Coronary Heart Disease Prediction Model Research Articles

An innovative model for predicting coronary heart disease using triglyceride-glucose index: a machine learning-based cohort study

BackgroundVarious predictive models have been developed for predicting the incidence of coronary heart disease (CHD), but none of them has had optimal predictive value. Although these models consider diabetes as an important CHD risk factor, they do not consider insulin resistance or triglyceride (TG). The unsatisfactory performance of these prediction models may be attributed to the ignoring of these factors despite their proven effects on CHD. We decided to modify standard CHD predictive models through machine learning to determine whether the triglyceride-glucose index (TyG-index, a logarithmized combination of fasting blood sugar (FBS) and TG that demonstrates insulin resistance) functions better than diabetes as a CHD predictor.MethodsTwo-thousand participants of a community-based Iranian population, aged 20–74 years, were investigated with a mean follow-up of 9.9 years (range: 7.6–12.2). The association between the TyG-index and CHD was investigated using multivariate Cox proportional hazard models. By selecting common components of previously validated CHD risk scores, we developed machine learning models for predicting CHD. The TyG-index was substituted for diabetes in CHD prediction models. All components of machine learning models were explained in terms of how they affect CHD prediction. CHD-predicting TyG-index cut-off points were calculated.ResultsThe incidence of CHD was 14.5%. Compared to the lowest quartile of the TyG-index, the fourth quartile had a fully adjusted hazard ratio of 2.32 (confidence interval [CI] 1.16–4.68, p-trend 0.04). A TyG-index > 8.42 had the highest negative predictive value for CHD. The TyG-index-based support vector machine (SVM) performed significantly better than diabetes-based SVM for predicting CHD. The TyG-index was not only more important than diabetes in predicting CHD; it was the most important factor after age in machine learning models.ConclusionWe recommend using the TyG-index in clinical practice and predictive models to identify individuals at risk of developing CHD and to aid in its prevention.

Comparison of Coronary Heart Disease Prediction models using various Machine Learning Algorithms

In the health sector, Data Analytics and Machine Learning (ML) methods are taking over role of skill and experience of a doctor especially in diagnosing diseases and preventive health measures. The health care industry is collecting very large amount of data related to patients, his medical history for preventive medication and diagnosing disease well in time and more accurately. In this paper, a comparison of five classification machine learning methods viz. Decision Tree, Random Forests, Support Vector Machine, Artificial Neural Network and Fuzzy Logic based soft computing method is done for heart disease diagnosis on the basis of data available on public domain. Out of 76 parameters collected for a patient, only 15 medical parameters such as blood pressure, sex, age, obesity and cholesterol level are used for predicting heart disease of patients.

Identification and Validation of Plasma Metabolomics Reveal Potential Biomarkers for Coronary Heart Disease.

Coronary heart disease (CHD) is a prevalent and chronic life-threatening disease. However, there is no reliable way for early diagnosis and prevention of CHD so far. The precise molecular pathological mechanism of CHD remains obscure. Therefore, developing novel biomarkers is urgently needed.In order to evaluate the potential of untargeted plasma metabolomics in biomarker discovery for characterizing CHD, plasma metabolites from patients newly diagnosed with CHD and controls were profiled using liquid chromatography quadrupole time-of-flight mass spectrometry. Differential metabolites were identified using both univariate and multivariate statistical analyses. Metabolites with significant changes were subjected to binary logistic regression analysis, and a CHD prediction model was established. A total of 28 differential plasma metabolites were identified, of which the concentrations of 11 increased significantly and those of 17 decreased significantly in patients with CHD compared with controls. The altered metabolic pathways included reduced phospholipid metabolism, increased monoglyceride metabolism, and abnormal fatty acid metabolism. Furthermore, binary logistic regression showed that nine metabolites could be used as potential plasma biomarkers for the diagnosis of CHD. The prediction model based on these nine metabolites was then tested with an independent cohort of samples (area under the curve = 0.929).Our plasma metabolomics study not only yielded fundamental insights into dysregulated metabolism in CHD but also presented a combinatorial biomarker that might support the clinical diagnosis of CHD.

