Dataset Information

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning.

ABSTRACT: 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.

SUBMITTER: Dogan MV

PROVIDER: S-EPMC6315411 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning.

Dogan Meeshanthini V MV Beach Steven R H SRH Simons Ronald L RL Lendasse Amaury A Penaluna Brandan B Philibert Robert A RA

Genes 20181218 12

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 m ...[more]

PMID: 30567402

Similar Datasets

Project description:Purpose: We aimed to establish and validate a risk assessment system that combines demographic and clinical variables to predict the 3-year risk of incident diabetes in Chinese adults. Methods: A 3-year cohort study was performed on 15,928 Chinese adults without diabetes at baseline. All participants were randomly divided into a training set (n = 7,940) and a validation set (n = 7,988). XGBoost method is an effective machine learning technique used to select the most important variables from candidate variables. And we further established a stepwise model based on the predictors chosen by the XGBoost model. The area under the receiver operating characteristic curve (AUC), decision curve and calibration analysis were used to assess discrimination, clinical use and calibration of the model, respectively. The external validation was performed on a cohort of 11,113 Japanese participants. Result: In the training and validation sets, 148 and 145 incident diabetes cases occurred. XGBoost methods selected the 10 most important variables from 15 candidate variables. Fasting plasma glucose (FPG), body mass index (BMI) and age were the top 3 important variables. And we further established a stepwise model and a prediction nomogram. The AUCs of the stepwise model were 0.933 and 0.910 in the training and validation sets, respectively. The Hosmer-Lemeshow test showed a perfect fit between the predicted diabetes risk and the observed diabetes risk (p = 0.068 for the training set, p = 0.165 for the validation set). Decision curve analysis presented the clinical use of the stepwise model and there was a wide range of alternative threshold probability spectrum. And there were almost no the interactions between these predictors (most P-values for interaction >0.05). Furthermore, the AUC for the external validation set was 0.830, and the Hosmer-Lemeshow test for the external validation set showed no statistically significant difference between the predicted diabetes risk and observed diabetes risk (P = 0.824). Conclusion: We established and validated a risk assessment system for characterizing the 3-year risk of incident diabetes.

Project description:BackgroundRemnant lipoproteins (RLPs), the triglyceride-enriched precursors to low-density lipoprotein, are an emerging risk factor for coronary heart disease (CHD). We sought to determine the association of RLP cholesterol (RLP-C) levels with incident CHD in 2 diverse, prospective, longitudinal observational US cohorts.Methods and resultsWe analyzed cholesterol levels from serum lipoprotein samples separated via density gradient ultracentrifugation in 4114 US black participants (mean age 53.8 years, 64% women) from the Jackson Heart Study and a random sample of 818 predominantly white participants (mean age 57.3 years, 52% women) from the Framingham Offspring Cohort Study. Multivariable-adjusted hazard ratios (HRs) for RLP-C (the sum of very low-density lipoprotein3 cholesterol and intermediate-density lipoprotein cholesterol) were derived to estimate associations with incident CHD events consisting of myocardial infarction, CHD death, and revascularizations for each cohort separately and as a combined population. There were 146 CHD events in the combined population. After adjustments for age, sex, body mass index, smoking, blood pressure, diabetes, and lipid-lowering therapy for the combined population, RLP-C (HR 1.23 per 1-SD increase, 95% CI 1.06-1.42, P<0.01) and intermediate-density lipoprotein cholesterol (HR 1.26 per 1-SD increase, 95% CI 1.08-1.47, P<0.01) predicted CHD during an 8-year follow-up. Associations were attenuated by high-density lipoprotein cholesterol and ultimately lost significance with inclusion of real low-density lipoprotein cholesterol, which excludes Lp(a) and IDL cholesterol fractions. Similar associations were seen in multivariable analyses within each cohort.ConclusionRLP-C levels are predictive of incident CHD in this diverse group of primary prevention subjects. Interventions aimed at reducing RLP-C to prevent CHD warrant further intensive investigation.Clinical trial registrationURL: http://www.ClinicalTrials.gov. Unique identifier: NCT00415415.

Project description:AimsIndividual risk stratification is a fundamental strategy in managing patients with heart failure (HF). Artificial intelligence, particularly machine learning (ML), can develop superior models for predicting the prognosis of HF patients, and administrative claim data (ACD) are suitable for ML analysis because ACD is a structured database. The objective of this study was to analyse ACD using an ML algorithm, predict the 1 year mortality of patients with HF, and finally develop an easy-to-use prediction model with high accuracy using the top predictors identified by the ML algorithm.Methods and resultsMachine learning-based prognostic prediction models were developed from the ACD on 10 175 HF patients from the Japanese Registry of Acute Decompensated Heart Failure with 17% mortality during 1 year follow-up. The top predictors for prognosis in HF were identified by the permutation feature importance technique, and an easy-to-use prediction model was developed based on these predictors. The c-statistics and Brier scores of the developed ML-based models were compared with those of conventional risk models: Seattle Heart Failure Model (SHFM) and Meta-Analysis Global Group in Chronic Heart Failure (MAGGIC). A voting classifier algorithm (ACD-VC) achieved the highest c-statistics among the six ML algorithms. The permutation feature importance technique enabled identification of the top predictors such as Barthel index, age, body mass index, duration of hospitalization, last hospitalization, renal disease, and non-loop diuretics use (feature importance values were 0.054, 0.025, 0.010, 0.005, 0.005, 0.004, and 0.004, respectively). Upon combination of some of the predictors that can be assessed from a brief interview, the Simple Model by ARTificial intelligence for HF risk stratification (SMART-HF) was established as an easy-to-use prediction model. Compared with the conventional models, SMART-HF achieved a higher c-statistic {ACD-VC: 0.777 [95% confidence interval (CI) 0.751-0.803], SMART-HF: 0.765 [95% CI 0.739-0.791], SHFM: 0.713 [95% CI 0.684-0.742], MAGGIC: 0.726 [95% CI 0.698-0.753]} and better Brier scores (ACD-VC: 0.121, SMART-HF: 0.124, SHFM: 0.139, MAGGIC: 0.130).ConclusionsThe ML model based on ACD predicted the 1 year mortality of HF patients with high accuracy, and SMART-HF along with the ML model achieved superior performance to that of the conventional risk models. The SMART-HF model has the clear merit of easy operability even by non-healthcare providers with a user-friendly online interface (https://hfriskcalculator.herokuapp.com/). Risk models developed using SMART-HF may provide a novel modality for risk stratification of patients with HF.

Dataset Information

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning.

Publications

Blood-Based Biomarkers for Predicting the Risk for Five-Year Incident Coronary Heart Disease in the Framingham Heart Study via Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets