Selection of 51 predictors from 13,782 candidate multimodal features using machine learning improves coronary artery disease prediction.
Ontology highlight
ABSTRACT:
SUBMITTER: Agrawal S
PROVIDER: S-EPMC8672148 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:MotivationSelecting the optimal machine learning (ML) model for a given dataset is often challenging. Automated ML (AutoML) has emerged as a powerful tool for enabling the automatic selection of ML methods and parameter settings for the prediction of biomedical endpoints. Here, we apply the tree-based pipeline optimization tool (TPOT) to predict angiographic diagnoses of coronary artery disease (CAD). With TPOT, ML models are represented as expression trees and optimal pipelines discovered using a stochastic search method called genetic programing. We provide some guidelines for TPOT-based ML pipeline selection and optimization-based on various clinical phenotypes and high-throughput metabolic profiles in the Angiography and Genes Study (ANGES).ResultsWe analyzed nuclear magnetic resonance-derived lipoprotein and metabolite profiles in the ANGES cohort with a goal to identify the role of non-obstructive CAD patients in CAD diagnostics. We performed a comparative analysis of TPOT-generated ML pipelines with selected ML classifiers, optimized with a grid search approach, applied to two phenotypic CAD profiles. As a result, TPOT-generated ML pipelines that outperformed grid search optimized models across multiple performance metrics including balanced accuracy and area under the precision-recall curve. With the selected models, we demonstrated that the phenotypic profile that distinguishes non-obstructive CAD patients from no CAD patients is associated with higher precision, suggesting a discrepancy in the underlying processes between these phenotypes.Availability and implementationTPOT is freely available via http://epistasislab.github.io/tpot/.Supplementary informationSupplementary data are available at Bioinformatics online.
| S-EPMC7703753 | biostudies-literature
Project description: Not available
| S-EPMC11020205 | biostudies-literature
Project description:BackgroundFor Glioblastoma (GBM), various prognostic nomograms have been proposed. This study aims to evaluate machine learning models to predict patients' overall survival (OS) and progression-free survival (PFS) on the basis of clinical, pathological, semantic MRI-based, and FET-PET/CT-derived information. Finally, the value of adding treatment features was evaluated.MethodsOne hundred and eighty-nine patients were retrospectively analyzed. We assessed clinical, pathological, and treatment information. The VASARI set of semantic imaging features was determined on MRIs. Metabolic information was retained from preoperative FET-PET/CT images. We generated multiple random survival forest prediction models on a patient training set and performed internal validation. Single feature class models were created including "clinical," "pathological," "MRI-based," and "FET-PET/CT-based" models, as well as combinations. Treatment features were combined with all other features.ResultsOf all single feature class models, the MRI-based model had the highest prediction performance on the validation set for OS (C-index: 0.61 [95% confidence interval: 0.51-0.72]) and PFS (C-index: 0.61 [0.50-0.72]). The combination of all features did increase performance above all single feature class models up to C-indices of 0.70 (0.59-0.84) and 0.68 (0.57-0.78) for OS and PFS, respectively. Adding treatment information further increased prognostic performance up to C-indices of 0.73 (0.62-0.84) and 0.71 (0.60-0.81) on the validation set for OS and PFS, respectively, allowing significant stratification of patient groups for OS.ConclusionsMRI-based features were the most relevant feature class for prognostic assessment. Combining clinical, pathological, and imaging information increased predictive power for OS and PFS. A further increase was achieved by adding treatment features.
| S-EPMC6346243 | biostudies-literature
Project description:Predicting candidate genes using gene expression profiles and unbiased protein-protein interactions (PPI) contributes a lot in deciphering the pathogenesis of complex diseases. Recent studies showed that there are significant disparities in network topological features between non-disease and disease genes in protein-protein interaction settings. Integrated methods could consider their characteristics comprehensively in a biological network. In this study, we introduce a novel computational method, based on combined network topological features, to construct a combined classifier and then use it to predict candidate genes for coronary artery diseases (CAD). As a result, 276 novel candidate genes were predicted and were found to share similar functions to known disease genes. The majority of the candidate genes were cross-validated by other three methods. Our method will be useful in the search for candidate genes of other diseases.
| S-EPMC3382204 | biostudies-literature
Project description:BackgroundGenome-wide association studies (GWAS) have identified hundreds of loci associated with coronary artery disease (CAD) and blood pressure (BP) or hypertension. Many of these loci are not linked to traditional risk factors, nor do they include obvious candidate genes, complicating their functional characterization. We hypothesize that many GWAS loci associated with vascular diseases modulate endothelial functions. Endothelial cells play critical roles in regulating vascular homeostasis, such as roles in forming a selective barrier, inflammation, hemostasis, and vascular tone, and endothelial dysfunction is a hallmark of atherosclerosis and hypertension. To test this hypothesis, we generate an integrated map of gene expression, open chromatin region, and 3D interactions in resting and TNFα-treated human endothelial cells.ResultsWe show that genetic variants associated with CAD and BP are enriched in open chromatin regions identified in endothelial cells. We identify physical loops by Hi-C and link open chromatin peaks that include CAD or BP SNPs with the promoters of genes expressed in endothelial cells. This analysis highlights 991 combinations of open chromatin regions and gene promoters that map to 38 CAD and 92 BP GWAS loci. We validate one CAD locus, by engineering a deletion of the TNFα-sensitive regulatory element using CRISPR/Cas9 and measure the effect on the expression of the novel CAD candidate gene AIDA.ConclusionsOur data support an important role played by genetic variants acting in the vascular endothelium to modulate inter-individual risk in CAD and hypertension.
