [lysophosphatidylcholine 18∶1 (hazard ratio [HR] per standard deviation [SD] increment = 0.77, P-value<0.001), lysophosphatidylcholine 18∶2 (HR = 0.81, P-value<0.001), monoglyceride 18∶2 (MG 18∶2; HR = 1.18, P-value = 0.011) and sphingomyelin 28∶1 (HR = 0.85, P-value = 0.015)]. Together they contributed to moderate improvements in discrimination and re-classification in addition to traditional risk factors (C-statistic: 0.76 vs. 0.75; NRI: 9.2%). MG 18∶2 was associated with CHD independently of triglycerides. Lysophosphatidylcholines were negatively associated with body mass index, C-reactive protein and with less evidence of subclinical cardiovascular disease in additional 970 participants; a reverse pattern was observed for MG 18∶2. MG 18∶2 showed an enrichment (P-value = 0.002) of significant associations with CHD-associated SNPs (P-value = 1.2×10-7 for association with rs964184 in the ZNF259/APOA5 region) and a weak, but positive causal effect (odds ratio = 1.05 per SD increment in MG 18∶2, P-value = 0.05) on CHD, as suggested by Mendelian randomization analysis. In conclusion, we identified four lipid-related metabolites with evidence for clinical utility, as well as a causal role in CHD development.
| S-EPMC4263376 | biostudies-literature
Project description:BackgroundThe Diamond-Forrester model was used extensively to predict obstructive coronary artery disease (CAD) but overestimates probability in current populations. Coronary artery calcium (CAC) is a useful marker of CAD, which is not routinely integrated with other features. We derived simple likelihood tables, integrating CAC with age, sex, and cardiac chest pain to predict obstructive CAD.Methods and resultsThe training population included patients from 3 multinational sites (n=2055), with 2 sites for external testing (n=3321). We determined associations between age, sex, cardiac chest pain, and CAC with the presence of obstructive CAD, defined as any stenosis ≥50% on coronary computed tomography angiography. Prediction performance was assessed using area under the receiver-operating characteristic curves (AUCs) and compared with the CAD Consortium models with and without CAC, which require detailed calculations, and the updated Diamond-Forrester model. In external testing, the proposed likelihood tables had higher AUC (0.875 [95% CI, 0.862-0.889]) than the CAD Consortium clinical+CAC score (AUC, 0.868 [95% CI, 0.855-0.881]; P=0.030) and the updated Diamond-Forrester model (AUC, 0.679 [95% CI, 0.658-0.699]; P<0.001). The calibration for the likelihood tables was better than the CAD Consortium model (Brier score, 0.116 versus 0.121; P=0.005).ConclusionsWe have developed and externally validated simple likelihood tables to integrate CAC with age, sex, and cardiac chest pain, demonstrating improved prediction performance compared with other risk models. Our tool affords physicians with the opportunity to rapidly and easily integrate a small number of important features to estimate a patient's likelihood of obstructive CAD as an aid to clinical management.
| S-EPMC10863788 | biostudies-literature
Project description:Sugar-sweetened beverage consumption is associated with weight gain and risk of type 2 diabetes mellitus. Few studies have tested for a relationship with coronary heart disease (CHD) or intermediate biomarkers. The role of artificially sweetened beverages is also unclear.We performed an analysis of the Health Professionals Follow-Up Study, a prospective cohort study including 42 883 men. Associations of cumulatively averaged sugar-sweetened (eg, sodas) and artificially sweetened (eg, diet sodas) beverage intake with incident fatal and nonfatal CHD (myocardial infarction) were examined with proportional hazard models. There were 3683 CHD cases over 22 years of follow-up. Participants in the top quartile of sugar-sweetened beverage intake had a 20% higher relative risk of CHD than those in the bottom quartile (relative risk=1.20; 95% confidence interval, 1.09-1.33; P for trend <0.01) after adjustment for age, smoking, physical activity, alcohol, multivitamins, family history, diet quality, energy intake, body mass index, pre-enrollment weight change, and dieting. Artificially sweetened beverage consumption was not significantly associated with CHD (multivariate relative risk=1.02; 95% confidence interval, 0.93-1.12; P for trend=0.28). Adjustment for self-reported high cholesterol, high triglycerides, high blood pressure, and diagnosed type 2 diabetes mellitus slightly attenuated these associations. Intake of sugar-sweetened but not artificially sweetened beverages was significantly associated with increased plasma triglycerides, C-reactive protein, interleukin-6, and tumor necrosis factor receptors 1 and 2 and decreased high-density lipoprotein, lipoprotein(a), and leptin (P<0.02).Consumption of sugar-sweetened beverages was associated with increased risk of CHD and some adverse changes in lipids, inflammatory factors, and leptin. Artificially sweetened beverage intake was not associated with CHD risk or biomarkers.
| S-EPMC3368965 | biostudies-literature
Project description:AimsAssessing the risk for HF rehospitalization is important for managing and treating patients with HF. To address this need, various risk prediction models have been developed. However, none of them used deep learning methods with real-world data. This study aimed to develop a deep learning-based prediction model for HF rehospitalization within 30, 90, and 365 days after acute HF (AHF) discharge.Methods and resultsWe analysed the data of patients admitted due to AHF between January 2014 and January 2019 in a tertiary hospital. In performing deep learning-based predictive algorithms for HF rehospitalization, we use hyperbolic tangent activation layers followed by recurrent layers with gated recurrent units. To assess the readmission prediction, we used the AUC, precision, recall, specificity, and F1 measure. We applied the Shapley value to identify which features contributed to HF readmission. Twenty-two prognostic features exhibiting statistically significant associations with HF rehospitalization were identified, consisting of 6 time-independent and 16 time-dependent features. The AUC value shows moderate discrimination for predicting readmission within 30, 90, and 365 days of follow-up (FU) (AUC:0.63, 0.74, and 0.76, respectively). The features during the FU have a relatively higher contribution to HF rehospitalization than features from other time points.ConclusionsOur deep learning-based model using real-world data could provide valid predictions of HF rehospitalization in 1 year follow-up. It can be easily utilized to guide appropriate interventions or care strategies for patients with HF. The closed monitoring and blood test in daily clinics are important for assessing the risk of HF rehospitalization.