New risk prediction model of coronary heart disease in participants with and without diabetes: Assessments of the Framingham risk and Suita scores in 3-year longitudinal database in a Japanese population

The Framingham Risk Score (FRS) has been reported to predict coronary heart disease (CHD), but its assessment has been unsuccessful in Asian population. We aimed to assess FRS and Suita score (a Japanese CHD prediction model) in a Japanese nation-wide annual health check program, participants aged 40–79 years were followed up longitudinally from 2008 to 2011. Of 35,379 participants analyzed, 1,234 had new-onset CHD. New-onset CHD was observed in diabetic men [6.00%], non-diabetic men [3.96%], diabetic women [5.51%], and non-diabetic women [2.86%], respectively. Area under the curve (AUC) of receiver operating characteristic (ROC) curve for CHD prediction were consistently low in Suita score (TC), FRS (TC) and NCEP-ATPIII FRS (TC), suggesting that these scores have only a limited power. ROC, net reclassification improvement (NRI), integrated discrimination improvement (IDI), and decision curve analysis (DCA) and Hosmer–Lemeshow goodness-of-fit test did not show clear differences between Suita score (TC) and FRS (TC). New models combining waist circumference ≥85 cm in men or proteinuria ≥1+ in women to Suita score (TC) was superior in diabetic men and women. New models could be useful to predict 3-year risk of CHD at least in Japanese population especially in diabetic population.

Comparing the Consistency and Performance of Various Coronary Heart Disease Prediction Models for Primary Prevention Using a National Representative Cohort in Taiwan.

Predicting future coronary artery disease (CAD) risk by model-based approaches can facilitate identification of high-risk individuals for prevention and management. Therefore, we compared the consistency and performance of various CAD models for primary prevention using 1 external validation dataset from a national representative cohort in Taiwan.Methods and Results:The 10 CAD prediction models were assessed in a validation cohort of 3559 participants (≥35 years old, 53.5% women) from a Taiwanese national representative cohort that was followed up for a median 9.70 (interquartile range, 9.63-9.74) years; 63 cases were documented as developing CAD events. The overall κ value was 0.51 for all 10 models, with a higher value for women than for men (0.53 for women, 0.40 for men). In addition, the areas under the receiver operating characteristics curves ranged from 0.804 (95% confidence interval, 0.758-0.851) to 0.847 (95% confidence interval, 0.805-0.889). All non-significant chi-square values indicated good calibration ability. Our study demonstrated these 10 CAD prediction models for primary prevention were feasible and validated for use in Taiwanese subjects. Further studies of screening and management are warranted.

Utility of genetic and non-genetic risk factors in predicting coronary heart disease in Singaporean Chinese.

Background Although numerous phenotype based equations for predicting risk of 'hard' coronary heart disease are available, data on the utility of genetic information for such risk prediction is lacking in Chinese populations. Design Case-control study nested within the Singapore Chinese Health Study. Methods A total of 1306 subjects comprising 836 men (267 incident cases and 569 controls) and 470 women (128 incident cases and 342 controls) were included. A Genetic Risk Score comprising 156 single nucleotide polymorphisms that have been robustly associated with coronary heart disease or its risk factors ( p < 5 × 10-8) in at least two independent cohorts of genome-wide association studies was built. For each gender, three base models were used: recalibrated Adult Treatment Panel III (ATPIII) Model (M1); ATP III model fitted using Singapore Chinese Health Study data (M2) and M3: M2 + C-reactive protein + creatinine. Results The Genetic Risk Score was significantly associated with incident 'hard' coronary heart disease ( p for men: 1.70 × 10-10-1.73 × 10-9; p for women: 0.001). The inclusion of the Genetic Risk Score in the prediction models improved discrimination in both genders (c-statistics: 0.706-0.722 vs. 0.663-0.695 from base models for men; 0.788-0.790 vs. 0.765-0.773 for women). In addition, the inclusion of the Genetic Risk Score also improved risk classification with a net gain of cases being reclassified to higher risk categories (men: 12.4%-16.5%; women: 10.2% (M3)), while not significantly reducing the classification accuracy in controls. Conclusions The Genetic Risk Score is an independent predictor for incident 'hard' coronary heart disease in our ethnic Chinese population. Inclusion of genetic factors into coronary heart disease prediction models could significantly improve risk prediction performance.

