Machine learning and atherosclerotic cardiovascular disease risk prediction in a multi-ethnic population.
Ontology highlight
ABSTRACT:
SUBMITTER: Ward A
PROVIDER: S-EPMC7511400 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:RATIONALE:Machine learning may be useful to characterize cardiovascular risk, predict outcomes, and identify biomarkers in population studies. OBJECTIVE:To test the ability of random survival forests, a machine learning technique, to predict 6 cardiovascular outcomes in comparison to standard cardiovascular risk scores. METHODS AND RESULTS:We included participants from the MESA (Multi-Ethnic Study of Atherosclerosis). Baseline measurements were used to predict cardiovascular outcomes over 12 years of follow-up. MESA was designed to study progression of subclinical disease to cardiovascular events where participants were initially free of cardiovascular disease. All 6814 participants from MESA, aged 45 to 84 years, from 4 ethnicities, and 6 centers across the United States were included. Seven-hundred thirty-five variables from imaging and noninvasive tests, questionnaires, and biomarker panels were obtained. We used the random survival forests technique to identify the top-20 predictors of each outcome. Imaging, electrocardiography, and serum biomarkers featured heavily on the top-20 lists as opposed to traditional cardiovascular risk factors. Age was the most important predictor for all-cause mortality. Fasting glucose levels and carotid ultrasonography measures were important predictors of stroke. Coronary Artery Calcium score was the most important predictor of coronary heart disease and all atherosclerotic cardiovascular disease combined outcomes. Left ventricular structure and function and cardiac troponin-T were among the top predictors for incident heart failure. Creatinine, age, and ankle-brachial index were among the top predictors of atrial fibrillation. TNF-? (tissue necrosis factor-?) and IL (interleukin)-2 soluble receptors and NT-proBNP (N-Terminal Pro-B-Type Natriuretic Peptide) levels were important across all outcomes. The random survival forests technique performed better than established risk scores with increased prediction accuracy (decreased Brier score by 10%-25%). CONCLUSIONS:Machine learning in conjunction with deep phenotyping improves prediction accuracy in cardiovascular event prediction in an initially asymptomatic population. These methods may lead to greater insights on subclinical disease markers without apriori assumptions of causality. CLINICAL TRIAL REGISTRATION:URL: http://www.clinicaltrials.gov. Unique identifier: NCT00005487.
| S-EPMC5640485 | biostudies-literature
Project description:IntroductionThis study developed a novel risk assessment model to predict the occurrence of cardiovascular disease (CVD) events. It uses a Genetic Algorithm (GA) to develop an easy-to-use model with high accuracy, calibrated based on the Isfahan Cohort Study (ICS) database.MethodsThe ICS was a population-based prospective cohort study of 6,504 healthy Iranian adults aged ≥ 35 years followed for incident CVD over ten years, from 2001 to 2010. To develop a risk score, the problem of predicting CVD was solved using a well-designed GA, and finally, the results were compared with classic machine learning (ML) and statistical methods.ResultsA number of risk scores such as the WHO, and PARS models were utilized as the baseline for comparison due to their similar chart-based models. The Framingham and PROCAM models were also applied to the dataset, with the area under a Receiver Operating Characteristic curve (AUROC) equal to 0.633 and 0.683, respectively. However, the more complex Deep Learning model using a three-layered Convolutional Neural Network (CNN) performed best among the ML models, with an AUROC of 0.74, and the GA-based eXplanaible Persian Atherosclerotic CVD Risk Stratification (XPARS) showed higher performance compared to the statistical methods. XPARS with eight features showed an AUROC of 0.76, and the XPARS with four features, showed an AUROC of 0.72.ConclusionA risk model that is extracted using GA substantially improves the prediction of CVD compared to conventional methods. It is clear, interpretable and can be a suitable replacement for conventional statistical methods.
| S-EPMC9333440 | biostudies-literature
Project description:Machine learning is often perceived as a sophisticated technology accessible only by highly trained experts. This prevents many physicians and biologists from using this tool in their research. The goal of this paper is to eliminate this out-dated perception. We argue that the recent development of auto machine learning techniques enables biomedical researchers to quickly build competitive machine learning classifiers without requiring in-depth knowledge about the underlying algorithms. We study the case of predicting the risk of cardiovascular diseases. To support our claim, we compare auto machine learning techniques against a graduate student using several important metrics, including the total amounts of time required for building machine learning models and the final classification accuracies on unseen test datasets. In particular, the graduate student manually builds multiple machine learning classifiers and tunes their parameters for one month using scikit-learn library, which is a popular machine learning library to obtain ones that perform best on two given, publicly available datasets. We run an auto machine learning library called auto-sklearn on the same datasets. Our experiments find that automatic machine learning takes 1 h to produce classifiers that perform better than the ones built by the graduate student in one month. More importantly, building this classifier only requires a few lines of standard code. Our findings are expected to change the way physicians see machine learning and encourage wide adoption of Artificial Intelligence (AI) techniques in clinical domains.