| S-EPMC11631275 | biostudies-literature
Project description:Background and aimsDespite interest in the use of polygenic risk scores (PRS) for predicting coronary heart disease (CHD) risk, the clinical utility of PRS compared to conventional risk factors has not been demonstrated. We compared the performance of PRS with that of high-sensitivity C-reactive protein (hsCRP) in two well-established cohorts.MethodsThe study population included individuals of European ancestry free of baseline CHD from ARIC (N = 13,113) and the Framingham Offspring Study (FHS) (N = 2,696). The primary predictors included a validated PRS consisting of >6.6 million single nucleotide polymorphisms and hsCRP. The outcome was incident CHD, defined as non-fatal or fatal myocardial infarction. We compared the performance of both predictors after adjusting for the Pooled Cohort Equations in multivariable-adjusted Cox regression models. We assessed discrimination and reclassification using c-statistics and net reclassification improvement.ResultsIncident CHD occurred in 565 ARIC and 153 FHS participants. In multivariable-adjusted models, both PRS and hsCRP were associated with incident CHD (p < 0.05 in both cohorts). In models incorporating both predictors, strengths of association were similar. For instance, in ARIC, the hazard ratio per SD increment was 1.38 (95% CI, 1.27-1.50, p = 2.94 × 10-14) for PRS and 1.41 (1.30-1.55, p = 3.10 × 10-15) for hsCRP. Neither predictor significantly increased model discrimination or net reclassification when compared with models containing the Pooled Cohort Equations alone.ConclusionsIn two independent cohorts, PRS performed similarly to hsCRP for the prediction of CHD risk. These findings suggest PRS does not have unique clinical utility beyond this widely-available, inexpensive measure of risk in unselected middle-aged populations.
| S-EPMC10529589 | biostudies-literature
Project description:Objective- Alterations in the serum metabolome may be detectable in at-risk individuals before the onset of coronary heart disease (CHD). Identifying metabolomic signatures associated with CHD may provide insight into disease pathophysiology and prevention. Approach and Results- Metabolomic profiling (chromatography-mass spectrometry) was performed in 2232 African Americans and 1366 European Americans from the ARIC study (Atherosclerosis Risk in Communities). We applied Cox regression with least absolute shrinkage and selection operator to select metabolites associated with incident CHD. A metabolite risk score was constructed to evaluate whether the metabolite risk score predicted CHD risk beyond traditional risk factors. After 30 years of follow-up, we observed 633 incident CHD cases. Thirty-two metabolites were selected by least absolute shrinkage and selection operator to be associated with CHD, and 19 of the 32 showed significant individual associations with CHD, including a sugar substitute, erythritol. Theophylline (hazard ratio [95% CI] =1.16 [1.09-1.25]) and gamma-linolenic acid (hazard ratio [95% CI] =0.89 [0.81-0.97]) showed the greatest positive and negative associations with CHD, respectively. A 1 SD greater standardized metabolite risk score was associated with a 1.37-fold higher risk of CHD (hazard ratio [95% CI] =1.37 [1.27-1.47]). Adding the metabolite risk score to the traditional risk factors significantly improved model predictive performance (30-year risk prediction: Δ C statistics [95% CI] =0.016 [0.008-0.024], continuous net reclassification index [95% CI] =0.522 [0.480-0.556], integrated discrimination index [95% CI] =0.038 [0.019-0.065]). Conclusions- We identified 19 metabolites from known and novel metabolic pathways that collectively improved CHD risk prediction. Visual Overview- An online visual overview is available for this article.
| S-EPMC6839698 | biostudies-literature
Project description:The aim of this study was to compare and externally validate risk scores developed to predict incident colorectal cancer that include common genetic variants (SNPs), with or without established lifestyle/environmental (questionnaire-based/classical/phenotypic) risk factors. We externally validated 23 risk models from a previous systematic review in 443,888 participants ages 37 to 73 from the UK Biobank cohort who had 6-year prospective follow-up, no prior history of colorectal cancer, and data for incidence of colorectal cancer through linkage to national cancer registries. There were 2,679 (0.6%) cases of incident colorectal cancer. We assessed model discrimination using the area under the operating characteristic curve (AUC) and relative risk calibration. The AUC of models including only SNPs increased with the number of included SNPs and was similar in men and women: the model by Huyghe with 120 SNPs had the highest AUC of 0.62 [95% confidence interval (CI), 0.59-0.64] in women and 0.64 (95% CI, 0.61-0.66) in men. Adding phenotypic risk factors without age improved discrimination in men but not in women. Adding phenotypic risk factors and age increased discrimination in all cases (P < 0.05), with the best performing models including SNPs, phenotypic risk factors, and age having AUCs between 0.64 and 0.67 in women and 0.67 and 0.71 in men. Relative risk calibration varied substantially across the models. Among middle-aged people in the UK, existing polygenic risk scores discriminate moderately well between those who do and do not develop colorectal cancer over 6 years. Consideration should be given to exploring the feasibility of incorporating genetic and lifestyle/environmental information in any future stratified colorectal cancer screening program.
| S-EPMC7610623 | biostudies-literature