Child abuse/neglect risk assessment under field practice conditions: Tests of external and temporal validity and comparison with heart disease prediction

Objectives(1) Identify validation design and accuracy assessment standards for medical prognostic models applicable to evaluation of child abuse/neglect (CA/N) risk assessment models. (2) Assess the accuracy of the California Family Risk Assessment (CFRA) in predicting CA/N using the foregoing standards. (3) Compare the prediction accuracy of the CFRA with the prediction accuracy of coronary heart disease (CHD) prediction models. Questions addressed(1) What validation design and accuracy assessment standards are used to evaluate medical prognostic models? (2) What is the evidence for the accuracy of the CFRA using those standards? (3) How does the accuracy of the CFRA in predicting CA/N compare with the accuracy of CHD prediction models, which are a reasonable exemplar for the CA/N prediction effort? MethodAn external validation sample of 236 California reports of CA/N from San Luis Obispo and Sutter counties, and a larger temporal validation sample of 6307 California reports from Orange, Los Angeles, and Humboldt counties were investigated and assessed with the CFRA by line child welfare staff and were followed prospectively statewide for two years to discover reported, substantiated CA/N in any California county. CFRA accuracy in predicting substantiated CA/N was assessed by calibration and discrimination. Calibration was measured as the ratio of predicted to observed cases of CA/N seen during follow-up, with a ratio of 1.0 registering perfect calibration. Discrimination was measured by the area under the receiver operating characteristic (ROC) curve (AUC), with values from .60 to .85 found typical for medical prognostic models. CHD prediction literature was reviewed to acquire values of these accuracy measures for CHD prediction models. CFRA CA/N prediction accuracy and CHD prediction accuracy were then compared. ResultsFindings from external and temporal validation samples support the accuracy of CFRA prediction of CA/N. CFRA accuracy in predicting CA/N compared well with CHD prediction accuracy: (1) in the external validation sample, 43.42 CA/N cases were predicted during follow-up and 47 were observed, with consequent 7.6% deviation from perfect calibration. (2) In the temporal validation sample 857.49 CA/N cases were predicted and 801 were observed, with 7.1% deviation from perfect calibration. (3) The best performing of 20 Framingham CHD prediction models identified by systematic literature review predicted 222 CHD cases and 206 were observed, with 7.8% deviation from perfect calibration. (3) The CFRA external and temporal validation sample AUCs were .74 and .64, respectively. (4) For 26 CHD prediction cohorts found by literature review, the AUC mean and median values were .72 and .71, respectively, with a range from .60 to .84. Conclusions/practice implications(1) External and temporal validation results support the accuracy of the CFRA. (2) CFRA CA/N prediction accuracy parity with that for CHD prediction is encouraging, suggesting that wide use of the CFRA, properly implemented, could improve risk assessment accuracy in child protection. (3) Findings underline the importance of ensuring that no risk assessment model or method, including actuarial and consensus models and clinical judgment, is used in the field unless it has passed a test of external, or at least temporal validation.

Apolipoprotein B improves risk assessment of future coronary heart disease in the Framingham Heart Study beyond LDL-C and non-HDL-C.

Analyses using conventional statistical methodologies have yielded conflicting results as to whether low-density lipoprotein cholesterol (LDL-C) or non-high-density lipoprotein cholesterol (non-HDL-C) or apolipoprotein B (apoB) is the best marker of the apoB-associated risk of coronary heart disease. The aim of this study was to determine the additional value of apoB beyond LDL-C or non-HDL-C as a predictor of coronary heart disease. For each patient from the Framingham Offspring Cohort aged 40-75 years (n = 2966), we calculated the extent to which the observed apoB differed from the expected apoB based on their LDL-C or non-HDL-C. We added this difference to a Cox model predicting new onset coronary heart disease over a maximum of 20 years adjusting for standard risk factors plus LDL-C or non-HDL. The difference between observed and expected apoB over LDL-C or non-HDL-C was highly prognostic of future coronary heart disease events: adjusted hazard ratios 1.26 (95% confidence interval: 1.15, 1.37) and 1.20 (1.11, 1.29), respectively, for each standard deviation increase beyond expected apoB levels. When this difference between observed and expected apoB was added to standard coronary heart disease prediction models including LDL-C or non-HDL-C, prediction improved significantly (likelihood ratio test p-values <0.0001) and discrimination c-statistics increased from 0.72 to 0.73. The corresponding relative integrated discrimination improvements were 11% and 8%, respectively. apoB improves risk assessment of future coronary heart disease events over and beyond LDL-C or non-HDL-C, which is consistent with coronary risk being more closely related to the number of atherogenic apoB particles than to the mass of cholesterol within them.

Data-Mining-Based Coronary Heart Disease Risk Prediction Model Using Fuzzy Logic and Decision Tree.

