Development and Validation of a Predictive Model for Coronary Artery Disease Using Machine Learning

Construction and Validation of a Predictive Model for Coronary Artery Disease Using Extreme Gradient Boosting

Purpose

Early recognition of coronary artery disease (CAD) could delay its progress and significantly reduce mortality. Sensitive, specific, cost-efficient and non-invasive indicators for assessing individual CAD risk in community population screening are urgently needed.

Patients and Methods

3112 patients with CAD and 3182 controls were recruited from three clinical centers in China, and differences in baseline and clinical characteristics were compared. For the discovery cohort, the least absolute shrinkage and selection operator (LASSO) regression was used to identify significant features and four machine learning algorithms (logistic regression, support vector machine (SVM), random forest (RF) and extreme gradient boosting (XGBoost)) were applied to construct models for CAD risk assessment, the receiver operating characteristics (ROC) curve and precision-recall (PR) curve were conducted to evaluate their predictive accuracy. The optimal model was interpreted by Shapley additive explanations (SHAP) analysis and assessed by the ROC curve, calibration curve, and decision curve analysis (DCA) and validated by two external cohorts.

Results

Using LASSO filtration, all included variables were considered to be statistically significant. Four machine learning models were constructed based on these features and the results of ROC and PR curve implied that the XGBoost model exhibited the highest predictive performance, which yielded a high area of ROC curve (AUC) of 0.988 (95% CI: 0.986-0.991) to distinguish CAD patients from controls with a sensitivity of 94.6% and a specificity of 94.6%. The calibration curve showed that the predicted results were in good agreement with actual observations, and DCA exhibited a better net benefit across a wide range of threshold probabilities. External validation of the model also exhibited favorable discriminatory performance, with an AUC, sensitivity, and specificity of 0.953 (95% CI: 0.945-0.960), 89.9%, and 87.1% in the validation cohort, and 0.935 (95% CI: 0.915-0.955), 82.0%, and 90.3% in the replication cohort.

Conclusion

Our model is highly informative for clinical practice and will be conducive to primary prevention and tailoring the precise management for CAD patients.

Explainable coronary artery disease prediction model based on AutoGluon from AutoML framework

Objective

This study focuses on the innovative application of Automated Machine Learning (AutoML) technology in cardiovascular medicine to construct an explainable Coronary Artery Disease (CAD) prediction model to support the clinical diagnosis of CAD.

Methods

This study utilizes a combined data set of five public data sets related to CAD. An ensemble model is constructed using the AutoML open-source framework AutoGluon to evaluate the feasibility of AutoML in constructing a disease prediction model in cardiovascular medicine. The performance of the ensemble model is compared against individual baseline models. Finally, the disease prediction ensemble model is explained using SHapley Additive exPlanations (SHAP).

Results

The experimental results show that the AutoGluon-based ensemble model performs better than the individual baseline models in predicting CAD. It achieved an accuracy of 0.9167 and an AUC of 0.9562 in 4-fold cross-bagging. SHAP measures the importance of each feature to the prediction of the model and explains the prediction results of the model.

Conclusion

This study demonstrates the feasibility and efficacy of AutoML technology in cardiovascular medicine and highlights its potential in disease prediction. AutoML reduces the barriers to model building and significantly improves prediction accuracy. Additionally, the integration of SHAP enhances model transparency and explainability, which is critical to ensuring model credibility and widespread adoption in cardiovascular medicine.

Machine learning reveals serum myristic acid, palmitic acid and heptanoylcarnitine as biomarkers of coronary artery disease risk in patients with type 2 diabetes mellitus

BACKGROUND

Coronary heart disease (CHD) is the most important complication of type 2 diabetes mellitus (T2DM) and the leading cause of death. Identifying the risk of CHD in T2DM patients is important for early clinical intervention.

METHODS

A total of 213 participants, including 81 healthy controls (HCs), 69 T2DM patients and 63 T2DM patients complicated with CHD were recruited in this study. Serum metabolomics were conducted by using ultra-high performance liquid chromatography coupled with tandem mass spectrometry (UHPLC-MS/MS). Demographic information and clinical laboratory test results were also collected.

RESULTS

Metabolic phenotypes were significantly altered among HC, T2DM and T2DM-CHD. Acylcarnitines were the most disturbed metabolites between T2DM patients and HCs. Lower levels of bile acids and higher levels of fatty acids in serum were closely associated with CHD risk in T2DM patients. Artificial neural network model was constructed for the discrimination of T2DM and T2DM complicated with CHD based on myristic acid, palmitic acid and heptanoylcarnitine, with accuracy larger than 0.95 in both training set and testing set.