| S-EPMC6678298 | biostudies-literature
Project description:BackgroundData derived from the Cardiovascular Outcomes in Renal Atherosclerotic Lesions (CORAL) study were analyzed in an effort to employ machine learning methods to predict the composite endpoint described in the original study.MethodsWe identified 573 CORAL subjects with complete baseline data and the presence or absence of a composite endpoint for the study. These data were subjected to several models including a generalized linear (logistic-linear) model, support vector machine, decision tree, feed-forward neural network, and random forest, in an effort to attempt to predict the composite endpoint. The subjects were arbitrarily divided into training and testing subsets according to an 80%:20% distribution with various seeds. Prediction models were optimized within the CARET package of R.ResultsThe best performance of the different machine learning techniques was that of the random forest method which yielded a receiver operator curve (ROC) area of 68.1%±4.2% (mean ± SD) on the testing subset with ten different seed values used to separate training and testing subsets. The four most important variables in the random forest method were SBP, serum creatinine, glycosylated hemoglobin, and DBP. Each of these variables was also important in at least some of the other methods. The treatment assignment group was not consistently an important determinant in any of the models.ConclusionPrediction of a composite cardiovascular outcome was difficult in the CORAL population, even when employing machine learning methods. Assignment to either the stenting or best medical therapy group did not serve as an important predictor of composite outcome.Clinical trial registrationClinicalTrials.gov, NCT00081731.
| S-EPMC6433104 | biostudies-literature
Project description:BackgroundCurrent approaches to predict cardiovascular risk fail to identify many people who would benefit from preventive treatment, while others receive unnecessary intervention. Machine-learning offers opportunity to improve accuracy by exploiting complex interactions between risk factors. We assessed whether machine-learning can improve cardiovascular risk prediction.MethodsProspective cohort study using routine clinical data of 378,256 patients from UK family practices, free from cardiovascular disease at outset. Four machine-learning algorithms (random forest, logistic regression, gradient boosting machines, neural networks) were compared to an established algorithm (American College of Cardiology guidelines) to predict first cardiovascular event over 10-years. Predictive accuracy was assessed by area under the 'receiver operating curve' (AUC); and sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV) to predict 7.5% cardiovascular risk (threshold for initiating statins).Findings24,970 incident cardiovascular events (6.6%) occurred. Compared to the established risk prediction algorithm (AUC 0.728, 95% CI 0.723-0.735), machine-learning algorithms improved prediction: random forest +1.7% (AUC 0.745, 95% CI 0.739-0.750), logistic regression +3.2% (AUC 0.760, 95% CI 0.755-0.766), gradient boosting +3.3% (AUC 0.761, 95% CI 0.755-0.766), neural networks +3.6% (AUC 0.764, 95% CI 0.759-0.769). The highest achieving (neural networks) algorithm predicted 4,998/7,404 cases (sensitivity 67.5%, PPV 18.4%) and 53,458/75,585 non-cases (specificity 70.7%, NPV 95.7%), correctly predicting 355 (+7.6%) more patients who developed cardiovascular disease compared to the established algorithm.ConclusionsMachine-learning significantly improves accuracy of cardiovascular risk prediction, increasing the number of patients identified who could benefit from preventive treatment, while avoiding unnecessary treatment of others.
| S-EPMC5380334 | biostudies-literature
Project description:Predicting the risk of cardiovascular disease is the key to primary prevention. Machine learning has attracted attention in analyzing increasingly large, complex healthcare data. We assessed discrimination and calibration of pre-existing cardiovascular risk prediction models and developed machine learning-based prediction algorithms. This study included 222,998 Korean adults aged 40-79 years, naïve to lipid-lowering therapy, had no history of cardiovascular disease. Pre-existing models showed moderate to good discrimination in predicting future cardiovascular events (C-statistics 0.70-0.80). Pooled cohort equation (PCE) specifically showed C-statistics of 0.738. Among other machine learning models such as logistic regression, treebag, random forest, and adaboost, the neural network model showed the greatest C-statistic (0.751), which was significantly higher than that for PCE. It also showed improved agreement between the predicted risk and observed outcomes (Hosmer-Lemeshow χ2 = 86.1, P < 0.001) than PCE for whites did (Hosmer-Lemeshow χ2 = 171.1, P < 0.001). Similar improvements were observed for Framingham risk score, systematic coronary risk evaluation, and QRISK3. This study demonstrated that machine learning-based algorithms could improve performance in cardiovascular risk prediction over contemporary cardiovascular risk models in statin-naïve healthy Korean adults without cardiovascular disease. The model can be easily adopted for risk assessment and clinical decision making.