ObjectivesThe importance of the prediction of coronary heart disease (CHD) has been recognized in Korea; however, few studies have been conducted in this area. Therefore, it is necessary to develop a method for the prediction and classification of CHD in Koreans.MethodsA model for CHD prediction must be designed according to rule-based guidelines. In this study, a fuzzy logic and decision tree (classification and regression tree [CART])-driven CHD prediction model was developed for Koreans. Datasets derived from the Korean National Health and Nutrition Examination Survey VI (KNHANES-VI) were utilized to generate the proposed model.ResultsThe rules were generated using a decision tree technique, and fuzzy logic was applied to overcome problems associated with uncertainty in CHD prediction.ConclusionsThe accuracy and receiver operating characteristic (ROC) curve values of the propose systems were 69.51% and 0.594, proving that the proposed methods were more efficient than other models.

Abstract 205: Potential Cardiovascular Risk Reduction in High-Risk Uninsured Patients: An Analysis of the Heart Improvement Project

Background: The Heart Improvement Project (HIP) is a cardiovascular (CV) risk reduction clinic targeting high-risk, uninsured patients. Using coronary heart disease prediction models from the Framingham Heart Study, it is possible to project an individual’s 10-year CV disease risk based on status of the following risk factors: sex, age, LDL-Cholesterol (LDL-C), HDL-Cholesterol (HDL-C), blood pressure (BP), diabetes, and smoking status. Objective: To project the reduction in CV risk associated with two levels of intervention: first-line therapy (designed to decrease the systolic BP by 15 mm Hg and LDL-C by 30%) and maximal therapy to optimally control all modifiable risk factors. Methods: Data on 251 patients (52% male, mean age 51 yrs; 48% with Diabetes, 45% smokers) from HIP were analyzed. For each patient, their Framingham Risk Scores (FRS) and 10-year Coronary Heart Disease Risk (CHDR) were calculated in three different conditions: their actual risk assessment, and that projected under first-line, and maximal therapy. The three sets of FRS and CHDR were summarized using descriptive statistics. Pairwise differences between the three sets of FRS and CHDR were tested using two-sample t-test and 95% confidence intervals for the differences were computed. Results: Table 1 shows that the mean FRSs were 7.33, 4.90, and 3.51 (under initial, first-line, and maximal conditions, respectively). The corresponding CHDRs were 13%, 8%, and 6% respectively. All comparisons were statistically significant at the p&lt;0.001 level. Conclusions: First-line interventions for BP and lipid management can yield significant improvement in CHD risk in a population of high-risk uninsured patients.

Challenges to Improve Coronary Heart Disease Risk Assessment

CORONARY HEART DISEASE (CHD) IS COMMON AND includes the diagnoses angina pectoris, myocardial infarction, and coronary disease death. Predicting the first occurrence of these events is important and may affect clinical decisions and care. It can be expected that more than a third of adult Americans will develop CHD during their lifetime, and improvements in diagnosis and care may provide great benefits. The article by Tzoulaki and colleagues assesses the scientific literature concerning efforts to improve the prediction of CHD over and above the Framingham risk score. The authors report that many articles have provided information on new risk factors, but the study designs and data analyses in those reports raise concerns about the usefulness of the new information and about how improvement over the Framingham risk score was assessed. Researchers and clinicians should understand how CHD risk estimation is undertaken and evaluated, as these methods are frequently used to assess risk of developing disease across a variety of health disciplines. Risk estimates for initial CHD events should be derived from studies based on complete information for carefully measured risk factors at baseline, adequate follow-up, and reliable outcome data. A common initial step is to use proportional hazards univariate or age-adjusted regression models. When possible, the variables of interest are analyzed as continuous measures. Factors that are significant in the univariate analyses are then considered for inclusion in multivariable prediction models. With this approach, a set of variables was developed by Framingham investigators and included age, sex, systolic blood pressure, cholesterol level, high-density lipoprotein cholesterol level, diabetes mellitus, and current smoking. This approach was further evaluated with external validation sets from cohort studies across the United States. Including newer variables is of considerable interest because factors might improve the prediction of CHD and prevention strategies might be more effective. A variety of performance criteria are used to evaluate the usefulness of CHD risk prediction and a brief summary explains the terms used to interpret these studies, including relative risk, discrimination, calibration, and reclassification. For each risk factor, proportional hazards modeling yields regression coefficients for a study cohort. The relative risk of a variable is computed by exponentiating the regression coefficient in the multivariable regression models. This measure estimates the difference in risk for an individual with a given risk factor such as cigarette smoking compared with the risk for an individual who does not smoke. An analogous approach can be undertaken to estimate effects for continuous variables by showing effects for a specific number of units for the variable or by identifying differences in risk associated with a difference in the number of units associated with a standard deviation for the factor. Discrimination is the ability of a statistical model to separate those who experience clinical CHD events from those who do not. The C statistic, analogous to the area under a receiver operating characteristic curve, is the typical performance measure used. This statistic represents an estimate of the probability that a model assigns a higher risk to those who develop CHD within a specified follow-up than to those who do not and represents a composite of the overall sensitivity and specificity of the prediction equation. Values for the C statistic range from 0.00 to 1.00; 0.50 reflects discrimination by chance. Higher values generally indicate a good level of agreement between observed and predicted risks. The average C statistic for the prediction of CHD is typically in the 0.70 range. The error associated with Cstatistic estimates can be estimated and used to compare differences in risk prediction models. Calibration measures how closely predicted estimates of absolute risk agree with actual outcomes. To present calibration analyses, the data are often separated into deciles of risk, and observed rates are tested for differences from what was expected from the estimating equation. A version of the Hosmer-Lemeshow 2 statistic can be used to evaluate how well the observed and expected agree; smaller 2 values generally indicate good calibration. A CHD prediction model might be recalibrated if it provides relatively good ranking of risk and discrimination, but the model sys-