CONCLUSION

Altogether, these findings suggest that myristic acid, palmitic acid and heptanoylcarnitine have a good prospect for the warning of CHD complications in T2DM patients, and are superior to traditional lipid, blood glucose and blood pressure indicators.

Risk factors for high CAD-RADS scoring in CAD patients revealed by machine learning methods: a retrospective study

OBJECTIVE

This study aimed to investigate a variety of machine learning (ML) methods to predict the association between cardiovascular risk factors and coronary artery disease-reporting and data system (CAD-RADS) scores.

METHODS

This is a retrospective cohort study. Demographical, cardiovascular risk factors and coronary CT angiography (CCTA) characteristics of the patients were obtained. Coronary artery disease (CAD) was evaluated using CAD-RADS score. The stenosis severity component of the CAD-RADS was stratified into two groups: CAD-RADS score 0-2 group and CAD-RADS score 3-5 group. CAD-RADS scores were predicted with random forest (RF), k-nearest neighbors (KNN), support vector machines (SVM), neural network (NN), decision tree classification (DTC) and linear discriminant analysis (LDA). Prediction sensitivity, specificity, accuracy and area under the curve (AUC) were calculated. Feature importance analysis was utilized to find the most important predictors.

RESULTS

A total of 442 CAD patients with CCTA examinations were included in this study. 234 (52.9%) subjects were CAD-RADS score 0-2 group and 208 (47.1%) were CAD-RADS score 3-5 group. CAD-RADS score 3-5 group had a high prevalence of hypertension (66.8%), hyperlipidemia (50%) and diabetes mellitus (DM) (35.1%). Age, systolic blood pressure (SBP), mean arterial pressure, pulse pressure, pulse pressure index, plasma fibrinogen, uric acid and blood urea nitrogen were significantly higher (p < 0.001), and high-density lipoprotein (HDL-C) lower (p < 0.001) in CAD-RADS score 3-5 group compared to the CAD-RADS score 0-2 group. Nineteen features were chosen to train the models. RF (AUC = 0.832) and LDA (AUC = 0.81) outperformed SVM (AUC = 0.772), NN (AUC = 0.773), DTC (AUC = 0.682), KNN (AUC = 0.707). Feature importance analysis indicated that plasma fibrinogen, age and DM contributed most to CAD-RADS scores.

CONCLUSION

ML algorithms are capable of predicting the correlation between cardiovascular risk factors and CAD-RADS scores with high accuracy.

Identification of DNA methylation-regulated genes as potential biomarkers for coronary heart disease via machine learning in the Framingham Heart Study

Background

DNA methylation-regulated genes have been demonstrated as the crucial participants in the occurrence of coronary heart disease (CHD). The machine learning based on DNA methylation-regulated genes has tremendous potential for mining non-invasive predictive biomarkers and exploring underlying new mechanisms of CHD.

Results

First, the 2085 age-gender-matched individuals in Framingham Heart Study (FHS) were randomly divided into training set and validation set. We then integrated methylome and transcriptome data of peripheral blood leukocytes (PBLs) from the training set to probe into the methylation and expression patterns of CHD-related genes. A total of five hub DNA methylation-regulated genes were identified in CHD through dimensionality reduction, including ATG7, BACH2, CDKN1B, DHCR24 and MPO. Subsequently, methylation and expression features of the hub DNA methylation-regulated genes were used to construct machine learning models for CHD prediction by LightGBM, XGBoost and Random Forest. The optimal model established by LightGBM exhibited favorable predictive capacity, whose AUC, sensitivity, and specificity were 0.834, 0.672, 0.864 in the validation set, respectively. Furthermore, the methylation and expression statuses of the hub genes were verified in monocytes using methylation microarray and transcriptome sequencing. The methylation statuses of ATG7, DHCR24 and MPO and the expression statuses of ATG7, BACH2 and DHCR24 in monocytes of our study population were consistent with those in PBLs from FHS.

Conclusions

We identified five DNA methylation-regulated genes based on a predictive model for CHD using machine learning, which may clue the new epigenetic mechanism for CHD.

Supplementary Information

The online version contains supplementary material available at 10.1186/s13148-022-01343-2.

Construction of a neural network diagnostic model and investigation of immune infiltration characteristics for Crohn’s disease

Objective: Crohn’s disease (CD), a chronic recurrent illness, is a type of inflammatory bowel disease whose incidence and prevalence rates are gradually increasing. However, there is no universally accepted criterion for CD diagnosis. The aim of this study was to create a diagnostic prediction model for CD and identify immune cell infiltration features in CD.