| S-EPMC6613242 | biostudies-literature
Project description:Background and aimsWe sought to understand the risk factor correlates of very early coronary artery calcium (CAC), and the potential investigational value of CAC phenotyping in adults aged 20-30 years.MethodsWe studied all participants aged 20-30 years at baseline (N = 373) in the Coronary Artery Calcium Consortium, a large multi-center cohort study of patients aged 18 years or older without known atherosclerotic cardiovascular disease (ASCVD) at baseline, referred for CAC scoring for clinical risk stratification. We described the prevalence of CAC in men and women, the frequency of risk factors by the presence of CAC (CAC = 0 vs CAC >0), and assessed the association between traditional non-demographic CVD risk factors (hypertension, hyperlipidemia, smoking, family history of CHD, and diabetes) and prevalent CAC, using age- and sex-adjusted logistic regression models.ResultsThe mean age of the study participants was 27.5 ± 2.4 years; 324 (86.9%) had CAC = 0, and 49 (13.1%) had CAC >0. Among the 49 participants with CAC, 38 (77.6%) were men, and median CAC score was low at 4.6. In age- and sex-adjusted models, there was a graded increase in the odds of CAC >0 with increasing traditional cardiovascular disease (CVD) risk factor burden (p = 0.001 for linear trend). Participants with ≥3 traditional risk factors had a statistically significant higher odds of having prevalent CAC (OR 5.57, 95% CI; 1.82-17.03) compared to participants with no risk factors.ConclusionsOur study demonstrates the non-negligible prevalence of CAC among very high-risk young US adults, reinforcing the critical importance of traditional risk factors in the earliest development of detectable subclinical ASCVD.
| S-EPMC7260100 | biostudies-literature
Project description:BackgroundPrecision estimation of cardiovascular risk remains the cornerstone of atherosclerotic cardiovascular disease (ASCVD) prevention. While coronary artery calcium (CAC) scoring is the best available non-invasive quantitative modality to evaluate risk of ASCVD, it excludes risk related to prior myocardial infarction, cardiomyopathy, and arrhythmia which are implicated in ASCVD. The high-dimensional and inter-correlated nature of ECG data makes it a good candidate for analysis using machine learning techniques and may provide additional prognostic information not captured by CAC. In this study, we aimed to develop a quantitative ECG risk score (eRiS) to predict major adverse cardiovascular events (MACE) alone, or when added to CAC. Further, we aimed to construct and validate a novel nomogram incorporating ECG, CAC and clinical factors for ASCVD.MethodsWe analyzed 5,864 patients with at least 1 cardiovascular risk factor who underwent CAC scoring and a standard ECG as part of the CLARIFY study (ClinicalTrials.gov Identifier: NCT04075162). Events were defined as myocardial infarction, coronary revascularization, stroke or death. A total of 649 ECG features, consisting of measurements such as amplitude and interval measurements from all deflections in the ECG waveform (53 per lead and 13 overall) were automatically extracted using a clinical software (GE Muse™ Cardiology Information System, GE Healthcare). The data was split into 4 training (Str) and internal validation (Sv) sets [Str (1): Sv (1): 50:50; Str (2): Sv (2): 60:40; Str (3): Sv (3): 70:30; Str (4): Sv (4): 80:20], and the results were compared across all the subsets. We used the ECG features derived from Str to develop eRiS. A least absolute shrinkage and selection operator-Cox (LASSO-Cox) regularization model was used for data dimension reduction, feature selection, and eRiS construction. A Cox-proportional hazards model was used to assess the benefit of using an eRiS alone (Mecg), CAC alone (Mcac) and a combination of eRiS and CAC (Mecg+cac) for MACE prediction. A nomogram (Mnom) was further constructed by integrating eRiS with CAC and demographics (age and sex). The primary endpoint of the study was the assessment of the performance of Mecg, Mcac, Mecg+cac and Mnom in predicting CV disease-free survival in ASCVD.FindingsOver a median follow-up of 14 months, 494 patients had MACE. The feature selection strategy preserved only about 18% of the features that were consistent across the various strata (Str). The Mecg model, comprising of eRiS alone was found to be significantly associated with MACE and had good discrimination of MACE (C-Index: 0.7, p = <2e-16). eRiS could predict time-to MACE (C-Index: 0.6, p = <2e-16 across all Sv). The Mecg+cac model was associated with MACE (C-index: 0.71). Model comparison showed that Mecg+cac was superior to Mecg (p = 1.8e-10) or Mcac (p < 2.2e-16) alone. The Mnom, comprising of eRiS, CAC, age and sex was associated with MACE (C-index 0.71). eRiS had the most significant contribution, followed by CAC score and other clinical variables. Further, Mnom was able to identify unique patient risk-groups based on eRiS, CAC and clinical variables.ConclusionThe use of ECG features in conjunction with CAC may allow for improved prognostication and identification of populations at risk. Future directions will involve prospective validation of the risk score and the nomogram across diverse populations with a heterogeneity of treatment effects.