The future impact of population growth and aging on coronary heart disease in China: projections from the Coronary Heart Disease Policy Model-China

BackgroundChina will experience an overall growth and aging of its adult population in coming decades. We used a computer model to forecast the future impact of these demographic changes on coronary heart disease (CHD) in China.MethodsThe CHD Policy Model is a validated state-transition, computer simulation of CHD on a national scale. China-specific CHD risk factor, incidence, case-fatality, and prevalence data were incorporated, and a CHD prediction model was generated from a Chinese cohort study and calibrated to age-specific Chinese mortality rates. Disability-adjusted life years (DALYs) due to CHD were calculated using standard methods. The projected population of China aged 35–84 years was entered, and CHD events, deaths, and DALYs were simulated over 2000–2029. CHD risk factors other than age and case-fatality were held at year 2000 levels. Sensitivity analyses tested uncertainty regarding CHD mortality coding, the proportion of total deaths attributable to CHD, and case-fatality.ResultsWe predicted 7.8 million excess CHD events (a 69% increase) and 3.4 million excess CHD deaths (a 64% increase) in the decade 2020–2029 compared with 2000–2009. For 2030, we predicted 71% of almost one million annual CHD deaths will occur in persons ≥65 years old, while 67% of the growing annual burden of CHD death and disability will weigh on adults <65 years old. Substituting alternate CHD mortality assumptions led to 17–20% more predicted CHD deaths over 2000–2029, though the pattern of increases in CHD events and deaths over time remained.ConclusionWe forecast that absolute numbers of CHD events and deaths will increase dramatically in China over 2010–2029, due to a growing and aging population alone. Recent data suggest CHD risk factor levels are increasing, so our projections may underestimate the extent of the potential CHD epidemic in China.

Usefulness of Genetic Polymorphisms and Conventional Risk Factors to Predict Coronary Heart Disease in Patients With Familial Hypercholesterolemia

Familial hypercholesterolemia (FH) is an autosomal dominant disorder with an associated high risk of coronary heart disease (CHD). The considerable variation in age of onset of CHD in patients with FH is believed to arise from conventional risk factors, as well as genetic variation other than in the low-density lipoprotein receptor gene. The degree to which currently known genetic variants can improve the prediction of CHD risk beyond conventional risk factors in this disorder was investigated. Fourteen genetic variants recently identified for association with CHD in a Dutch FH population were considered. Prediction models were constructed using Cox proportional hazards models, and predictive value was assessed using a concordance statistic (c statistic). A total of 1,337 patients with FH were completely genotyped for all genetic variants. Hazard ratios of the genetic variants ranged from 0.61 to 0.74 and 1.24 to 2.33. The c statistic of the CHD prediction model based on genetic variants was 0.59, denoting little discrimination. The model based on conventional risk factors had a c statistic of 0.75, denoting moderate discrimination. Adding genetic test results to this model increased the c statistic to 0.76. In conclusion, the contribution of 14 genetic variants to the prediction of CHD risk in patients with FH was limited. To improve genome-based prediction of CHD, larger numbers of genetic variants need to be identified that either on their own or in gene-gene interaction have substantial effects on CHD risk.