Methods: In this study, gene expression microarray datasets were obtained from the Gene Expression Omnibus (GEO) database. Then, we identified differentially expressed genes (DEGs) between 178 CD and 38 control cases. Enrichment analysis of DEGs was also performed to explore the biological role of DEGs. Moreover, the “randomForest” package was applied to select core genes that were used to create a neural network model. Finally, in the training cohort, we used CIBERSORT to evaluate the immune landscape between the CD and normal groups.

Results: The results of enrichment analysis revealed that these DEGs may be involved in biological processes associated with immunity and inflammatory responses. Moreover, the top 3 hub genes in the protein-protein interaction network were IL-1β, CCL2, and CXCR2. The diagnostic model allowed significant discrimination with an area under the ROC curve of 0.984 [95% confidence interval: 0.971–0.993]. A validation cohort (GSE36807) was utilized to ensure the reliability and applicability of the model. In addition, the immune infiltration analysis indicated nine different immune cell types were significantly different between the CD and healthy control groups.

Conclusion: In summary, this study offers a novel insight into the diagnosis of CD and provides potential biomarkers for the precise treatment of CD.

Prediction of Atrial Fibrillation in Hospitalized Elderly Patients With Coronary Heart Disease and Type 2 Diabetes Mellitus Using Machine Learning: A Multicenter Retrospective Study

Background

The objective of this study was to use machine learning algorithms to construct predictive models for atrial fibrillation (AF) in elderly patients with coronary heart disease (CHD) and type 2 diabetes mellitus (T2DM).

Methods

The diagnosis and treatment data of elderly patients with CHD and T2DM, who were treated in four tertiary hospitals in Chongqing, China from 2015 to 2021, were collected. Five machine learning algorithms: logistic regression, logistic regression+least absolute shrinkage and selection operator, classified regression tree (CART), random forest (RF) and extreme gradient lifting (XGBoost) were used to construct the prediction models. The area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy were used as the comparison measures between different models.

Results

A total of 3,858 elderly patients with CHD and T2DM were included. In the internal validation cohort, XGBoost had the highest AUC (0.743) and sensitivity (0.833), and RF had the highest specificity (0.753) and accuracy (0.735). In the external verification, RF had the highest AUC (0.726) and sensitivity (0.686), and CART had the highest specificity (0.925) and accuracy (0.841). Total bilirubin, triglycerides and uric acid were the three most important predictors of AF.

Conclusion

The risk prediction models of AF in elderly patients with CHD and T2DM based on machine learning algorithms had high diagnostic value. The prediction models constructed by RF and XGBoost were more effective. The results of this study can provide reference for the clinical prevention and treatment of AF.

Comparing the Prognostic Value of Stress Myocardial Perfusion Imaging by Conventional and Cadmium-Zinc Telluride Single-Photon Emission Computed Tomography through a Machine Learning Approach

We compared the prognostic value of myocardial perfusion imaging (MPI) by conventional- (C-) single-photon emission computed tomography (SPECT) and cadmium-zinc-telluride- (CZT-) SPECT in a cohort of patients with suspected or known coronary artery disease (CAD) using machine learning (ML) algorithms. A total of 453 consecutive patients underwent stress MPI by both C-SPECT and CZT-SPECT. The outcome was a composite end point of all-cause death, cardiac death, nonfatal myocardial infarction, or coronary revascularization procedures whichever occurred first. ML analysis performed through the implementation of random forest (RF) and k-nearest neighbors (KNN) algorithms proved that CZT-SPECT has greater accuracy than C-SPECT in detecting CAD. For both algorithms, the sensitivity of CZT-SPECT (96% for RF and 60% for KNN) was greater than that of C-SPECT (88% for RF and 53% for KNN). A preliminary univariate analysis was performed through Mann-Whitney tests separately on the features of each camera in order to understand which ones could distinguish patients who will experience an adverse event from those who will not. Then, a machine learning analysis was performed by using Matlab (v. 2019b). Tree, KNN, support vector machine (SVM), Naïve Bayes, and RF were implemented twice: first, the analysis was performed on the as-is dataset; then, since the dataset was imbalanced (patients experiencing an adverse event were lower than the others), the analysis was performed again after balancing the classes through the Synthetic Minority Oversampling Technique. According to KNN and SVM with and without balancing the classes, the accuracy (p value = 0.02 and p value = 0.01) and recall (p value = 0.001 and p value = 0.03) of the CZT-SPECT were greater than those obtained by C-SPECT in a statistically significant way. ML approach showed that although the prognostic value of stress MPI by C-SPECT and CZT-SPECT is comparable, CZT-SPECT seems to have higher accuracy and recall.