| S-EPMC9580025 | biostudies-literature
Project description:ObjectiveMachine learning (ML) approaches have the potential to uncover regular patterns in multi-layered data. Here we applied self-organizing maps (SOMs) to detect such patterns with the aim to better predict in-stent restenosis (ISR) at surveillance angiography 6 to 8 months after percutaneous coronary intervention with stenting.MethodsIn prospectively collected data from 10,004 patients receiving percutaneous coronary intervention (PCI) for 15,004 lesions, we applied SOMs to predict ISR angiographically 6-8 months after index procedure. SOM findings were compared with results of conventional uni- and multivariate analyses. The predictive value of both approaches was assessed after random splitting of patients into training and test sets (50:50).ResultsConventional multivariate analyses revealed 10, mostly known, predictors for restenosis after coronary stenting: balloon-to-vessel ratio, complex lesion morphology, diabetes mellitus, left main stenting, stent type (bare metal vs. first vs. second generation drug eluting stent), stent length, stenosis severity, vessel size reduction, and prior bypass surgery. The SOM approach identified all these and nine further predictors, including chronic vessel occlusion, lesion length, and prior PCI. Moreover, the SOM-based model performed well in predicting ISR (AUC under ROC: 0.728); however, there was no meaningful advantage in predicting ISR at surveillance angiography in comparison with the conventional multivariable model (0.726, p = 0.3).ConclusionsThe agnostic SOM-based approach identified-without clinical knowledge-even more contributors to restenosis risk. In fact, SOMs applied to a large prospectively sampled cohort identified several novel predictors of restenosis after PCI. However, as compared with established covariates, ML technologies did not improve identification of patients at high risk for restenosis after PCI in a clinically relevant fashion.
| S-EPMC10142067 | biostudies-literature
Project description:Machine Learning (ML) approaches are increasingly being used in biomedical applications. Important challenges of ML include choosing the right algorithm and tuning the parameters for optimal performance. Automated ML (AutoML) methods, such as Tree-based Pipeline Optimization Tool (TPOT), have been developed to take some of the guesswork out of ML thus making this technology available to users from more diverse backgrounds. The goals of this study were to assess applicability of TPOT to genomics and to identify combinations of single nucleotide polymorphisms (SNPs) associated with coronary artery disease (CAD), with a focus on genes with high likelihood of being good CAD drug targets. We leveraged public functional genomic resources to group SNPs into biologically meaningful sets to be selected by TPOT. We applied this strategy to data from the U.K. Biobank, detecting a strikingly recurrent signal stemming from a group of 28 SNPs. Importance analysis of these SNPs uncovered functional relevance of the top SNPs to genes whose association with CAD is supported in the literature and other resources. Furthermore, we employed game-theory based metrics to study SNP contributions to individual-level TPOT predictions and discover distinct clusters of well-predicted CAD cases. The latter indicates a promising approach towards precision medicine.
| S-EPMC9291719 | biostudies-literature
Project description:Coronary artery spasm (CAS) plays an important role in the pathogenesis of ischemic heart disease, including angina pectoris, myocardial infarction, and sudden death, occurring most often from midnight to early morning. CAS is prevalent among East Asians and is associated with an aldehyde dehydrogenase 2 (ALDH2)-deficient genotype (ALDH2*2) and alcohol flushing, which is prevalent among East Asians but is virtually non-existent in other populations. ALDH2 eliminates not only acetaldehyde but also other toxic aldehydes from lipid peroxidation and tobacco smoking, thereby protecting tissues and cells from oxidative damage. Risk factors for CAS include smoking and genetic polymorphisms including those of ALDH2*2, endothelial NO synthase, paraoxonase I, and interleukin-6. Accordingly, oxidative stress, endothelial dysfunction, and low-grade chronic inflammation play an important role in the pathogenesis of CAS, leading to increased coronary smooth muscle Ca2+ sensitivity through RhoA/ROCK activation and resultant hypercontraction. Ca-channel blockers blocking the intracellular entry of Ca2+ are specifically effective for treatment for CAS.
| S-EPMC6403432 | biostudies-literature