| S-EPMC8076166 | biostudies-literature
Project description:Background: Cardiovascular disease (CVD) screening entails precise event prediction to orient risk stratification, resource allocation, and insurance policy. We used random survival forests (RSF) to identify markers of incident CVD among Japanese adults enrolled in an employer-mandated screening program. Methods and Results: We examined biomarker, health history, medication use, and lifestyle data from 155,108 adults aged ≥40 years. The occurrence of coronary artery disease (CAD) or atherosclerotic CVD (ASCVD) events was examined over 6 years of follow-up. The analysis used RSF to identify predictors, then investigated simplified RSF models with fewer predictors for individual-level risk prediction. Data were split into training (70%) and test (30%) datasets. At baseline, the median patient age was 47 years (interquartile range 41-56 years), with 65% males. In all, 1,642 CAD and 2,164 ASCVD events were observed. RSF identified history of heart disease, age, self-reported blood pressure medication, HbA1c, fasting blood sugar, and high-density lipoprotein as important markers of both endpoints. RSF analyses with only the top 20 predictors demonstrated good performance, with areas under the curve of >84% for CAD and >82% for ASCVD in test data across 6 years. Conclusions: We present a machine learning technique for accurate assessment of cardiovascular risk using employer-mandated annual health checkup information. The algorithm produces individual-level risk curves over time, empowering clinicians to efficiently implement prevention strategies in a low-risk population.
| S-EPMC9726526 | biostudies-literature
Project description:BackgroundIdentifying 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.Methods and findingsUsing 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).ConclusionsOur 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.
| S-EPMC6519796 | biostudies-literature
Project description:ImportanceThe interplay of self-rated health (SRH), coronary artery calcium (CAC) scores, and cardiovascular risk is poorly described.ObjectivesTo assess the degree of correlation between SRH and CAC, to determine whether these measures are complementary for risk prediction, and to assess the incremental value of the addition of SRH to established risk tools.Design, setting, and participantsThe Multi-Ethnic Study of Atherosclerosis (MESA) is a large population-based prospective cohort study of adults aged 45 to 84 years who were recruited from 6 US communities. A total of 6764 participants without baseline cardiovascular disease (CVD) were included in the analysis. Data were collected from July 2000 through August 2002. Follow-up was completed by December 2013, and data were analyzed from October 2018 to December 2018.ExposuresThe EVGGFP (excellent, very good, good, fair, and poor) self-assessment of overall health (assessed before the baseline study examination) and CAC score. The EVGGFP rating was categorized as poor/fair, good, very good, or excellent.Main outcomes and measuresHard coronary heart disease (CHD) events, hard CVD events, and all-cause mortality during a median follow-up of 13.2 years (interquartile range, 12.7-13.7 years).ResultsAmong the study population of 6764 participants, the mean (SD) age was 62.1 (10.2) years, and 52.9% were women. The EVGGFP rating was strongly associated with age, sex, race/ethnicity, educational and income levels, healthy diet and physical activity, and cardiovascular risk factors. Despite encapsulating many risk variables, no correlation (r = -0.007; P = .57) or association between EVGGFP and the presence (χ2 = 0.84; P = .84) or severity (χ2 = 4.64; P = .86) of CAC was found. During follow-up, 1161 deaths, 637 hard CVD events, and 405 hard CHD events were recorded. In models adjusted for age, sex, race/ethnicity, and CAC, participants who reported excellent health had a 45% lower risk of CVD (hazard ratio [HR], 0.55; 95% CI, 0.39-0.77) and a 42% lower risk of CHD (HR, 0.58; 95% CI, 0.37-0.90) compared with those who reported poor/fair health. Participants in the excellent SRH category who had any CAC had markedly elevated risk of hard CHD (HR, 6.19; 95% CI, 2.1-18.3) and CVD (HR, 6.50; 95% CI, 2.7-15.6) events compared with those with a CAC score of 0. The addition of the EVGGFP rating to CAC improved the area under the curve (C statistic) for CHD events (0.725 vs 0.734; P = .007), CVD events (0.693 vs 0.706; P < .001), and all-cause mortality (0.685 vs 0.707; P < .001). However, the addition of the EVGGFP rating to the combination of CAC and atherosclerotic CVD risk score did not significantly improve C statistics for CHD events (0.751 vs 0.753; P = .39), CVD events (0.739 vs 0.741; P = .18), or all-cause mortality (0.779 vs 0.781; P = .13).Conclusions and relevanceAlthough SRH and CAC integrate many risk variables, this study suggests that they are poorly correlated and have complementary predictive utility. A perception of excellent health does not obviate the need for definitive assessment of CVD risk, whereas fair/poor perceived health may serve as a risk enhancer, arguing for advanced risk assessment in selected clinical scenarios.
| S-EPMC6484585 | biostudies-literature
Project description:Gene expression profiles were generated from 199 primary breast cancer patients. Samples 1-176 were used in another study, GEO Series GSE22820, and form the training data set in this study. Sample numbers 200-222 form a validation set. This data is used to model a machine learning classifier for Estrogen Receptor Status. RNA was isolated from 199 primary breast cancer patients. A machine learning classifier was built to predict ER status using only three gene features.
2013-01-01 | E-GEOD-29210 | biostudies-arrayexpress